Information sending method and communication apparatus

Abstract

Provided in the present application are an information sending method and a communication apparatus. When sending a plurality of trusted factors, a first device does not directly send the plurality of trusted factors themselves, but instead determines probability information corresponding to the plurality of trusted factors. Moreover, second probability information is determined on the basis of first probability information, and a plurality of pieces of probability information are then sent. Compared with a method of directly sending a plurality of trusted factors, the method of sending K pieces of probability information can reduce overheads.

Description

Method and communication device for sending information

[0001] This application claims priority to the Chinese patent application filed with the State Intellectual Property Office of China on April 3, 2024, with application number 202410408740.2 and invention name “Method and communication device for sending information”, the entire contents of which are incorporated by reference into this application. Technical Field

[0002] The present application relates to the field of wireless communication technology, and more specifically, to a method and a communication device for sending information. Background Art

[0003] In beam management for artificial intelligence (AI), the network configures reference signal resources for a subset of all beams. The user equipment (UE) measures these reference signal resources to obtain measurement information, which is used as input for the AI. The AI ​​predicts the measurement information corresponding to these beams and outputs information for all beams. After the UE completes inference, it reports the information of the optimal K beams, and the network performs a second round of reference signal resource configuration based on these K beams. The optimal beam obtained by the UE after the second round of scanning is the beam used for data transmission.

[0004] When AI is deployed on the UE side, the UE needs to report the output of the AI ​​model. There are generally two reporting schemes: reporting when the AI ​​model is a classification model or reporting when the AI ​​model is a regression model. If the AI ​​model is a classification model, the UE reports the identifiers (IDs) of 1 to K optimal beams to the network. If the AI ​​model is a regression model, the UE reports the IDs of the optimal K beams and the predicted RSRP.

[0005] However, the UE reports the optimal beam in this way, and the network side configures the reference signal resources for the second round of beam scanning based on the UE's report, and finally determines the beam used for data transmission. The performance of data transmission still needs to be improved. Summary of the Invention

[0006] The present application provides a method and a communication device for sending information, which can report more information to a network device with less bit overhead, thereby improving the performance of data transmission.

[0007] In a first aspect, a method for sending information is provided, which can be performed by a communication device or a module (e.g., a chip or circuit) applied to the communication device. The communication device can be a first device or a terminal device in a method embodiment. The method includes: determining K pieces of probability information, the K pieces of probability information including first probability information and second probability information, any one of the K pieces of probability information being used to determine a trust factor, the second probability information being determined based on the first probability information; and sending first information, the first information including the K pieces of probability information, where K is an integer greater than 1.

[0008] In the technical solution of the present application, the first device sends K probability information to the second device, and the K probability information is used to determine a trust factor respectively. After determining the first probability information, K-1 second probability information is determined based on the first probability information. The second probability information may be information obtained by quantifying the corresponding trust factor. By reporting the probability information, the first device can enable the second device to obtain more information. In the AI-based beam management scenario, the second device determines the configuration of the reference signal resources for the second round of beam scanning based on the K probability information, which can make the determined configuration of the reference signal resources more accurate and ultimately improve the data transmission performance. In addition, since the second probability information can be determined based on the first probability information, the first device sends K probability information, which can reduce the bit overhead compared to directly sending K trust factors.

[0009] In a second aspect, a method for receiving information is provided, which can be performed by a communication device or a module (e.g., a chip or circuit) applied to the communication device. The communication device can be a second device or a network device in a method embodiment. The method includes: receiving first information, the first information including K probability information, the K probability information including first probability information and second probability information, the second probability information being related to the first probability information, where K is an integer greater than 1.

[0010] The technical effects of the second aspect can refer to the description of the technical effects of the first aspect.

[0011] In certain implementations of the first aspect or the second aspect, the second probability information is determined based on the first probability information, including: the second probability information includes differential information of the trust factor corresponding to the second probability information compared to the trust factor corresponding to the first probability information.

[0012] In this implementation, after determining the first probability information, the second probability information may be the difference between the trust factor corresponding to the second probability information and the trust factor corresponding to the first probability information. Representing the second probability information based on the difference information can reduce bit overhead compared to directly representing the trust factor corresponding to the second probability information.

[0013] In certain implementations of the first aspect or the second aspect, the first probability information includes probability information corresponding to a reference credible factor in the K probability information, and the reference credible factor is the credible factor with the largest value or the credible factor with the smallest value among the K credible factors corresponding to the K probability information.

[0014] In this implementation, the first probability information is the probability information corresponding to the reference trust factor. By selecting an appropriate reference trust factor and determining the second probability information based on this, the bit overhead of representing the K probability information can be reduced. For example, the trust factor with the largest or smallest value is selected as the reference trust factor, and the second probability information can be the difference between the trust factor corresponding to the second probability information and the reference trust factor. If the difference between the selected reference trust factor and the trust factor corresponding to the second probability information is small, then fewer bits will be used to represent the K-1 second probability information, which can further reduce the bit overhead.

[0015] In certain implementations of the first aspect or the second aspect, the first information is further used to indicate reference signal identification information corresponding to the reference credibility factor.

[0016] In an implementation manner in which K pieces of probability information are represented based on a reference credibility factor, the first information sent by the first device may further indicate reference signal identification information corresponding to the reference credibility factor.

[0017] In certain implementations of the first aspect or the second aspect, in the first information, the reference credibility factor is arranged at the front or back or a preset position of the K credibility factors; or, in the first information, the reference signal identification information corresponding to the reference credibility factor is arranged at the front or back or a preset position of the K reference signal identification information, and the K reference signal identification information are the reference signal identification information corresponding to the K probability information respectively; or, the field in the first information indicates the reference signal identification corresponding to the reference credibility factor.

[0018] This implementation provides multiple ways for the first device to indicate the reference trust factor to the second device. For example, the reference trust factor can be a default position (for example, the front or the back) or a preset position in the sorting of K trust factors corresponding to K probability information; or it can be indicated by the position of the reference signal identification information corresponding to the reference signal factor in the K reference signal identification information, or it can be indicated by bit mapping.

[0019] In certain implementations of the first aspect or the second aspect, the K probability information include K1 probability information and K2 probability information, the K1 probability information corresponds to a first prediction time unit, the K2 probability information corresponds to a second prediction time unit, the K1 probability information includes the first probability information, and the K2 probability information includes the second probability information, wherein the second prediction time unit is earlier or later than the first prediction time unit.

[0020] In this implementation, the K probability information may correspond to K prediction time units, and can be applied to a scenario where a first device indicates relevant parameters for the K prediction time units to a second device. The relevant parameters for these K prediction time units can be represented by the "probability information" method provided in this application.

[0021] In certain implementations of the first aspect or the second aspect, the reference signal identifier corresponding to the first probability information is the same as the reference signal identifier corresponding to the second probability information.

[0022] This implementation method can be applied to AI-based beam management. When the first device reports the probability information of the future prediction time to the second device, for the prediction time unit with the same reference signal identifier (i.e., CRI), it can indicate one CRI, and at the same time, the probability information corresponding to the multiple prediction time units is reported based on the quantization method provided in this application (or quantization based on differential information).

[0023] In certain implementations of the first aspect or the second aspect, the first information is further used to indicate information of a prediction time unit corresponding to the reference credibility factor.

[0024] In an implementation involving a reference signal factor and a prediction time unit, the reference credibility factor may be a credibility factor corresponding to a certain prediction time unit.

[0025] In certain implementations of the first aspect or the second aspect, the K probability information further includes third probability information, and the third probability information is determined based on the second probability information.

[0026] In this implementation, after determining the first probability information among the K probability information, the remaining probability information can be obtained by step-by-step differentiation. For example, the second probability information is determined based on the first probability information, the third probability information is determined based on the second probability information, and so on.

[0027] In certain implementations of the first aspect or the second aspect, the third probability information is determined based on the second probability information and further includes: the third probability information includes a difference between a credibility factor corresponding to the third probability information and a credibility factor corresponding to the second probability information.

[0028] In this implementation, the third probability information may be differential information between the credibility factor corresponding to the third probability information and the credibility factor corresponding to the second probability information.

[0029] In certain implementations of the first aspect or the second aspect, the second probability information is determined based on the first probability information, including: the trust factor corresponding to the second probability information is determined in a first quantization interval, the first quantization interval is determined by a baseline trust factor and the trust factor corresponding to the first probability information, and the baseline trust factor is predefined or indicated by a network device.

[0030] In this implementation, after determining the first probability information, the second probability information can be determined based on the percentage interval corresponding to the complement of the trust factor corresponding to the first probability information, which can reduce the bit overhead of representing the trust factors corresponding to K probability information and may improve the quantization accuracy of the second probability information.

[0031] In certain implementations of the first aspect or the second aspect, the first quantization interval includes a difference between a baseline credibility factor and a credibility factor corresponding to the first probability information.

[0032] In certain implementations of the first aspect or the second aspect, the second probability information is determined based on the first probability information, including: the trust factor corresponding to the first probability information is determined in a second quantization interval, and the trust factor corresponding to the second probability information is determined in a third quantization interval, and the second quantization interval and the third quantization interval correspond to different quantization steps.

[0033] In this implementation, K pieces of probability information may correspond to K quantization intervals, and the K quantization intervals may be non-uniform.

[0034] In certain implementations of the first aspect or the second aspect, the second quantization interval and the third quantization interval correspond to different quantization steps, including: the quantization step corresponding to the second quantization interval is smaller than the quantization step corresponding to the third quantization interval.

[0035] In certain implementations of the first aspect or the second aspect, a credibility factor corresponding to any one of the K pieces of probability information is higher than a credibility factor threshold.

[0036] In this implementation, the first device may choose to report only trust factors that are higher than a trust factor threshold.

[0037] In certain implementations of the first aspect or the second aspect, the first information does not include probability information that the credibility factor is higher than a credibility factor threshold.

[0038] In this implementation, in some scenarios, the first device reports probability information corresponding to a trust factor that is less than a trust factor threshold, which can save bit overhead. For example, if the first device selects information about beams that need to be reported, if the number of beams excluded from the trust factor threshold is less than the number of beams that need to be reported, in this case, the first device can report information about beams that are less than the trust factor threshold. Since the second device already knows which beams' information needs to be reported, it can determine which beams' corresponding trust factors are greater than the trust factor threshold based on the beam information reported by the first device, and these beams greater than the trust factor threshold need to be configured with reference signals and perform beam scanning. Compared to reporting beams greater than the trust factor threshold, reporting beams less than the trust factor threshold can save bit overhead.

[0039] In certain implementations of the first aspect or the second aspect, the first information also includes beam information corresponding to each probability information in the K probability information, and the beam information includes at least one of the following: reference signal identification information; RSRP information; CSI.

[0040] In a third aspect, a communication device is provided, wherein the communication device has the function of implementing the method of the first aspect or any possible implementation thereof, or implementing the method of the second aspect or any possible implementation thereof. The functions may be implemented by hardware or by hardware executing corresponding software implementations. The hardware or software includes one or more units corresponding to the above functions.

[0041] In a fourth aspect, a communication device is provided, comprising at least one processor, wherein the at least one processor is configured to cause the communication device to execute the method of the first aspect or any possible implementation thereof; or to execute the method of the second aspect or any possible implementation thereof. Optionally, the at least one processor is coupled to at least one memory, the at least one memory being configured to store a computer program or instruction, and the at least one processor being configured to call and execute the computer program or instruction from the at least one memory, causing the communication device to execute the method of the first aspect or any possible implementation thereof; or to execute the method of the second aspect or any possible implementation thereof. The at least one processor may be included in the communication device or may be configured externally to the communication device.

[0042] In a fifth aspect, a communication device is provided, comprising a communication interface and a processing circuit, wherein the communication interface is configured to receive information and / or data to be processed and transmit the information and / or data to the processing circuit; the processing circuit is configured to process the information and / or data to execute the method of the first aspect or any possible implementation thereof; or to execute the method of the second aspect or any possible implementation thereof. Optionally, the communication interface is further configured to output the processed information and / or data.

[0043] In a sixth aspect, a computer-readable storage medium is provided, in which computer program code or instructions are stored. When the computer instructions are executed on a computer, the method in the first aspect or any one of its possible implementations is implemented; or the method in the second aspect or any one of its possible implementations is implemented.

[0044] In a seventh aspect, a computer program product is provided, comprising computer program code or instructions, which, when the computer program code or instructions are run on a computer, enables the method in the first aspect or any one of its possible implementations to be implemented; or, enables the method in the second aspect or any one of its possible implementations to be implemented.

[0045] In an eighth aspect, a wireless communication system is provided, comprising the communication device as described in the first aspect and the communication device as described in the second aspect. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] FIG1 is a schematic diagram of a communication system applicable to the communication method of an embodiment of the present application.

[0047] FIG2 is a schematic diagram of another communication system applicable to the communication method of an embodiment of the present application.

[0048] FIG3 is a schematic diagram of a possible application framework in a communication system.

[0049] Figure 4 is a schematic diagram of the AI-assisted sparse beam scanning process.

[0050] FIG5 is a schematic flowchart of the method for sending information provided in this application.

[0051] FIG6 is a schematic flowchart of sending information provided in an embodiment of the present application.

[0052] FIG7 is a schematic flowchart of sending information provided in an embodiment of the present application.

[0053] FIG8 is a schematic process of reporting cross-time domain beam information.

[0054] FIG9 is a schematic structural diagram of a communication device provided in this application.

[0055] FIG10 is a schematic structural diagram of a communication device provided in this application. DETAILED DESCRIPTION

[0056] The technical solution in this application will be described below with reference to the accompanying drawings.

[0057] The technical solutions provided in this application can be applied to various communication systems, such as: fifth generation (5G) or new radio (NR) systems, long term evolution (LTE) systems, LTE frequency division duplex (FDD) systems, LTE time division duplex (TDD) systems, wireless local area networks (WLAN) systems, satellite communication systems, future communication systems, or integrated systems of multiple systems. The technical solutions provided in this application can also be applied to device to device (D2D) communication, vehicle-to-everything (V2X) communication, machine to machine (M2M) communication, machine type communication (MTC), and Internet of Things (IoT) communication systems or other communication systems.

[0058] A network element in a communication system can send a signal to another network element or receive a signal from another network element. The signal may include information, signaling, or data, etc. The network element can also be replaced by an entity, a network entity, a device, a communication device, a communication module, a node, a communication node, etc. The embodiments of the present application are described using a device as an example. For example, a communication system may include at least one terminal device and at least one network device. The network device can send a downlink signal to the terminal device, and / or the terminal device can send an uplink signal to the network device. The first device in the embodiments of the present application can be replaced by a terminal device, and the second device can be replaced by a network device, and the two devices perform the corresponding communication method in the present application.

[0059] In addition, in order to support AI technology in wireless networks, AI nodes may also be introduced into the network.

[0060] FIG1 is a schematic diagram of a communication system applicable to the communication method of an embodiment of the present application. As shown in FIG1 , the communication system 100 may include at least one network device, such as the network device 110 shown in FIG1 ; the communication system 100 may also include at least one terminal device, such as the terminal device 120 and the terminal device 130 shown in FIG1 . The network device 110 and the terminal device (such as the terminal device 120 and the terminal device 130) can communicate via a wireless link. The communication devices in the communication system, for example, the network device 110 and the terminal device 120, can communicate via multi-antenna technology.

[0061] Figure 2 is a schematic diagram of another communication system applicable to the communication method of an embodiment of the present application. Compared to the communication system 100 shown in Figure 1, the communication system 200 shown in Figure 2 also includes an AI network element 140. AI network element 140 is used to perform AI-related operations, such as constructing a training dataset or training an AI model.

[0062] In one possible implementation, the terminal device 120 may send data related to the training of the AI ​​model to the AI ​​network element 140, which constructs a training data set and trains the AI ​​model. For example, the data related to the training of the AI ​​model may include measurement results, historical measurement results, etc. obtained by the terminal device through reference signal resource measurement. The AI ​​network element 140 may send the results of operations related to the AI ​​model to the terminal device 120. For example, the results of operations related to the AI ​​model may include at least one of the following: an AI model that has completed training, an evaluation result or a test result of the model, etc. Exemplarily, a portion of the trained AI model may be deployed on the network device 110, and another portion may be deployed on the terminal device. Alternatively, the trained AI model may be deployed on the network device 110. Alternatively, the trained AI model may be deployed on the terminal device.

[0063] It should be understood that Figure 2 illustrates only the example of a direct connection between AI network element 140 and terminal device 120. In other scenarios, AI network element 140 may also be connected to a network device. Alternatively, AI network element 140 may be simultaneously connected to network device 110 and a terminal device (e.g., terminal device 120). Alternatively, AI network element 140 may be connected to terminal device 120 through a third-party network element. This embodiment of the present application does not limit the connection relationship between the AI ​​network element and other network elements.

[0064] Optionally, the AI ​​network element 140 may also be provided as a module in a network device and / or a terminal device, for example, in the network device 110 or the terminal device 120 shown in FIG1 .

[0065] In the embodiments of this application, it mainly involves the scenario where the AI ​​model is deployed on the terminal device.

[0066] It should be noted that Figures 1 and 2 are simplified schematic diagrams for ease of understanding. 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 1 and 2. In actual applications, the communication system may include multiple network devices and multiple terminal devices. The embodiments of the present application do not limit the number of network devices and terminal devices included in the communication system.

[0067] In an embodiment of the present application, the terminal device may also be referred to as user equipment (UE), access terminal, user unit, user station, mobile station, mobile station, remote station, remote terminal, mobile device, user terminal, terminal, wireless communication device, user agent or user device.

[0068] The terminal device may be a device that provides voice / data, such as a handheld device or vehicle-mounted device with a wireless connection function. At present, some examples of terminals may include: mobile phones, tablet computers, laptop computers, PDAs, mobile internet devices (MIDs), wearable devices, virtual reality (VR) devices, augmented reality (AR) devices, wireless terminals in industrial control, wireless terminals in self-driving, wireless terminals in remote medical surgery, wireless terminals in smart grids, wireless terminals in transportation safety, wireless terminals in smart cities, wireless terminals in smart homes, cellular phones, cordless phones, session initiation protocol (SIP) phones, wireless local loop (WLL) stations, personal digital assistants (PDAs), handheld devices with wireless communication capabilities, computing devices or other processing devices connected to wireless modems, wearable devices, terminal devices in 5G networks or terminal devices in future evolved public land mobile networks (PLMNs), etc.

[0069] In the embodiments of the present application, the device for realizing the function of the terminal device can be a terminal device, or a device that can support the terminal device to realize the function, such as a chip, a chip system, a hardware circuit, a software module, or a combination of a hardware circuit and a software module. The device can be installed in the terminal device or used in conjunction with the terminal device. In the embodiments of the present application, the chip system can be composed of chips, or it can include chips and other discrete devices. In the embodiments of the present application, only the terminal device is used as an example for description.

[0070] The network device in the embodiments of the present application may include a device for communicating with a terminal device, and the network device may include an access network device or a radio access network device. For example, the network device may be a base station. The access network device in the embodiments of the present application may refer to a radio access network (RAN) node (or device) that connects the terminal device to a wireless network. The term "base station" may broadly cover the following names, or be replaced with the following names, for example: NodeB, evolved NodeB (eNB), next generation NodeB (gNB), relay station, access point, transmitting and receiving point (TRP), transmitting point (TP), master station, secondary station, motor slide retainer (MSR) node, home base station, network controller, access node, wireless node, access point (AP), transmission node, transceiver node, baseband unit (BBU), remote radio unit (RRU), active antenna unit (AAU), remote radio head (RRH), central unit (CU), distributed unit (DU), radio unit (RU), positioning node, etc. A base station may be a macro base station, a micro base station, a relay node, a donor node, or a combination thereof. The base station may also refer to a communication module, modem or chip that is set in the aforementioned equipment or device. The base station may also be a mobile switching center and a device that performs the base station function in D2D, V2X, and M2M communications, a network side device in a 6G network, a device that performs the base station function in future communication systems, etc. The base station can support networks with the same or different access technologies. Optionally, the RAN node may also be a server, a wearable device, a vehicle or an on-board device, etc. For example, the access network device in the vehicle to everything (V2X) technology may be a road side unit (RSU). The embodiments of the present application do not limit the specific technology and specific device form adopted by the network equipment.

[0071] Base stations can be fixed or mobile. For example, a helicopter or drone can be configured to act as a mobile base station, and one or more cells can move based on the location of the mobile base station. In other examples, a helicopter or drone can be configured to act as a device that communicates with another base station.

[0072] In some deployments, the network devices mentioned in the embodiments of the present application may include a CU, a DU, or both a CU and a DU, or a control plane CU node (central unit-control plane (CU-CP)), a user plane CU node (central unit-user plane (CU-UP)), and a DU node. For example, the network devices may include a gNB-CU-CP, a gNB-CU-UP, and a gNB-DU.

[0073] In some deployments, multiple RAN nodes collaborate to assist terminals in achieving wireless access, with different RAN nodes implementing portions of the base station's functionality. For example, a RAN node can be a CU, DU, CU-CP, CU-UP, or RU. The CU and DU can be separate or included in the same network element, such as the BBU. The RU can be included in a radio frequency device or radio unit, such as an RRU, AAU, or RRH.

[0074] In different systems, CU (or CU-CP and CU-UP), DU or RU may also have different names, but those skilled in the art can understand their meanings. For example, in an open radio access network (open RAN, ORAN / O-RAN) system, CU may also be called open CU (open CU, O-CU), and DU may also be called open DU (open DU, O-DU). CU-CP may also be called O-CU-CP, CU-UP may also be called O-CU-UP, and RU may also be called O-RU. Any unit of CU (or CU-CP, CU-UP), DU and RU in this application may be implemented by a software module, a hardware module, or a combination of a software module and a hardware module.

[0075] In the embodiments of the present application, the device for implementing the function of the network device can be a network device; it can also be a device that can support the network device to implement the function, such as a chip system, a hardware circuit, a software module, or a combination of a hardware circuit and a software module. The device can be installed in the network device or used in conjunction with the network device. In the embodiments of the present application, only the device for implementing the function of the network device is used as an example to illustrate, and does not constitute a limitation on the embodiments of the present application.

[0076] Optionally, the AI ​​node can be deployed in one or more of the following locations in the communication system: access network equipment, terminal equipment, or core network equipment. Alternatively, the AI ​​node can be deployed separately, for example, in a location other than any of the above devices, such as a host or cloud server in an over-the-top (OTT) system. The AI ​​node can communicate with other devices in the communication system, such as one or more of the following: network equipment, terminal equipment, or core network elements.

[0077] It is understood that this application does not limit the number of AI nodes. For example, when there are multiple AI nodes, the multiple AI nodes can be divided based on function, such as different AI nodes responsible for different functions. In addition, the AI ​​node can be an AI network element or an AI module.

[0078] It can also be understood that AI nodes can be independent devices, or they can be integrated into the same device to implement different functions, or they can be network elements in hardware devices, or they can be software functions running on dedicated hardware, or they can be virtualized functions instantiated on a platform (for example, a cloud platform). This application does not limit the specific form of the above-mentioned AI nodes.

[0079] Figure 3 is a schematic diagram of a possible application framework in a communication system. As shown in Figure 3, network elements in the communication system are connected through interfaces (such as NG interfaces, Xn interfaces, etc.) or air interfaces. These network element nodes, such as core network equipment, access network nodes (RAN nodes), terminals or one or more devices in operations, administration and maintenance (OAM) are provided with one or more AI modules (for clarity, only one is shown in Figure 3). The access network node can be a separate RAN node or can include multiple RAN nodes, for example, including CU and DU. The CU and / or DU can also be provided with one or more AI modules. Optionally, the CU can also be split into CU-CP and CU-UP. One or more AI models are provided in the CU-CP and / or CU-UP.

[0080] The AI ​​module is used to implement the corresponding AI function. The AI ​​modules deployed in different network elements may be the same or different. The model of the AI ​​module can implement different functions according to different parameter configurations. The model of the AI ​​module can be configured based on one or more of the following parameters: structural parameters (such as the number of neural network layers, the width of the neural network, the connection relationship between layers, the weight of the neuron, the activation function of the neuron, or at least one of the bias in the activation function), input parameters (such as the type of input parameters and / or the dimension of the input parameters), or output parameters (such as the type of output parameters and / or the dimension of the output parameters). Among them, the bias in the activation function can also be called the bias of the neural network.

[0081] An AI module can have 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 on the same node or device.

[0082] The following is a brief introduction to the beam management related technologies involved in the embodiments of this application.

[0083] In beam management, beam selection is primarily accomplished through reference signals and corresponding beam measurements. Specifically, reference signals primarily 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), the Secondary Synchronization Signal (SSS), the Physical Broadcast Channel (PBCH), and the Demodulation Reference Signal (DMRS). The SSB is transmitted periodically according to the cell configuration and is used not only for beam management but also for initial access, time-frequency synchronization, and other purposes. Simply put, the SSB signal can be considered a wide-beam signal. Correspondingly, the CSI-RS signal is a user-level signal, with the network configuring one or more sets of CSI-RS resources for each user based on actual conditions. Similarly, the CSI-RS signal is used not only for beam management but also for channel quality measurement, and can be simply understood as a narrow-beam signal.

[0084] The purpose of beam management is to establish and maintain a set of suitable beam pairs, that is, to select a suitable transmit beam (direction) at the transmitter and a suitable receive beam (direction) at the receiver. Together, they form a set of beam pairs to maintain a good wireless connection. We call this process service beam selection. In some scenarios, due to environmental changes, the originally established beam pairs may be blocked, and the base station and UE do not have enough time to adjust the beams. At this time, beam failure recovery can be used to quickly select and establish another set of beam pairs. Since this application is mainly aimed at service beam selection scenarios, the beam recovery process will not be described in detail.

[0085] For AI-based beam management, if the AI ​​model is deployed on the UE side, the network side configures the reference signal resources corresponding to some of the beams in all beams, allowing the UE to complete the scanning of some beams to obtain specific measurement results. These measurement results serve as the input of the AI ​​model. The AI ​​model predicts the information of all beams based on the measurement information of some beams.

[0086] For beam management, after the UE completes inference, it needs to report the information of the optimal K beams, and the network side needs to perform a second round of reference signal configuration for these K beams. The optimal beam obtained after the UE completes the second round of scanning is the beam used for data transmission. It is worth noting that the second round of beam scanning does not involve the access of the AI ​​model.

[0087] Figure 4 is a schematic diagram of the AI-assisted sparse beam scanning process. Assuming that the precoding matrix in the network-side codebook corresponds to 64 shaped beams, in the AI-assisted (i.e., AI-model-based) sparse beam scanning scheme, only some of the beams in the codebook need to be scanned, such as the 16 beams marked in Figure 4. There are many ways to select some beams from the codebook for scanning, and each selected beam combination is called a sparse beam pattern. The network side uses the precoding matrix in the sparse beam pattern for precoding and sends a reference signal. The terminal device inputs the measurement results of the reference signal into the AI ​​model for inference, and the AI ​​model outputs the indexes of K beams, also called the indexes of Top-K beams. It should be noted that the K beams are K of all 64 shaped beams in the codebook, and are not limited to the K shaped beams contained in the sparse beam pattern. The terminal device feeds back the index of the Top-K beam to the network device. Wherein, K is a positive integer.

[0088] When the AI ​​model is deployed on the UE side, the UE needs to report the output of the AI ​​model. If the UE-side AI model is a classification model, the AI ​​model output is the probability of each beam being the optimal beam. The UE compares the probabilities to find 1 to K optimal beams and reports the IDs of these 1 to K optimal beams. These are used by the network to configure reference signal resources for the second round of beam scanning. If the UE-side AI model is a regression model, the AI ​​model output is the RSRP of each beam. The UE compares the RSRP to identify the K optimal beams and reports the predicted RSRP and beam identifier (ID) of these K optimal beams.

[0089] Practice has shown that when the UE reports the beam IDs of 1 to K optimal beams, or predicts the RSRP and beam ID, and the network configures the reference signal resources for the second round of beam scanning based on the report, the performance of the optimal beam for data transmission determined in this way still needs to be improved when used for actual data transmission.

[0090] To this end, the present application provides a method for sending information, and proposes that after the UE selects K optimal beams based on the AI ​​model, when reporting the information of these K optimal beams, in addition to reporting the beam ID, it can also report the probability information of these K beams. In an embodiment of the present application, K is an integer greater than 1. When the AI ​​model deployed on the UE side is a classification model, the probability information of each of the K beams is used to indicate the probability that the beam is predicted to be the optimal beam; when the AI ​​model deployed on the UE side is of the regression type, the probability information of each of the K beams is used to indicate the confidence of the predicted RSRP of the beam.

[0091] Therefore, the UE needs to report multiple probability information (the case of a single probability information is not considered in this application) to the network. Considering that probabilities or confidence levels are often percentages, directly reporting their actual values ​​requires a high number of bits. For example, for a probability value of 90%, directly representing this value may require 7 bits. Assuming that the UE selects 6 optimal beams for reporting, the reporting overhead required is 42 bits. Clearly, this results in a significant bit overhead.

[0092] Therefore, the present application further provides a method for sending information, which can reduce the bit overhead of information transmission for transmission scenarios with percentages such as probability and confidence level of predicted RSRP in beam management scenarios.

[0093] It should be noted that although the technical solution of this application is proposed in the beam management scenario, it can also be used in other application scenarios. As long as the information sent in these application scenarios has characteristics similar to the probability or confidence information in the beam management scenario, the technical solution provided by this application can be used.

[0094] In the technical solution proposed in the present application, a quantization method is proposed for percentages such as probabilities or confidence levels whose values ​​are less than 100%. In general, one of the K percentages is selected (for the convenience of description, referred to as the first percentage) and the first percentage is expressed in a high-precision form. For example, in the above example, 7 bits are used to report 90%, but for the other K-1 percentages, some quantization methods can be used to quantize them, and then the quantized information is reported, where K is an integer greater than 1. It is important to note that in the embodiment of the present application, these K percentages are not simply quantized, because it can be noted that the first percentage of the K percentages is expressed with high precision, while the quantization of the remaining K-1 percentages is related to the first percentage. Specifically, how the quantization of the remaining K-1 percentages is related to the first percentage is related to the specific quantization process, which will be described in detail below.

[0095] Alternatively, the first percentile may be represented directly as its actual value, or may be represented after processing the first percentile within an acceptable information loss range. The precision of representing other percentiles may be lower than or equal to the precision of representing the first percentile.

[0096] The method for sending information provided by this application is described in detail below with reference to FIG5 .

[0097] FIG5 is a schematic flowchart of the method for sending information provided in this application.

[0098] 210. The first device determines K pieces of probability information, where the K pieces of probability information include first probability information and second probability information. Any piece of the K pieces of probability information is used to determine a trust factor. The second probability information is determined based on the first probability information.

[0099] In the embodiment of the present application, any one of the K probability information is used to determine a trust factor. As an example, the trust factor includes any one of the following:

[0100] The predicted probability or predicted confidence of the reference signal identification information;

[0101] The predicted probability or prediction confidence of RSRP;

[0102] The prediction probability or prediction confidence of (channel state information, CSI).

[0103] It can be seen that the credibility factor can essentially be a percentage less than 100%, such as probability or confidence, etc. Therefore, the credibility factor in the embodiment of the present application can also adopt other names, or represent other parameters besides probability or confidence.

[0104] CSI is a type of channel information. Based on the channel information, the network device can decide one or more of the resources, modulation and coding scheme (MCS) and precoding configurations of the downlink or uplink data channel of the scheduling terminal device. It can be understood that channel information can reflect channel characteristics, channel quality, etc. Channel information can also be called CSI, or channel environment information. It can be understood that the CSI in this application is not limited to traditional CSI, such as channel quality indication (CQI), precoding matrix indicator (PMI), rank indicator (RI), channel state information reference signal resource indicator (CSI-RS CRI), and can also be channel response information, such as channel response matrix, precoding matrix, precoding vector, eigenvector, eigenmatrix, channel vector, channel matrix, (signal to interference plus noise ratio, SINR) and one or more of the above.

[0105] As an example, in the application scenario of AI-based beam management, the trust factor can be the predicted probability or prediction confidence of reference signal identification information. In other application scenarios, the trust factor can also take other forms, such as the predicted probability or prediction confidence of RSRP, the predicted probability or prediction confidence of CSI, etc.

[0106] As mentioned above, in AI-based beam management, if the AI ​​model deployed on the UE side is a classification model, the trust factor can be the predicted probability of each beam output by the AI ​​model becoming the optimal beam. Alternatively, if the AI ​​model deployed on the UE side is a regression model, the trust factor can be the confidence level of the predicted RSRP of each beam output by the AI ​​model. Therefore, in AI-based beam management, the process of the AI ​​model inputting and outputting the trust factor is essentially AI reasoning. Therefore, the probability or confidence level output by the AI ​​model can be called reasoning probability or reasoning confidence level, but is not limited to this name. It can be understood that, without loss of generality, the trust factor can be a numerical value in the form of a percentage less than 100% of any parameter in the data processing process, and the data processing process can be not limited to any scenario. Therefore, the trust factor can also be called processing probability, processing confidence level, etc., without limitation.

[0107] In addition, for a classification model, the output of the AI ​​model is the probability that each beam becomes the optimal beam, and the probability that each beam becomes the optimal beam can be used to construct a credibility factor.

[0108] For regression models, the AI ​​model output can include RSRP and the corresponding confidence level. During training, the AI ​​training label is the measured RSRP for each beam, and the initial confidence level can be set to 100%. If there is a difference between the predicted RSRP and the actual measured RSRP, the confidence level of this prediction can be constructed by using the difference between the predicted and measured RSRP. This difference is then input into the loss function for AI backpropagation to update the model parameters, ultimately determining the confidence level corresponding to the predicted RSRP. In other words, the model parameters of the AI ​​model can include the confidence level of the predicted RSRP.

[0109] In the embodiment of the present application, the reference signal resource may also be referred to as a reference signal, or a beam, etc. Therefore, the reference signal identification information may also be replaced by beam identification information.

[0110] Based on the above examples of trust factors, it can be seen that the trust factors in the embodiments of the present application can be for reference signal identification, RSRP, or CSI. Therefore, in addition to AI-based beam management, it can also be applied to other scenarios that require predicting the probability of RSRP or CSI or the confidence of the predicted value. As an example, in a scenario where the UE predicts CSI at a future time based on historical CSI, the above trust factor can be the predicted value of CSI at the future time or the confidence of the predicted value.

[0111] In the embodiment of the present application, the K pieces of probability information are information determined by the first device to be sent to the second device. The K pieces of probability information are processed and suitable for transmission. Directly reporting the K trust factors by the first device would consume a high bit overhead. To this end, the first device processes the K trust factors to obtain K pieces of probability information that correspond one to one. Sending K pieces of probability information saves bit overhead compared to sending K trust factors. This is because the second piece of probability information in the K pieces of probability information is determined based on the first piece of probability information, as will be explained in detail below.

[0112] In some implementations, one or more of the K probability information may be the actual value of the corresponding credibility factor, such as the actual predicted probability value or the predicted confidence level. For example, if the credibility factor is the predicted probability of the reference signal identification information, and the predicted probability is 65%, then the probability information corresponding to the credibility factor is 65%.

[0113] In other implementations, one or more of the K probability information may be the numerical value of the corresponding credibility factor after processing according to certain rules. For example, the probability information corresponding to the credibility factor is represented by the percentage threshold corresponding to the credibility factor, or the numerical value corresponding to the percentage threshold. As an example, the probability information corresponding to the credibility factor is represented by the percentage threshold corresponding to the credibility factor. Assuming that the credibility factor is the predicted probability of the reference signal identification information, the predicted probability is 65.88%, and the credibility factor can be divided into three intervals: 0-50% (including 50%), 50%-70% (including 70%), and above 70%. Each interval includes its lower limit but does not include its upper limit. For example, the interval of 0-50% includes 50%, and the interval of 50%-70% does not include 50% but includes 70%. Among them, the credibility factor falling within the interval of 0-50% (including 50%) is represented by 50%, and the credibility factor falling within the interval of 50%-70% (including 70%) is represented by 70%. Therefore, if the predicted probability is 65.88%, it can be represented by 70%. In this example, the probability information of the predicted probability (i.e., 65.88%) after processing is 70%. As another example, the probability information corresponding to the credibility factor is represented by the numerical value corresponding to the percentage threshold, for example, 0 corresponds to 0-10% (including 10%), 1 corresponds to 10%-20% (excluding 10% and including 20%), and so on. In this way, the probability information of a credibility factor can be represented by a specific numerical value, which can save bit overhead.

[0114] The above two implementations are applicable to the first probability information or the second probability information among the K probability information.

[0115] Generally speaking, it is important to note that in the embodiments of the present application, the second probability information is determined based on the first probability information, and the first probability information can be represented with higher precision. However, the representation precision of the second probability information may be equal to or lower than the representation precision of the first probability information, depending on the specific value of the credibility factor corresponding to the second probability information after the first probability information is determined. For example, after the first probability information is represented with high precision, if the credibility factor corresponding to the remaining second probability information falls within a smaller numerical range, the quantization precision of this smaller numerical range can be improved in this case.

[0116] The process of the first device processing the trust factor into probability information can be implemented in multiple ways.

[0117] As an example, in one possible implementation, after the first device obtains K trusted factors, it uses high precision to represent the trusted factor with the largest value, such as the actual value of the trusted factor with the largest value, without any processing; for the remaining K-1 trusted factors, multiple quantization intervals are used, and the identifiers of the multiple quantization intervals are used to represent the K-1 trusted factors, so as to reduce the bit overhead of reporting these K trusted factors.

[0118] For example, assuming the credibility factor is the predicted probability of beam identification information, if the AI ​​model deployed on the UE side is a classification model, the sum of the probabilities of all beams becoming the optimal beam is 1. If the maximum predicted probability among the K predicted probabilities corresponding to all K optimal beams is 65%, 65% is directly represented with high precision to determine the first probability information. In addition, for the remaining K-1 predicted probabilities corresponding to the K-1 optimal beams, the sum of their predicted probabilities does not exceed 35%. If the 0-35% interval is quantized with a gradient of 10%, four quantization intervals can be obtained: 0-10% (inclusive), 10%-20% (inclusive), 10%-30% (inclusive), and 10%-40% (inclusive). These four intervals can be represented by 2 bits, and the quantization identifiers of these four quantization intervals can be 00, 01, 10, and 11, respectively. Assuming that a 5% quantization gradient is used for quantization, a quantization interval with a smaller granularity will be obtained. In this way, the 0-35% interval can be quantized into 7 intervals, namely 0-5% (including 5%), 5%-10% (including 10%), ..., and 30%-35%. The quantization identifiers of these 7 quantization intervals can be represented by 3 bits.

[0119] In the above example, the second probability information is directly determined by quantizing the credibility factor. In other examples, the second probability information can be determined by superimposing the differential processing and the quantization processing. This differential and quantization processing is hereinafter referred to as a quantization method based on differential information.

[0120] 1. Quantification based on differential information.

[0121] As an example, the second probability information includes differential information between the trust factor corresponding to the second probability information and the trust factor corresponding to the first probability information. The differential information may include: a difference between the trust factor corresponding to the second probability information and the trust factor corresponding to the first probability information.

[0122] For example, taking the credibility factor as the predicted probability as an example, assuming K = 3, and the AI ​​model deployed on the UE side is of regression type, assuming that the maximum predicted probability among the K predicted probabilities corresponding to the three optimal beams is 50%, then 50% is directly represented with high precision to determine the first probability information. In addition, if the two predicted probabilities corresponding to the remaining two optimal beams are 40% and 30% respectively, the differences between these two predicted probabilities and the first predicted probability are 10% and 20% respectively, that is, two second probability information. If based on the differential information without quantization, the two second probability information are 10% and 20% respectively. Alternatively, based on the differential information, quantization is performed again, and the differences of 10% and 20% are represented by the identifiers of the quantization intervals according to a gradient of 10%, for example, 0 represents the quantization interval of 0 to 10% (including 10%), and 1 represents the quantization interval of 10% to 20% (including 20%). As a result, the two second probability information determined by the first device are 0 and 1 respectively. Of course, in this example, the first device sends K pieces of probability information based on differential information, or sends K pieces of probability information based on differential information and quantization processing. The first device and the second device reach a consensus, which can be agreed in advance, or specified in the protocol standard, or instructed by one party to the other party, or implemented by other commonly used technologies in the field, without limitation.

[0123] For another example, if the credibility factor corresponding to the first probability information is 57% and the credibility factor corresponding to the second probability information is 10%, then the difference between the credibility factor corresponding to the second probability information and the credibility factor corresponding to the first probability information is 47%. In this example, the first probability information can be 57% and the second probability information can be 47%.

[0124] Optionally, in the embodiment of the present application, the difference between the credibility factors corresponding to the probability information can be a linear value or a dB value, which is not limited and will not be repeated in the following embodiments.

[0125] In the previous example, the first probability information is the probability information corresponding to the trust factor with the largest value among the K trust factors. As another example, the first probability information may be the probability information corresponding to the reference trust factor among the K trust factors. The reference trust factor may be the trust factor with the largest value among the K trust factors or the trust factor with the smallest value.

[0126] In this implementation, in addition to including K probability information, the first information may also indicate reference signal identification information corresponding to the reference credibility factor.

[0127] For the K trust factors corresponding to the K probability information, the reference trust factor can be arranged at any position of the K trust factors, such as the front, the back or the preset position; or, the K trust factors correspond to K reference signal identification information, wherein the reference signal identification information corresponding to the reference trust factor (such as the first reference signal information identification) is arranged at the front, the back or the preset position of the K reference signal identification information; or, one or more fields in the first information indicate the reference signal identification information corresponding to the reference trust factor.

[0128] In an embodiment of the present application, the reference signal identification information may also be replaced by beam identification information. The reference signal identification information or beam identification information may be: a CSI-RS resource indicator (CSI-RS resource indicator, CRI) or an indication method based on a bitmap, wherein any bit in the bitmap corresponds to a beam identifier or a reference signal identifier. In the bitmap, the bit value corresponding to the reported reference signal identifier is 1, and the bit value corresponding to the unreported reference signal identifier is 0. The reference credibility factor is a credibility factor corresponding to a reference signal identifier in the reported reference signal identifier.

[0129] Optionally, in the quantization method based on differential information, a possible implementation is based on time domain differential.

[0130] As an example, the K pieces of probability information include K1 pieces of probability information and K2 pieces of probability information. The K1 pieces of probability information correspond to a first prediction time unit, and the K2 pieces of probability information correspond to a second prediction time unit. The K1 pieces of probability information include the first probability information, and the K2 pieces of probability information include the second probability information. The second prediction time unit is earlier or later than the first prediction time unit.

[0131] In other words, K probability information corresponds to K prediction time units, which means that the K prediction time units are K time units in the future. To clearly describe the prediction time unit corresponding to the first probability information and the prediction time unit corresponding to the second probability information in the K probability information, they are defined as the first prediction time unit and the second prediction time unit, respectively. It can be understood that the first prediction time unit and the second prediction time unit are different time units.

[0132] Optionally, the reference signal identification information corresponding to the first probability information is the same as the reference signal identification information corresponding to the second probability information. In other words, when the two prediction time units are exactly the same, the probability information corresponding to the two prediction time units can be differentiated. For example, for reporting the probability information of each of the two time units, the first device may need to make two separate reports, but considering that the reference signal identifiers (i.e., CRIs) corresponding to the two time units are the same, one CRI can be indicated, but the probability information corresponding to the two time units can be reported differentially from each other.

[0133] Optionally, in a time-domain-based differential solution, the first information may further indicate information about the prediction time unit corresponding to the reference credible factor. For example, if the reference credible factor is the credible factor with the largest value among the K credible factors, the first information may further indicate the prediction time unit corresponding to the credible factor with the largest value.

[0134] In the difference-based approach, another possible implementation is multi-level difference.

[0135] As an example, the K probability information includes the third probability information, and the third probability information is determined based on the second probability information. In combination with the above introduction, it can be seen that in these K probability information, the second probability information is determined based on the first probability information, the third probability information is determined based on the second probability information, and so on. When there are more probability information, the latter probability information is determined based on the previous probability information. The difference between two adjacent probability information is regarded as a first-level difference. When there are multiple probability information and each adjacent two probability information is differentiated, multi-level differences are involved. Optionally, the adjacent here can be determined by arranging the K credible factors in a certain order, for example, in the order of the values ​​of the credible factors from large to small or from small to large, but it is not limited to this. For example, in the time domain-based differential scheme, the K credible factors can also be arranged from front to back according to the order of the prediction time units, or the K credible factors can also be arranged in a random order or in an order determined by other methods.

[0136] 2. Quantification of differential information based on complement.

[0137] In this implementation, the second probability information is determined based on the first probability information, and may include: the trust factor corresponding to the second probability information is determined in a first quantization interval, the first quantization interval is determined by a baseline trust factor and the trust factor corresponding to the first probability information, and the baseline trust factor is predefined or indicated by the network device.

[0138] For example, the value of the credibility factor corresponding to the first probability information is 60%, and the complement of the credibility factor corresponding to the first probability information is 1-60%=40%. The baseline credibility factor can refer to the granularity (or quantization step) of quantizing the percentage interval corresponding to the complement. For example, assuming that the baseline credibility factor is 10%, that is, according to the granularity of 10%, the percentage interval of 0-40% is quantized, and 4 first quantization intervals can be obtained, corresponding to 0-10%, 10%-20%, 20%-30%, and 30%-40% respectively. The second probability information other than the first probability information can be determined by the corresponding first quantization interval. For example, if the table identifiers of the four first quantization intervals are used to represent the second probability information respectively, then 2 bits (a total of 4 values) can represent the percentage interval of 0-40%.

[0139] Optionally, when this implementation is used for a classification AI model, in addition to being able to represent K probability information with a lower bit overhead, it may also improve the representation accuracy of the second probability information. The reason is that, as mentioned above, in the classification AI model, the sum of the probabilities of all beams becoming the optimal beam is 1. If the probability of a certain beam (for example, called the first beam) becoming the optimal beam is already large, and the sum of the probabilities of all beams becoming the optimal beam is 1, then the probabilities of each beam other than the first beam becoming the optimal beam will fall within a smaller range. The smaller range is 1 minus the probability of the first beam becoming the optimal beam, or the complement of the probability of the first beam becoming the optimal beam. If the probability of the first beam becoming the optimal beam is determined as the first probability information, and the remaining second probability information is determined on this basis, since the second probability information itself is in a smaller numerical range, a smaller quantization granularity can be used to quantize the percentage interval corresponding to the complement, thereby improving the quantization accuracy of the second probability information. For example, if the credibility factor corresponding to the first probability information is 70%, then the complement of the credibility factor corresponding to the first probability information is 30%. Assuming the baseline credibility factor is 5%, the percentage interval corresponding to the complement can be divided into 6 quantization intervals, with a smaller quantization granularity. If the baseline credibility factor is 10%, compared to the baseline credibility factor of 5%, the quantization interval is reduced. In this case, the number of bits of the second probability information can be increased to carry more information and improve the representation accuracy of the second probability information.

[0140] As an example, the first quantization interval includes: a difference between a reference credibility factor and a credibility factor corresponding to the first probability information. Optionally, the difference may be a linear value or a dB value.

[0141] As an example, the first quantization interval can also be determined based on the baseline credibility factor and the credibility factor corresponding to the first probability information and other information or in combination with other calculation methods, for example, based on the baseline credibility factor, the credibility factor corresponding to the first probability information and mathematical operations (such as division, log, etc.).

[0142] 3. Non-uniform quantization.

[0143] In the above quantization method, if the granularity of the quantization interval is consistent, it refers to uniform quantization. For example, if quantization is performed at a granularity of 10%, the quantization granularity corresponding to each two adjacent quantization intervals is the same. As another implementation, the quantization granularity can be more than one. For example, the percentage interval from 0 to 100% is quantized into 4 quantization intervals of 0-5% (including 5%), 5%-30% (including 30%), 30%-60% (including 60%), and greater than 60% (excluding 60%). The quantization steps are 5%, 25%, 30%, and 40% respectively. In the quantization process, if two or more quantization steps are involved and the quantization steps are not completely equal, it is non-uniform quantization as mentioned in the embodiments of this application.

[0144] In non-uniform quantization, the second probability information is determined based on the first probability information, including: the trust factor corresponding to the first probability information is determined in the second quantization interval, the trust factor corresponding to the second probability information is determined in the third quantization interval, and the second quantization interval and the third quantization interval correspond to different quantization steps. Continuing with the above example, assuming that the AI ​​model is a regression model, K=3, and the trust factors corresponding to the K probability information are 65% (the trust factor corresponding to the first probability information), 13% and 40% (the trust factors corresponding to the two second probability information), and 5% to 30% (including 30%). Then, the trust factor corresponding to the first probability factor is determined in quantization interval 4, and the trust factors corresponding to the two second probability information are determined in quantization interval 2 and quantization interval 3, respectively.

[0145] It should be understood that the second quantization interval and the third quantization interval are used as examples for explanation here. By analogy, it can be known that when there are multiple probability information and multiple quantization steps, how to perform quantization is not described in detail.

[0146] Optionally, the step corresponding to the second quantization interval is smaller than the step corresponding to the third quantization interval. As an example, the quantization steps can be arranged in a certain order from small to large, or from large to small, or can be randomly set according to the requirements of information representation, without conforming to any rules and without limitation.

[0147] 4. The K probability information is the probability information filtered by the first device and needs to be sent to the second device.

[0148] Based on the sparse beam scanning process shown in Figure 4, after the first round of beam scanning, the UE uses the AI ​​model to perform inference and determine K optimal beams. However, when the first device sends the optimal beam information to the second device, it can only send information about some of the K optimal beams. In other words, some of the optimal beam information can be discarded.

[0149] The K probability information mentioned in the embodiment of the present application refers to the information of the K optimal beams that need to be sent after screening, and is the information after quantization processing.

[0150] As an example, the trust factor corresponding to any one of the K probability information is higher than the trust factor threshold. That is to say, if the first device determines K trust factors, among which the trust factors below the trust factor threshold are not sent. Therefore, the first information does not include probability information corresponding to trust factors below the trust factor threshold, or in other words, the trust factor corresponding to any one of the K probability information included in the first information is equal to or greater than the trust factor threshold. In addition, optionally, for the K probability information included in the first information, the first information may also include beam information corresponding to the K probability information. As an example, the beam information may include one or more of the following: reference signal identification information, RSRP information, or CSI.

[0151] 220. Send first information, and the second device receives the first information, where the first information includes the K probability information.

[0152] For the second device, the second probability information is related to the first probability information.

[0153] Optionally, method 200 may further include step 230 .

[0154] 230. The second device determines information provided by the K probability information based on the K probability information.

[0155] Since the second device and the first device have reached a consensus on the information processing method, the second device can determine the information provided by the K probability information based on the K probability information. The information provided by the K probability information refers to the information that the second device can obtain based on the K probability information. For example, if the first probability information is the actual value of the trust factor corresponding to the first probability information represented by high precision, the second device can obtain the trust factor corresponding to the first probability information; at the same time, if the second probability information is represented by a quantization interval identifier, the second device cannot determine the actual value of the trust factor corresponding to the second probability information, but based on the quantization interval identifier, it can obtain the quantization interval corresponding to each second probability information, thereby having a coarse-grained understanding of the numerical range of the trust factor corresponding to the second probability information.

[0156] Based on the information provided by the K probability information, the second device can perform other processing or operations. For example, in beam management based on the AI ​​model, the first device is a terminal device and the second device is a network device. After the network device obtains the K probability information fed back by the terminal device, it configures the reference signal resources for the second round of beam scanning based on the K probability information to support the terminal device to perform the second round of beam scanning.

[0157] In an embodiment of the present application, after the first device determines K probability information, when sending K probability information to the second device, the second probability information is determined based on the first probability information. Compared to directly reporting K trust factors, the method of reporting K probability information provided by the present application can reduce overhead.

[0158] In the embodiments of the present application, the first device may be a terminal-side device, for example, a base station, and the second device may be a network-side device. The network-side device may be a network device, or a module (such as a chip) within the network device, or software (such as a control subsystem) that includes network device functions, or other devices that communicate with the network device, such as an AI network element, which is a server, such as an OTT device or a cloud server. The terminal-side device may be a terminal device, such as a UE, or a module (such as a chip) within the terminal device, or software (such as a control subsystem) that includes terminal device functions, or other devices that communicate with the terminal device, such as an AI network element, which is a server, such as an OTT device or a cloud server. The above describes in detail the process by which the first device quantizes and transmits K probability information. Several examples are provided below to illustrate the specific application of this quantized reporting method. It should be understood that the following description assumes that the first device is a UE and the second device is a network device. The UE can be replaced with the first device, and the network device can be replaced with the second device. In addition, when the AI ​​model is set on a server that communicates with a terminal device, the probability information determined by the AI ​​model can be sent to a network side device, such as a network device, through the terminal device, and the terminal device can send the obtained measurement results to the server to perform operations on the AI ​​model, such as reasoning, training or monitoring.

[0159] Example 1

[0160] If the AI ​​model deployed on the UE side is a classification model, the output of the AI ​​model is the probability of each beam becoming the optimal beam. Specifically, the UE obtains the measurement results of N beams through the first round of beam scanning. The measurement results of these N beams are used as the input of the AI ​​model to determine the K beams and the probability of each of these K beams becoming the optimal beam. It should be noted that these K beams are the global optimal beams, not K beams out of N beams. If the UE directly reports the probabilities corresponding to each of the K beams, it will bring huge overhead. To this end, the UE can use the method provided in this application to report K probability information. According to the above embodiments, the UE can determine more than K (for example, Q) optimal beams, but the final reporting amount is K probability information. In this implementation, some beam information is discarded and not reported.

[0161] FIG6 is a schematic flowchart of sending information provided in an embodiment of the present application.

[0162] 601. The network device configures reference signal resources, where the reference signal resources are used by the UE to perform a first round of beam scanning.

[0163] 602. The UE measures the reference signal resources and determines probability information based on the measurement results of the reference signal resources and the AI ​​model.

[0164] As described above, the reference signal resources configured by the network device are a subset of the total reference signal resources. The UE measures this subset of reference signal resources and obtains measurement results for this subset of reference signal resources. These measurement results can serve as input to the AI ​​model deployed on the UE side. If the AI ​​model is a classification model, the UE uses the AI ​​model for inference, and the output of the AI ​​model is the probability of each beam being the optimal beam. The UE compares the probability of each beam being the optimal beam to obtain K optimal beams.

[0165] Furthermore, based on the obtained probability that each of the K optimal beams becomes the optimal beam, the UE determines the probability information corresponding to the K beams, that is, the K probability information mentioned in the embodiment of the present application.

[0166] The method for the UE to determine K pieces of probability information may refer to the description in step 210 and will not be described in detail again.

[0167] 603. The UE sends K pieces of probability information and reference signal identification information corresponding to each of the K pieces of probability information to the network device.

[0168] 604. The network device determines the reference signal resources required to be configured for the second round of beam scanning based on the K probability information.

[0169] 605. The network device configures reference signal resources for a second round of beam scanning.

[0170] In the above process, there are multiple possible implementations of the UE's quantization method and reporting method. As an example, the following implementation is provided for how the UE determines which quantization method to use:

[0171] a) Directly standardize and define quantitative methods;

[0172] b) The network device indicates the quantization method to the UE. For example, the network device indicates the quantization method to the UE before configuring the corresponding reference signal resources.

[0173] In Example 1, for the classification type AI model deployed on the UE side, the UE quantifies the probability of each beam output by the AI ​​model becoming the optimal beam and reports the quantified information. Compared with the UE directly reporting the probability corresponding to the optimal beam, the overhead can be reduced.

[0174] Example 2

[0175] If the AI ​​model deployed on the UE is a regression model, the output of the AI ​​model is the predicted RSRP for each beam. Specifically, the UE obtains measurement results for N beams through the first round of beam scanning and uses these N beam measurement results as input to the AI ​​model, which outputs the predicted RSRP for each of the M beams. Based on the output of the configured algorithm or AI model, the UE calculates the confidence information corresponding to the predicted RSRP for all M beams. In this example, the confidence factor is the confidence information for the predicted RSRP.

[0176] If the UE directly reports the confidence information of the predicted RSRP for each of the multiple beams to the network device, it will incur significant overhead. Therefore, the method provided in this application can be used to quantify the confidence information of the predicted RSRP for multiple beams, thereby determining the probability information corresponding to the confidence information of K predicted RSRPs. The UE reports K probability information to the network device, which can reduce overhead.

[0177] Unlike when the AI ​​model is a classification model, where the sum of the probabilities of each beam being the optimal beam is 1, when the AI ​​model is a regression model, there is no correlation between the confidence levels corresponding to the predicted RSRP of each beam. Furthermore, in the embodiments of this application, the RSRP confidence level can be output by the AI ​​model or calculated by the UE based on an algorithm. This application does not focus on the specific method by which the UE obtains RSRP confidence information.

[0178] Additionally, it's important to note that in the regression model, there's no correlation between the RSRP value and the confidence level associated with that RSRP. For example, the confidence level associated with the maximum predicted RSRP value might be very low. In this case, it can be assumed that the predicted RSRP doesn't fully reflect the actual measured RSRP, and there might be a significant difference between the predicted and measured RSRP values.

[0179] FIG7 is a schematic flowchart of sending information provided in an embodiment of the present application.

[0180] 701. The network device configures reference signal resources, where the reference signal resources are used for the first round of beam scanning of the UE.

[0181] 702. The UE measures the reference signal resources and determines K pieces of probability information based on the measurement results and the AI ​​model.

[0182] As mentioned above, the reference signal resources configured by the network device are part of all reference signal resources. The UE measures this part of the reference signal resources and obtains the measurement results of this part of the reference signal resources. The measurement results of this part of the reference signal resources can be used as the input of the AI ​​model deployed on the UE side. If the AI ​​model is a regression model, the UE uses the AI ​​model for inference to obtain the predicted RSRP of each beam in all beams. As mentioned above, the UE can train the confidence corresponding to the predicted RSRP as one of the AI ​​model parameters during the beam training phase, and the output of the AI ​​model includes the predicted RSRP and its corresponding confidence information. Thus, the UE selects to report the predicted RSRP of K beams and the confidence information of these K predicted RSRPs by comparing the predicted RSRP of all beams and their corresponding confidence information.

[0183] The UE can quantize the confidence information corresponding to the K predicted RSRPs to obtain K probability information. The specific quantization method can be found in the description of step 210 in Figure 5 and will not be described in detail here. Only a few examples are given below.

[0184] As an example, the maximum confidence level among the K confidence levels corresponding to the K predicted RSRPs can be represented with high precision, and the confidence information for the remaining K-1 predicted RSRPs can be quantized. Assuming the aforementioned differential-based quantization method is used, the confidence information for the K predicted RSRPs can be differential information rather than the confidence information itself.

[0185] 703. The UE sends K pieces of probability information, including reference signal identification information corresponding to the K pieces of probability information and their corresponding predicted RSRP, to the network device.

[0186] 704. The network device determines reference signal resources for a second round of beam scanning based on the K probability information.

[0187] 705. The network device configures reference signal resources for the second round of beam scanning to the UE.

[0188] Similar to Example 1, in the above process, the quantization method of the UE can be implemented in multiple ways. As an example, the quantization method can be directly standardized and defined; or, the network device indicates the quantization method to the UE.

[0189] In Example 2, for the regression-type AI model deployed on the UE side, the UE quantifies the confidence information of the predicted RSRP of each beam output by the AI ​​model to become the optimal beam, and reports the quantized information. Compared with the UE directly reporting the confidence information of the predicted RSRP of the optimal beam, the overhead can be reduced.

[0190] Example 3

[0191] In Example 3, a method for reporting beam information across the time domain is provided. Taking AI-based time domain beam prediction as an example, if the AI ​​model is deployed on the UE side, the UE can obtain historical beam prediction information by measuring reference signal resources at multiple times. Furthermore, the historical beam prediction information is used as the input of the AI ​​model for reasoning. The AI ​​model uses the beam prediction information of these past moments to predict the optimal beam information for one or more moments in the future. For example, based on a classification AI model or a regression AI model, the UE will obtain the probability of the beam at each of one or more moments in the future becoming the optimal beam or the confidence of the predicted RSRP of the beam. Afterwards, the UE can report the output of the AI ​​model to the network device. The following Figure 8 illustrates the example of the UE obtaining the probability of the beam at each of one or more moments in the future becoming the optimal beam. The implementation of the confidence of the RSRP of the beam at one or more moments in the future using the regression AI model is similar to that in Example 2.

[0192] FIG8 is a schematic process of reporting cross-time domain beam information.

[0193] 801. During the historical information collection phase, the network device configures the corresponding reference signal resources in each time window. The UE measures the configured reference signal resources, obtains the reference signal resource measurement results, and uses them as input to the AI ​​model. In Figure 8, each reference signal resource configuration corresponds to a time window. After collecting historical information for several time windows, the UE obtains the reference signal resource measurement results within these time windows.

[0194] 802. The UE inputs the measurement results of the reference signal resources obtained in these several time windows into the AI ​​model, obtains the probability of each beam in each of the K prediction time units becoming the optimal beam, and determines the probability information corresponding to the K prediction time units based on the quantization method provided in this application.

[0195] As mentioned above, Figure 8 uses the classification AI model as an example for illustration. Therefore, the probability information corresponding to the K prediction time units includes the probability information corresponding to each of the K prediction time units, and each prediction time unit corresponds to a set of probability information, which includes at least one probability information.

[0196] Optionally, if the AI ​​model is a regression model, the probability information corresponding to the K prediction time units includes the probability information corresponding to each of the K prediction time units, and each prediction time unit also corresponds to a set of probability information, which includes at least one probability information.

[0197] The difference is that in the classification AI model, the set of probability information corresponding to each prediction time unit corresponds to a set of confidence factors, and each confidence factor in this set represents the probability of the beam becoming the optimal beam. In the regression AI model, the set of probability information corresponding to each prediction time unit corresponds to a set of confidence factors, and each confidence factor in this set represents the confidence level of the predicted RSRP of the beam.

[0198] The process of the UE determining K groups of probability information corresponding to K prediction time units may refer to the description in step 210 .

[0199] 803. The UE sends K groups of probability information and reference signal identification information corresponding to the K prediction units to the network device (the corresponding AI model is a classification model); or, the UE sends K groups of probability information, reference signal identification information and their corresponding predicted RSRP corresponding to the K prediction units to the network device (the corresponding AI model is a regression model).

[0200] 804. The network device determines the reference signal resources required to be configured for the second round of beam scanning based on the K groups of probability information corresponding to the K prediction time units.

[0201] 805. The network device configures reference signal resources for the second round of beam scanning for the UE.

[0202] The method for sending information provided in the embodiments of the present application can be applied to any scenario where the information to be sent is multiple percentages. Those skilled in the art should immediately understand that the scenario in which the UE feeds back information about the optimal beam to the network device in AI-based beam management is only one possible scenario. According to the detailed description of the above embodiments, determining the second probability information based on the first probability information and then sending the first probability information and the second probability information can save the bit overhead of sending information.

[0203] The communication method provided by this application has been described in detail above. The communication device provided by this application is introduced below.

[0204] See FIG9 , which is a schematic structural diagram of a communication device provided in this application.

[0205] As shown in Figure 9, a communication device 1000 includes a processing module 1001 and a communication module 1002. The communication device 1000 can be a communication device (e.g., a first device or a second device), or a device applied to a communication device and capable of implementing the corresponding functions of the communication device, such as a chip, a chip system, or a circuit. For example, the communication device can be a network device (e.g., an access network device) or a terminal device.

[0206] The communication module may also be a transceiver module, a transceiver, a transceiver, or a transceiver device. The processing module may also be a processor, a processing board, a processing unit, or a processing device. Optionally, the communication module is used to perform a sending operation or a receiving operation by a communication device (e.g., a network device or a terminal device) in any method embodiment. The device used to implement the receiving function in the communication module can be regarded as a receiving unit, and the device used to implement the sending function in the communication module can be regarded as a sending unit, that is, the communication module includes a receiving unit and a sending unit. The processing module is used to perform operations / processing related to the internal implementation of the network device or the terminal device in any method embodiment.

[0207] As an example, in FIG5 , if the communication apparatus corresponds to a first device, the processing module 1001 may be used to perform step 210, and the communication module 1002 may be used to perform the sending operation in step 220; if the communication apparatus corresponds to a second device, the processing module 1001 may be used to perform step 230, and the communication module 1002 may be used to perform the receiving operation in step 220. It should be understood that the specific operations of each module can be referred to the description in the method embodiment, and will not be described in detail here.

[0208] Furthermore, it should be noted that the aforementioned communication module and / or processing module may be implemented as a virtual module. For example, the processing module may be implemented as a software functional unit or a virtual device, and the communication module may be implemented as a software function or a virtual device. Alternatively, the processing module or the communication module may be implemented as a physical device. For example, if the device is implemented as a chip / hardware circuit, the communication module may be an input / output circuit and / or a communication interface that performs input operations (corresponding to the aforementioned receiving operations) and output operations (corresponding to the aforementioned sending operations); the processing module may be an integrated circuit or a logic circuit, etc.

[0209] The division of modules in this application is illustrative and represents only a logical functional division. In actual implementation, other division methods may be used. Furthermore, the functional modules in the examples of this application may be integrated into a single module, physically exist separately, or two or more modules may be integrated into a single module. The aforementioned integrated modules may be implemented in the form of hardware, software functional modules, or a combination of hardware and software functional modules, without limitation.

[0210] Referring to FIG10 , the present application also provides a schematic structural diagram of another communication device.

[0211] The communication device 1100 can be used to implement the functions of any communication device (for example, the first device or the second device) described in the aforementioned method embodiments. The communication device 1100 may include at least one processing circuit. The processing circuit may be one or more processors 1110, or all or part of the circuits in one or more processors for controlling or processing functions. Optionally, the processor 1110 (or processing device) is coupled to a memory, and the memory may be located within the communication device, or the memory may be integrated with the processor, or the memory may be located outside the communication device. For example, the communication device 1100 may also include at least one memory 1120. The memory 1120 stores the necessary computer programs, instructions and / or data for implementing any of the above embodiments; the processor 1110 may execute the computer programs, instructions and / or data stored in the memory 1120 to complete the corresponding functions of the first device or the second device (for example, a network device or a terminal device) in any of the above embodiments.

[0212] The communication device 1100 may further include a communication interface 1130, through which the communication device 1100 may exchange information with other devices. Exemplarily, the communication interface 1130 may be a transceiver, a circuit, a bus, a module, a pin, or another type of communication interface. When the communication device 1100 is a chip-type device or circuit, the communication interface 1130 in the device 1100 may also be an input / output circuit that may input information (or receive information) and / or output information (or send information). The processor may be an integrated circuit or a logic circuit, etc., and the processor may determine output information based on the input information.

[0213] Coupling in this application refers to an indirect coupling or communication connection between devices, units, or modules, which can be electrical, mechanical, or other forms, and is used for information exchange between devices, units, or modules. Processor 1110 may operate in conjunction with memory 1120 and communication interface 1130. This application does not limit the connection medium between the processor 1110, memory 1120, and communication interface 1130.

[0214] Optionally, the notification device may be a network device or a terminal device, the communication interface 1130 may be a transceiver or a transceiver circuit, and the processing circuit may be one or more processors.

[0215] Optionally, the notification device may be a server, the communication interface 1130 may be a transceiver circuit, and the processing circuit may be one or more processors.

[0216] Optionally, the above communication device can be a chip, such as a chip for a network device or a terminal device. The processing circuit can be a logic circuit, an integrated circuit, etc., and the communication interface can also be an input / output circuit, an input / output interface, an interface circuit, etc., which can input information (or receive information) or output information (or send information). The chip can execute the method performed by the network device or terminal device in each embodiment of the present application.

[0217] In addition, the present application also provides a computer-readable storage medium, which stores computer instructions. When the computer instructions are executed on a computer, the operations and / or processing performed by the network device or terminal device in each method embodiment of the present application are executed.

[0218] The present application also provides a computer program product, which includes computer program code or instructions. When the computer program code or instructions are run on a computer, the operations and / or processing performed by the network device or terminal device in the various method embodiments of the present application are executed.

[0219] The present application provides a communication system, including the network device and terminal device in the above method embodiment. For example, the communication system includes a first network device and a terminal device. Further, it may also include a second network device.

[0220] In this application, a processor may be a general-purpose processor, a digital signal processor, a graphics processor, an artificial intelligence processor, an application-specific integrated circuit, a field-programmable gate array or other programmable logic device, a discrete gate or transistor logic device, or a discrete hardware component, and may implement or execute the methods, steps, and logic block diagrams disclosed in this application. A general-purpose processor may be a microprocessor or any conventional processor. The steps of the methods disclosed in this application may be directly implemented as being executed by a hardware processor, or may be executed by a combination of hardware and software modules in the processor.

[0221] In the present application, the memory may be a non-volatile memory, such as a hard disk drive (HDD) or a solid-state drive (SSD), or a volatile memory, such as a random-access memory (RAM). The memory is any other medium that can be used to carry or store desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto. The memory in the present application may also be a circuit or any other device that can implement a storage function, for storing program instructions and / or data.

[0222] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel 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.

[0223] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0224] In the several embodiments provided in this application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0225] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0226] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0227] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

Claims

1. A method for sending information, characterized in that: include: Determine K pieces of probability information, where the K pieces of probability information include first probability information and second probability information, any one piece of probability information among the K pieces of probability information is used to determine a trust factor, and the second probability information is determined based on the first probability information; First information is sent, where the first information includes the K probability information, where K is an integer greater than 1.

2. The method according to claim 1, characterized in that The trust factor includes any of the following: The predicted probability or predicted confidence of the reference signal identification information; The prediction probability or prediction confidence of the reference signal received power RSRP information; The prediction probability or prediction confidence of the channel state information CSI.

3. The method according to claim 1 or 2, characterized in that The second probability information is determined according to the first probability information, including: The second probability information includes differential information between a credibility factor corresponding to the second probability information and a credibility factor corresponding to the first probability information.

4. The method according to any one of claims 1 to 3, characterized in that The first probability information includes probability information corresponding to a reference credible factor, where the reference credible factor is the credible factor with the largest value or the credible factor with the smallest value among the K credible factors corresponding to the K probability information.

5. The method according to claim 4, characterized in that The first information is further used to indicate reference signal identification information corresponding to the reference credibility factor.

6. The method according to claim 5, characterized in that In the first information, the reference trustworthy factor is arranged at the front or the back or a preset position of the K trustworthy factors; or, In the first information, the reference signal identification information corresponding to the reference credibility factor is arranged at the front or the back or a preset position of K reference signal identification information, and the K reference signal identification information are the reference signal identification information corresponding to the K probability information respectively; or, The field in the first information indicates the reference signal identifier corresponding to the reference credibility factor.

7. The method according to any one of claims 1 to 6, characterized in that The K probability information includes K1 probability information and K2 probability information, the K1 probability information corresponds to the first prediction time unit, the K2 probability information corresponds to the second prediction time unit, the K1 probability information includes the first probability information, and the K2 probability information includes the second probability information, wherein the second prediction time unit is earlier than or later than the first prediction time unit, and K1 and K2 are both positive integers.

8. The method according to claim 7, characterized in that The reference signal identifier corresponding to the first probability information is the same as the reference signal identifier corresponding to the second probability information.

9. The method according to any one of claims 4 to 8, characterized in that The first information is further used to indicate information of a prediction time unit corresponding to the reference credibility factor.

10. The method according to any one of claims 1 to 8, characterized in that The K probability information also includes third probability information, and the third probability information is determined according to the second probability information.

11. The method according to claim 10, characterized in that The third probability information is determined according to the second probability information, further comprising: The third probability information includes a difference between a credibility factor corresponding to the third probability information and a credibility factor corresponding to the second probability information.

12. The method according to claim 1 or 2, characterized in that: The second probability information is determined according to the first probability information, including: The trust factor corresponding to the second probability information is determined in a first quantization interval, and the first quantization interval is determined by a reference trust factor and a trust factor corresponding to the first probability information, and the reference trust factor is predefined or indicated by a network device.

13. The method according to claim 12, characterized in that The first quantization interval includes a difference between a reference credibility factor and a credibility factor corresponding to the first probability information.

14. The method according to claim 1 or 2, characterized in that The second probability information is determined according to the first probability information, including: The credibility factor corresponding to the first probability information is determined in a second quantization interval, and the credibility factor corresponding to the second probability information is determined in a third quantization interval. The second quantization interval and the third quantization interval correspond to different quantization steps.

15. The method according to claim 14, characterized in that The second quantization interval and the third quantization interval correspond to different quantization steps, including: The quantization step corresponding to the second quantization interval is smaller than the quantization step corresponding to the third quantization interval.

16. The method according to any one of claims 1 to 15, characterized in that The credibility factor corresponding to any one of the K probability information is higher than the credibility factor threshold.

17. The method according to any one of claims 1 to 15, characterized in that The first information does not include probability information that the credibility factor is higher than the credibility factor threshold.

18. The method according to any one of claims 1 to 17, characterized in that The first information also includes beam information corresponding to each probability information in the K probability information, and the beam information includes at least one of the following: Reference signal identification information; RSRP information; CSI.

19. A method for receiving information, characterized in that: include: receiving first information, where the first information includes the K probability information, the K probability information includes first probability information and second probability information, the second probability information is related to the first probability information, and K is an integer greater than 1; Determine the information provided by the K probability information.

20. The method according to claim 19, characterized in that Any one of the K probability information is used to determine a credibility factor, and the credibility factor includes any one of the following: The predicted probability or predicted confidence of the reference signal identification information; The prediction probability or prediction confidence of the reference signal received power RSRP information; The prediction probability or prediction confidence of the channel state information CSI.

21. The method according to claim 19 or 20, characterized in that The second probability information includes: Differential information between the credibility factor corresponding to the second probability information and the credibility factor corresponding to the first probability information.

22. The method according to any one of claims 19 to 21, characterized in that The first probability information includes probability information corresponding to a reference credible factor, where the reference credible factor is the credible factor with the largest value or the credible factor with the smallest value among the K credible factors corresponding to the K probability information.

23. The method according to claim 22, characterized in that The first information is further used to indicate reference signal identification information corresponding to the reference credibility factor.

24. The method according to claim 23, wherein In the first information, the reference trustworthy factor is arranged at the front or the back or a preset position of the K trustworthy factors; or, In the first information, the reference signal identification information corresponding to the reference credibility factor is arranged at the front or the back or a preset position of K reference signal identification information, and the K reference signal identification information are the reference signal identification information corresponding to the K probability information respectively; or, The field in the first information indicates the reference signal identifier corresponding to the reference credibility factor.

25. The method according to any one of claims 19 to 24, characterized in that The K probability information includes K1 probability information and K2 probability information, the K1 probability information corresponds to the first prediction time unit, the K2 probability information corresponds to the second prediction time unit, the K1 probability information includes the first probability information, and the K2 probability information includes the second probability information, wherein the second prediction time unit is earlier than or later than the first prediction time unit, and K1 and K2 are both positive integers.

26. The method according to claim 25, characterized in that The reference signal identifier corresponding to the first probability information is the same as the reference signal identifier corresponding to the second probability information.

27. The method according to any one of claims 22 to 26, characterized in that The first information is further used to indicate information of a prediction time unit corresponding to the reference credibility factor.

28. The method according to any one of claims 19 to 26, characterized in that The K probability information also includes third probability information, and the third probability information is determined according to the second probability information.

29. The method according to claim 28, characterized in that The third probability information includes: The difference between the credibility factor corresponding to the third probability information and the credibility factor corresponding to the second probability information.

30. The method according to claim 19 or 20, characterized in that The second probability information is determined according to the first probability information, including: The trust factor corresponding to the second probability information is determined in a first quantization interval, and the first quantization interval is determined by a reference trust factor and a trust factor corresponding to the first probability information, and the reference trust factor is predefined or indicated by a network device.

31. The method according to claim 30, wherein The first quantization interval includes a difference between a reference credibility factor and a credibility factor corresponding to the first probability information.

32. The method according to claim 19 or 20, characterized in that The second probability information is determined according to the first probability information, including: The credibility factor corresponding to the first probability information is determined in a second quantization interval, and the credibility factor corresponding to the second probability information is determined in a third quantization interval. The second quantization interval and the third quantization interval correspond to different quantization steps.

33. The method according to claim 32, characterized in that The second quantization interval and the third quantization interval correspond to different quantization steps, including: The quantization step corresponding to the second quantization interval is smaller than the quantization step corresponding to the third quantization interval.

34. The method according to any one of claims 19 to 33, characterized in that The credibility factor corresponding to any one of the K probability information is higher than the credibility factor threshold.

35. The method according to any one of claims 19 to 33, characterized in that The first information does not include probability information that the credibility factor is higher than the credibility factor threshold.

36. The method according to any one of claims 19 to 35, wherein: The first information also includes beam information corresponding to each probability information in the K probability information, and the beam information includes at least one of the following: Reference signal identification information; RSRP information; CSI.

37. A communication device, characterized in that: The method comprises modules or units for performing the method according to any one of claims 1 to 36.

38. A communication device, characterized in that: The communication device comprises a processor coupled to a memory, wherein the processor is configured to execute a computer program or instruction stored in the memory, so as to enable the communication device to perform the method according to any one of claims 1 to 18, or to perform the method according to any one of claims 19 to 36.

39. A computer-readable storage medium, characterized in that The computer-readable storage medium stores instructions, and when the instructions are executed, the method according to any one of claims 1 to 18 or the method according to any one of claims 19 to 36 is implemented.

40. A computer program product, characterized in that The computer program product comprises instructions, and when the instructions are executed, the method according to any one of claims 1 to 18 or the method according to any one of claims 19 to 36 is implemented.

41. A communication system, characterized in that The invention comprises an apparatus for performing the method according to any one of claims 1 to 18 and an apparatus for performing the method according to any one of claims 19 to 36.

Images