Prediction-related processing method, terminal, and network side device

Abstract

The present application relates to the technical field of communications, and discloses a prediction-related processing method, a terminal, and a network side device. The prediction-related processing method in an embodiment of the present application comprises: a terminal acquiring predicted accuracy information; determining first information on the basis of the predicted accuracy information; and executing at least one of the following: generating a first cell value on the basis of the first information and a first beam value of a first beam, or performing layer-3 filtering on the first beam value of the first beam on the basis of the first information and a beam filtering coefficient for layer-3 filtering; performing layer-3 filtering on a second cell value on the basis of the first information and a cell filtering coefficient for layer-3 filtering; obtaining a third beam value on the basis of the first information and a second beam value of the first beam, and, on the basis of the third beam value, executing beam selection for beam reporting; and obtaining a fourth beam value on the basis of the first information and the first beam value of the first beam, and, on the basis of the fourth beam value, executing beam selection for generating the first cell value.

Description

Processing method, terminal and network side device related to prediction

[0001] Cross-reference to Related Applications

[0002] This application claims priority to the Chinese patent application No. 202411272541.X entitled "Processing method, terminal and network side device related to prediction" and filed with the China Patent Office on September 11, 2024, the content of which is incorporated herein by reference in its entirety. TECHNICAL FIELD

[0003] The present application belongs to the field of communication technology, and specifically relates to a processing method, terminal and network side device related to prediction. BACKGROUND

[0004] Artificial intelligence (AI) is currently widely used in various fields. By integrating an AI model into a wireless communication network, the mobility performance and technical indicators such as throughput, latency, and user capacity can be significantly improved.

[0005] For AI for mobility, one important use case is to introduce RRM measurement prediction, including cell-level measurement prediction and beam-level measurement prediction.

[0006] Since the predicted values of the AI model may have inaccuracy / errors / prediction accuracy problems, i.e., there is a certain deviation between the predicted values and the actual values, if these predicted values are not reasonably processed, but directly used for subsequent processing, it may affect the accuracy of the obtained processing results. SUMMARY

[0007] The embodiments of the present application provide a processing method, terminal and network side device related to prediction, which can solve the problem of how to process the predicted values obtained based on the AI model to improve the accuracy of the processing results obtained based on the predicted values.

[0008] In a first aspect, a processing method for prediction correlation is provided, and the method comprises the following steps: a terminal acquires prediction accuracy information; the terminal determines first information based on the prediction accuracy information; and the terminal performs at least one of the following: generating a first cell value based on the first information and a first beam value of a first beam, the first information being a weight factor corresponding to the first beam; or performing layer three filtering on a first beam value of a first beam based on the first information and a layer three filtered beam filtering coefficient, the first information being a second adjustment coefficient corresponding to the first beam; wherein the prediction accuracy information is first prediction accuracy information corresponding to the first beam value, the first beam value being a beam value predicted based on a first artificial intelligence (AI) model, and the second adjustment coefficient is used for adjusting the beam filtering coefficient; performing layer three filtering on a second cell value based on the first information and a layer three filtered cell filtering coefficient; wherein the prediction accuracy information is second prediction accuracy information corresponding to the second cell value, the first information being a first adjustment coefficient, and the first adjustment coefficient being used for adjusting the cell filtering coefficient; obtaining a third beam value based on the first information and a second beam value of a first beam, and performing beam selection for beam reporting based on the third beam value; wherein the second beam value is a beam value obtained by performing layer three filtering on a first beam value of the first beam predicted based on the first AI model; obtaining a fourth beam value based on the first information and a first beam value of a first beam, and performing beam selection for generating a first cell value based on the fourth beam value; wherein the first beam value is a beam value predicted based on the first AI model.

[0009] In a second aspect, a processing method for prediction is provided, including: sending, by a network-side device, second information to a terminal, the second information being used by the terminal to determine first information based on prediction accuracy information; wherein the first information is used for at least one of: generating a first cell value based on a first beam value of a first beam, the first information being a weight factor corresponding to the first beam; or performing layer-three filtering on a first beam value of a first beam based on a layer-three filtering beam filtering coefficient, the first information being a second adjustment coefficient corresponding to the first beam; wherein the prediction accuracy information is first prediction accuracy information corresponding to the first beam value, the first beam value being a beam value predicted based on a first AI model, and the second adjustment coefficient is used to adjust the beam filtering coefficient; performing layer-three filtering on a second cell value based on a layer-three filtering cell filtering coefficient; wherein the prediction accuracy information is second prediction accuracy information corresponding to the second cell value, and the first information is a first adjustment coefficient used to adjust the cell filtering coefficient; obtaining a third beam value based on a second beam value of a first beam, and performing beam selection for beam reporting based on the third beam value; wherein the second beam value is a beam value obtained by performing layer-three filtering on a first beam value of the first beam predicted based on a first AI model; obtaining a fourth beam value based on a first beam value of a first beam, and performing beam selection for generating a first cell value based on the fourth beam value; wherein the first beam value is a beam value predicted based on a first AI model.

[0010] In a third aspect, a prediction-related processing apparatus applied to a terminal is provided, comprising: a processing module configured to obtain prediction accuracy information; determine first information based on the prediction accuracy information; and perform at least one of: generate a first cell value based on the first information and a first beam value of a first beam, the first information being a weight factor corresponding to the first beam; or perform layer three filtering on a first beam value of a first beam based on the first information and a layer three filtered beam filtering coefficient, the first information being a second adjustment coefficient corresponding to the first beam; wherein the prediction accuracy information is first prediction accuracy information corresponding to the first beam value, the first beam value being a beam value predicted based on a first AI model, and the second adjustment coefficient is used to adjust the beam filtering coefficient; perform layer three filtering on a second cell value based on the first information and a layer three filtered cell filtering coefficient; wherein the prediction accuracy information is second prediction accuracy information corresponding to the second cell value, the first information being a first adjustment coefficient, and the first adjustment coefficient is used to adjust the cell filtering coefficient; obtain a third beam value based on the first information and a second beam value of the first beam, and perform beam selection for beam reporting based on the third beam value; wherein the second beam value is a beam value obtained by performing layer three filtering on the first beam value of the first beam predicted based on the first AI model; obtain a fourth beam value based on the first information and a first beam value of the first beam, and perform beam selection for generating the first cell value based on the fourth beam value; wherein the first beam value is a beam value predicted based on the first AI model.

[0011] In a fourth aspect, a prediction-related processing apparatus is provided, comprising: a sending module configured to send second information to a terminal, the second information being used by the terminal to determine first information based on prediction accuracy information, wherein the first information is used for at least one of: generating a first cell value based on a first beam value of a first beam, the first information being a weight factor corresponding to the first beam; or performing layer three filtering on a first beam value of a first beam based on a layer three filtered beam filtering coefficient, the first information being a second adjustment coefficient corresponding to the first beam; wherein the prediction accuracy information is first prediction accuracy information corresponding to the first beam value, the first beam value being a beam value predicted based on a first AI model, and the second adjustment coefficient is used to adjust the beam filtering coefficient; performing layer three filtering on a second cell value based on a layer three filtered cell filtering coefficient; wherein the prediction accuracy information is second prediction accuracy information corresponding to the second cell value, and the first information is a first adjustment coefficient used to adjust the cell filtering coefficient; obtaining a third beam value based on a second beam value of a first beam, and performing beam selection for beam reporting based on the third beam value; wherein the second beam value is a beam value obtained by performing layer three filtering on a first beam value of the first beam predicted based on a first AI model; obtaining a fourth beam value based on a first beam value of a first beam, and performing beam selection for generating a first cell value based on the fourth beam value; wherein the first beam value is a beam value predicted based on a first AI model.

[0012] In a fifth aspect, a prediction-related processing apparatus is provided, the apparatus being configured to perform the steps of the method according to the first aspect or the second aspect.

[0013] In a sixth aspect, a terminal is provided, comprising a processor and a memory, the memory storing a program or instructions executable on the processor, the program or instructions, when executed by the processor, implementing the steps of the method according to the first aspect.

[0014] In a seventh aspect, a terminal is provided, comprising a processor and a communication interface, wherein the processor is configured to obtain prediction accuracy information, determine first information based on the prediction accuracy information, and perform at least one of: generate a first cell value based on the first information and a first beam value of a first beam, the first information being a weight factor corresponding to the first beam; or perform layer-three filtering on a first beam value of a first beam based on the first information and a layer-three filtered beam filtering coefficient, the first information being a second adjustment coefficient corresponding to the first beam; wherein the prediction accuracy information is first prediction accuracy information corresponding to the first beam value, the first beam value being a beam value predicted based on a first AI model, and the second adjustment coefficient is used to adjust the beam filtering coefficient; perform layer-three filtering on a second cell value based on the first information and a layer-three filtered cell filtering coefficient; wherein the prediction accuracy information is second prediction accuracy information corresponding to the second cell value, the first information being a first adjustment coefficient, and the first adjustment coefficient is used to adjust the cell filtering coefficient; obtain a third beam value based on the first information and a second beam value of a first beam, and perform beam selection for beam reporting based on the third beam value; wherein the second beam value is a beam value obtained by performing layer-three filtering on a first beam value of the first beam predicted based on a first AI model; obtain a fourth beam value based on the first information and a first beam value of a first beam, and perform beam selection for generating a first cell value based on the fourth beam value; wherein the first beam value is a beam value predicted based on a first AI model.

[0015] In an eighth aspect, a network-side device is provided, comprising a processor and a memory, the memory storing programs or instructions executable on the processor, and the programs or instructions, when executed by the processor, implement the steps of the method according to the second aspect.

[0016] In a ninth aspect, a network-side device is provided, including a processor and a communication interface, wherein the communication interface is configured to send second information to a terminal, the second information being used by the terminal to determine first information based on prediction accuracy information; wherein the first information is used for at least one of: generating a first cell value based on a first beam value of a first beam, the first information being a weight factor corresponding to the first beam; or performing layer-three filtering on a first beam value of a first beam based on a layer-three filtering beam filtering coefficient, the first information being a second adjustment coefficient corresponding to the first beam; wherein the prediction accuracy information is first prediction accuracy information corresponding to the first beam value, the first beam value being a beam value predicted based on a first AI model, and the second adjustment coefficient is used to adjust the beam filtering coefficient; performing layer-three filtering on a second cell value based on a layer-three filtering cell filtering coefficient; wherein the prediction accuracy information is second prediction accuracy information corresponding to the second cell value, and the first information is a first adjustment coefficient used to adjust the cell filtering coefficient; obtaining a third beam value based on a second beam value of a first beam, and performing beam selection for beam reporting based on the third beam value; wherein the second beam value is a beam value obtained by performing layer-three filtering on a first beam value of the first beam predicted based on a first AI model; obtaining a fourth beam value based on a first beam value of a first beam, and performing beam selection for generating a first cell value based on the fourth beam value; wherein the first beam value is a beam value predicted based on a first AI model.

[0017] In a tenth aspect, a readable storage medium is provided, the readable storage medium storing a program or instructions, the program or instructions being executed by a processor to implement steps of the method according to the first aspect or steps of the method according to the second aspect.

[0018] In an eleventh aspect, a wireless communication system is provided, including a terminal and a network-side device, the terminal being configured to implement steps of the method according to the first aspect, and the network-side device being configured to implement steps of the method according to the second aspect.

[0019] In a twelfth aspect, a chip is provided, including a processor and a communication interface, the communication interface being coupled to the processor, and the processor being configured to run a program or instructions to implement the method according to the first aspect or steps of the method according to the second aspect.

[0020] In a thirteenth aspect, a computer program / program product is provided, the computer program / program product being stored in a storage medium, and the computer program / program product being executed by at least one processor to implement the method according to the first aspect or steps of the method according to the second aspect.

[0021] In the embodiments of the present application, the terminal acquires prediction accuracy information; determines first information based on the prediction accuracy information; and performs at least one of the following: 1) generates a first cell value based on the first information and a first beam value of a first beam, improves the accuracy of the first cell value, and facilitates improving mobility performance; or performs layer three filtering on a first beam value of a first beam based on the first information and a beam filtering coefficient of layer three filtering, and increases the accuracy of the first beam value after layer three filtering; 2) performs layer three filtering on a second cell value based on the first information and a cell filtering coefficient of layer three filtering, and increases the accuracy of the second cell value after layer three filtering; 3) obtains a third beam value based on the first information and a second beam value of the first beam, performs beam selection for beam reporting based on the third beam value, and improves the accuracy of beam selection; and 4) obtains a fourth beam value based on the first information and the first beam value of the first beam, performs beam selection for generating a first cell value based on the fourth beam value, and improves the accuracy of the first cell value. BRIEF DESCRIPTION OF DRAWINGS

[0022] FIG. 1 is a schematic diagram of a wireless communication system according to an embodiment of the present application;

[0023] FIG. 2 is a schematic flowchart of a prediction-related processing method according to an embodiment of the present application;

[0024] FIG. 3 is a schematic flowchart of a prediction-related processing method according to an embodiment of the present application;

[0025] FIG. 4 is a schematic flowchart of a prediction-related processing method according to an embodiment of the present application;

[0026] FIG. 5 is a schematic flowchart of a prediction-related processing method according to an embodiment of the present application;

[0027] FIG. 6 is a schematic flowchart of a prediction-related processing method according to an embodiment of the present application;

[0028] FIG. 7 is a schematic flowchart of a prediction-related processing method according to an embodiment of the present application;

[0029] FIG. 8 is a schematic flowchart of a prediction-related processing method according to an embodiment of the present application;

[0030] FIG. 9 is a schematic structural diagram of a prediction-related processing apparatus according to an embodiment of the present application;

[0031] FIG. 10 is a schematic structural diagram of a prediction-related processing apparatus according to an embodiment of the present application;

[0032] FIG. 11 is a schematic structural diagram of a communication device according to an embodiment of the present application;

[0033] FIG. 12 is a structural schematic diagram of a terminal according to an embodiment of the present application;

[0034] FIG. 13 is a structural schematic diagram of a network side device according to an embodiment of the present application. DETAILED DESCRIPTION

[0035] The technical solutions in the embodiments of the present application will be clearly described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some of the embodiments of the present application, but not all the embodiments of the present application. Based on the embodiments in the present application, all the other embodiments obtained by those of ordinary skill in the art belong to the scope of protection of the present application.

[0036] The terms "first", "second", and the like in the present application are used to distinguish similar objects, and are not used to describe a specific order or sequence. It should be understood that the terms used in this way can be interchanged under appropriate circumstances, so that the embodiments of the present application can be implemented in an order other than those illustrated or described herein, and the objects distinguished by "first", "second" are generally a category and do not limit the number of objects, for example, the first object can be one or more. In addition, "or" in the present application means at least one of the connected objects. For example, the protection scope of "A or B" at least covers three schemes, namely, scheme one: including A and not including B; scheme two: including B and not including A; scheme three: including A and including B. In addition, the terms "A and / or B", "at least one of A and B", "at least one of A or B" also at least cover the above three schemes, respectively. The character " / " generally represents that the objects before and after are in an "or" relationship.

[0037] The term "indication" in the present application can be a direct indication (or explicit indication) or an indirect indication (or implicit indication). The direct indication can be understood as that the sender explicitly informs the receiver of specific information, operations to be performed or requested results, etc. in the indication sent by the sender. The indirect indication can be understood as that the receiver determines the corresponding information according to the indication sent by the sender, or judges and determines the operations to be performed or the requested results according to the judgment result.

[0038] It is worth noting that the technology described in the embodiments of the present application is not limited to Long Term Evolution (LTE) / LTE-Advanced (LTE-A) systems, but can also be used in other wireless communication systems, such as Code Division Multiple Access (CDMA), Time Division Multiple Access (TDMA), Frequency Division Multiple Access (FDMA), Orthogonal Frequency Division Multiple Access (OFDMA), Single-carrier Frequency-Division Multiple Access (SC-FDMA) or other systems. The terms "system" and "network" in the embodiments of the present application are often used interchangeably, and the described technology can be used in the above-mentioned systems and radio technologies, as well as in other systems and radio technologies. The following description describes a New Radio (NR) system for example purposes, and NR terminology is used in most of the following description, but these technologies can also be applied to systems other than NR systems, such as 6th Generation (6G) communication systems. th

[0039] ​FIG. 1 shows a block diagram of a wireless communication system to which embodiments of the present application can be applied. The wireless communication system includes a terminal 11 and a network-side device 12. The terminal 11 can be a terminal-side device such as a mobile phone, a Tablet Personal Computer, a Laptop Computer, a notebook computer, a Personal Digital Assistant (PDA), a palmtop computer, a netbook, an Ultra-mobile Personal Computer (UMPC), a Mobile Internet Device (MID), an Augmented Reality (AR) device, a Virtual Reality (VR) device, a robot, a wearable device, a flight vehicle, a Vehicle User Equipment (VUE), a shipboard device, a Pedestrian User Equipment (PUE), a smart home (a home device with a wireless communication function such as a refrigerator, a television, a washing machine, or furniture), a game console, a Personal Computer (PC), a kiosk, or a self-service machine. The wearable device includes a smart watch, a smart bracelet, a smart earphone, smart glasses, smart jewelry (a smart bracelet, a smart necklace, a smart ring, a smart necklace, a smart anklet, a smart necklace, etc.), a smart wristband, smart clothes, etc. The vehicle-mounted device can also be referred to as a vehicle-mounted terminal, a vehicle-mounted controller, a vehicle-mounted module, a vehicle-mounted component, a vehicle-mounted chip, or a vehicle-mounted unit, etc. It should be noted that the specific type of the terminal 11 is not limited in the embodiments of the present application. The network-side device 12 can include an access network device or a core network device. The access network device can also be referred to as a Radio Access Network (RAN) device, a radio access network function, or a radio access network unit. The access network device can include a base station, a Wireless Local Area Network (WLAN) Access Point (AP), or a Wireless Fidelity (WiFi) node, etc.The base station can be referred to as a Node B (NB), an evolved Node B (eNB), a next generation Node B (gNB), a New Radio Node B (NR Node B), an access point, a relay station (RBS), a serving base station (SBS), a base transceiver station (BTS), a radio base station, a radio transceiver, a basic service set (BSS), an extended service set (ESS), a home Node B (HNB), a home evolved Node B, a transmit / receive point (TRP), or some other suitable terminology in the art, and is not limited to a particular technical terminology, provided that the same technical effect is achieved. It should be noted that in the embodiments of the present application, only the base station in the NR system is taken as an example for introduction, and the specific type of the base station is not limited.

[0040] The core network device can also be referred to as a core network node, a core network function, or a core network network element, etc., which includes but is not limited to at least one of the following: a mobility management entity (MME), an access and mobility management function (AMF), a session management function (SMF), a user plane function (UPF), a policy control function (PCF), a policy and charging rules function (PCRF), an edge application server discovery function (EASDF), a unified data management (UDM), a unified data repository (UDR), a home subscriber server (HSS), a centralized network configuration (CNC), a network repository function (NRF), a network exposure function (NEF), a local NEF (L-NEF), a binding support function (BSF), an application function (AF), a location management function (LMF), a gateway mobile location center (GMLC), a network data analytics function (NWDAF), etc. It should be noted that only the core network device in the NR system is taken as an example for introduction in the embodiments of the present application, and the specific type of the core network device is not limited. If the name of the core network device mentioned in the embodiments of the present application changes in the subsequent protocol version (for example, 6G), it is also within the protection scope of the present application.

[0041] Optionally, the core network device can be implemented by one or more function modules in one device, or can be implemented by multiple devices jointly, and the embodiments of the present application do not make a specific limitation here. It can be understood that the above function modules can be network elements in a hardware device, can be software function modules running on a dedicated hardware, or can be virtualized function modules instantiated on a platform (for example, a cloud platform).

[0042] In the related art, the network side device (such as a base station) performs switching decision and other operations based on a layer three (L3) filtered cell measurement value. The related art is based on the beam measurement value obtained by actual measurement to obtain the cell measurement value, and does not involve how to perform beam selection and merging based on the predicted value to obtain the cell value; nor does it involve how to obtain the layer three filtered cell value based on the predicted layer three filtered cell value.

[0043] After introducing the Radio Resource Management (RRM) measurement prediction, for the beam level measurement prediction, one scenario is that a part of beams (hereinafter second beams) of a cell perform actual measurement to obtain actual measurement values of the beams, while another part of beams (hereinafter first beams) of the cell can obtain predicted values of the beams through the first AI model. Due to the problem of inaccuracy / error / prediction accuracy of the predicted values, that is, there is a certain deviation between the predicted values and the actual values, if the actual measurement values of a part of beams and the predicted values of another part of beams are simply averaged, in the case that the predicted values of the beams and the actual values have a large deviation, the generated cell value (including the layer three filtered cell value) will also have a large deviation from the actual value, which can cause unreasonable switching, thereby affecting the user experience. How to generate a more accurate cell value (including the layer three filtered cell value) based on the predicted values of a part of beams and the actual measurement values of another part of beams is one of the problems to be solved by the embodiments of the present application.

[0044] In addition, the layer three filtered cell value is inaccurate, including: 1) for the above beam level measurement prediction, the inaccuracy of the predicted values of a part of beams causes the inaccuracy of the layer three filtered cell value; 2) for the cell level measurement prediction, if the predicted cell value output by the second AI model is the layer three filtered cell value, similarly, the predicted cell value can be inaccurate. Due to the problem of inaccuracy of the layer three filtered cell value, the layer three filtered cell value will have a large deviation from the actual value, and triggering the measurement report based on the cell value with a large deviation can cause unreasonable switching. How to perform layer three filtering based on the inaccurate layer three filtered cell value is one of the problems to be solved by the embodiments of the present application.

[0045] In addition, how to improve the accuracy and rationality of the selected beam in the beam selection process for beam reporting or in the beam selection process for generating a cell value based on a beam value is also a problem to be solved by the present application.

[0046] It should be noted that the AI model mentioned in each embodiment of the present application can also be referred to as an AI unit, an AI model, a machine learning (ML) model, an ML unit, an AI structure, an AI function, an AI feature, a machine learning model, a neural network, a neural network function, a neural network function, etc. Or the AI model can refer to a processing unit that can implement a specific algorithm, formula, processing flow, capability, etc. related to AI, or the AI model can be a processing method, algorithm, function, module or unit for a specific data set, or the AI model can be a processing method, algorithm, function, module or unit running on AI / ML related hardware such as GPU, NPU, TPU, ASIC, etc. The present application does not make specific limitations.

[0047] In each embodiment of the present application, the measurement value can also be referred to as a measurement quality, a measured result, etc. The predicted value can also be referred to as a predicted measurement value, a prediction quality, a prediction result, etc. The cell value can also be referred to as a cell quality, a cell measurement value or a cell predicted value. The beam value can also be referred to as a beam quality, a beam measurement value or a beam predicted value. The measurement value, the predicted value, the cell value or the beam value can be a signal strength, such as Reference Signal Receiving Power (RSRP), or a signal quality, such as Reference Signal Receiving Quality (RSRQ). Here, no limitation is made.

[0048] The prediction-related processing method provided by the embodiments of the present application will be described in detail in combination with the accompanying drawings and some embodiments and application scenarios.

[0049] As shown in FIG. 2, the present application provides a prediction-related processing method 200, which can be executed by a terminal, in other words, the method can be executed by software or hardware installed in the terminal, and the method includes the following steps.

[0050] S202: The terminal acquires prediction accuracy information.

[0051] The prediction accuracy information can be related to a predicted value of a beam or a cell, for example, the prediction accuracy information is first prediction accuracy information corresponding to a first beam value; wherein the first beam value of the first beam is a beam value predicted based on a first AI model. For another example, the prediction accuracy information is second prediction accuracy information corresponding to a second cell value; wherein the second cell value can be predicted based on a second AI model; or the second cell value can be obtained based on the first beam value of the first beam and the actual measurement value of the second beam, and the first beam value of the first beam is a beam value predicted based on the first AI model.

[0052] S204: The terminal determines first information based on the prediction accuracy information.

[0053] The first information can be used to adjust the predicted value (also including the value obtained after processing the predicted value, etc.), for example, the first information can be a weight factor corresponding to the first beam, which can be used as the weight of the first beam when generating the first cell value; or the first information is a second adjustment coefficient corresponding to the first beam, which is used to adjust the beam filtering coefficient; or the first information is a first adjustment coefficient, which is used to adjust the cell filtering coefficient; or the first information is used to adjust the first beam value or the second beam value of the first beam.

[0054] S206: The terminal executes at least one of the following schemes 1 to 4:

[0055] Scheme 1: generating a first cell value based on the first information and the first beam value of the first beam, the first information being a weight factor corresponding to the first beam; or performing layer three filtering on the first beam value of the first beam based on the first information and a layer three filtered beam filtering coefficient, the first information being a second adjustment coefficient corresponding to the first beam; wherein the prediction accuracy information is first prediction accuracy information corresponding to the first beam value, the first beam value being a beam value predicted based on a first AI model, and the second adjustment coefficient being used to adjust the beam filtering coefficient.

[0056] The prediction accuracy information mentioned in various embodiments of the present application can not only include prediction accuracy (such as percentage, maximum error), but also include other information, such as prediction accuracy range, or prediction accuracy category, etc.

[0057] In scheme 1, the terminal determines the first information based on the prediction accuracy information includes: the terminal determines the first information based on the first prediction accuracy information and second information; wherein the second information includes at least one of the following: a mapping relationship between the first prediction accuracy information and the first information, and a first threshold.

[0058] In an embodiment, in a case where the prediction accuracy corresponding to the first prediction accuracy information is less than or equal to the first threshold: in generating the first cell value, the weight factor corresponding to the first beam value is 0 or the first beam is not selected to participate in the generation process of the first cell value; or, in layer three filtering of the first beam value, the second adjustment coefficient is 0 or layer three filtering is not performed based on the first beam value.

[0059] In an embodiment, before the terminal determines the first information based on the first prediction accuracy information and the second information, the terminal further receives the second information from a network side device.

[0060] In an embodiment, the first prediction accuracy information includes at least one of:

[0061] 1) the prediction accuracy of the first beam value, wherein different first beams can correspond to different prediction accuracies.

[0062] 2) the current prediction accuracy of the first AI model, for example, the terminal or the network side device can monitor the first AI model to obtain the current prediction accuracy of the first AI model.

[0063] 3) the prediction accuracy associated with the first AI model, which can be associated with the first AI model and can be considered as attribute information of the first AI model.

[0064] In an embodiment, the generating the first cell value based on the first information and the first beam value of the first beam includes: generating the first cell value based on one of the following formulas: M c = (c1*B1+c2*B2+…+c m *B m ) / (c1+c2+…+c m ); M c =d1*B1+d2*B2+…+d m *B m,， , d x =c x / (c1+c2+…+c m );

[0065] wherein, M c is the first cell value, B x is the selected first beam value or the beam measurement value of the second beam, c x is B xcorresponding weight factor, m is the number of beams participating in generating the first cell value, 1≤x≤m, the second beam is a beam for which the terminal performs actual measurement to obtain a beam measurement value and is selected to generate the first cell value of the first cell.

[0066] In this embodiment, at least one beam participates in beam selection, and the selected beam participates in the combination to generate the first cell value of the first cell. Among the selected at least one beam, there are not only at least one first beam in the first beam set, but also at least one second beam in the second beam set.

[0067] In one embodiment, the weight factor corresponding to the second beam is 1, so that the processing of the second beam is consistent with the existing mechanism, or the network side device configures a weight factor for the second beam, thereby increasing the flexibility of calculation.

[0068] In one embodiment, the layer three filtering of the first beam value of the first beam based on the first information and the beam filtering coefficient filtered by layer three includes: filtering the first beam value by layer three based on the following formula: F n =(1-a2*x2)*F n-1 +a2*x2*M n ;

[0069] Wherein, F n is the value filtered by layer three; F n-1 is the value filtered by layer three last time; a2 is the beam filtering coefficient; x2 is the second adjustment coefficient; M n is the first beam value.

[0070] In scheme 1, since the weight factor is related to the first prediction accuracy information of the first beam value of the first beam, for example, the lower the prediction accuracy, the lower the weight factor used by the first beam, thereby reducing the inaccuracy of the first cell value caused by the inaccurate prediction of the first beam, improving the accuracy of the first cell value, and helping to improve the mobility performance.

[0071] In scheme 1, the first beam value of the first beam is filtered by layer three based on the second adjustment coefficient corresponding to the first beam and the beam filtering coefficient filtered by layer three. Generally speaking, high prediction accuracy indicates that the first beam value has high credibility, so a high second adjustment coefficient can be corresponded to, thereby increasing the accuracy of the first beam value filtered by layer three.

[0072] Scheme 2: filtering the second cell value by layer three based on the first information and the cell filtering coefficient filtered by layer three; wherein the prediction accuracy information is second prediction accuracy information corresponding to the second cell value, and the first information is a first adjustment coefficient used to adjust the cell filtering coefficient.

[0073] In scheme 2, the terminal determining the first information based on the prediction accuracy information includes: the terminal determining the first information based on the second prediction accuracy information and second information; wherein the second information includes at least one of: a mapping relationship between the second prediction accuracy information and the first information, and a first threshold.

[0074] In an embodiment, in the case that the prediction accuracy corresponding to the second prediction accuracy information is less than or equal to the first threshold: when performing layer three filtering on the second cell value, the first adjustment coefficient takes a value of 0 or does not perform layer three filtering based on the second cell value.

[0075] In an embodiment, before the terminal determines the first information based on the prediction accuracy information and second information, the terminal further receives the second information from a network side device.

[0076] In an embodiment, the second cell value is predicted based on a second AI model, and the second prediction accuracy information includes at least one of:

[0077] 1) prediction accuracy output by the second AI model.

[0078] 2) current prediction accuracy of the second AI model.

[0079] 3) prediction accuracy associated with the second AI model.

[0080] In another embodiment, the second cell value is the first cell value; the second prediction accuracy information is the first prediction accuracy information; or the second prediction accuracy information is an average of prediction accuracies corresponding to a plurality of first prediction accuracy information. That is, scheme 2 can be based on scheme 1 to obtain the first cell value, and perform layer three filtering on the first cell value.

[0081] In an embodiment, the layer three filtering of the second cell value based on the first information and the cell filtering coefficient of layer three filtering includes: performing layer three filtering on the second cell value based on the following formula: F n = (1 - a1 * x1) * F n-1 + a1 * x1 * M n ;

[0082] wherein F n is the value after layer three filtering; F n-1 is the value after layer three filtering last time; a1 is the cell filtering coefficient; x1 is the first adjustment coefficient; M n is the second cell value.

[0083] Optionally, in order to be compatible with the existing mechanism, for M n In the case that the second cell value is completely based on actual measurement, the above formula can also be used uniformly, and the first adjustment coefficient can be 1, that is, no adjustment is needed.

[0084] Generally, high prediction accuracy indicates that the second cell value is highly reliable, so the corresponding first adjustment coefficient is high, and x1 is a coefficient less than or equal to 1, which increases the accuracy of the second cell value after layer 3 filtering.

[0085] Option 3: Obtain a third beam value based on the first information and a second beam value of the first beam, and perform beam selection for beam reporting based on the third beam value; wherein the second beam value is a beam value after layer 3 filtering of the first beam value of the first beam predicted based on a first AI model.

[0086] In one embodiment, obtaining a third beam value based on the first information and a second beam value of the first beam can be: multiplying the second beam value of the first beam by a value indicated by the first information to obtain the third beam value; wherein the value indicated by the first information is a positive number less than or equal to 1.

[0087] In one embodiment, obtaining a third beam value based on the first information and a second beam value of the first beam can be: subtracting a value indicated by the first information from the second beam value of the first beam to obtain the third beam value; wherein the value indicated by the first information is a number greater than or equal to 0.

[0088] Since the second beam value of the first beam has a prediction factor, multiplying or subtracting the value indicated by the first information can reduce the likelihood of the first beam being selected for reporting, thereby improving the accuracy of beam selection.

[0089] In option 3, the terminal determines the first information based on the prediction accuracy information includes: the terminal determines the first information based on the prediction accuracy information and second information; wherein the second information includes at least one of: a mapping relationship between the prediction accuracy information and the first information, a first threshold.

[0090] In one embodiment, in the case that the prediction accuracy corresponding to the prediction accuracy information is less than or equal to the first threshold: when performing beam selection for beam reporting, the first information takes a value of 0 or the first beam is not selected for beam reporting (that is, the first beam is excluded when selecting a beam).

[0091] In one embodiment, before the terminal determines the first information based on the prediction accuracy information and the second information, the terminal further receives the second information from a network side device.

[0092] In an embodiment, the performing the beam selection for the beam reporting based on the third beam value comprises: selecting, from at least one of the first beams and at least one of the third beams of the first cell, up to X beams based on the third beam value and the beam value corresponding to the third beam, the X beams including a beam with the highest beam value and up to X-1 beams higher than a second threshold, wherein the third beam is a beam for which the terminal performs actual measurement to obtain the beam value, and X is an integer greater than or equal to 1.

[0093] In this embodiment, the first beam in the first beam set and the third beam in the second beam set can participate in the beam selection for the beam reporting together, wherein the beam value of the first beam in the first beam set has a prediction factor, and the third beam in the second beam set is actually measured, and the two participate in the beam selection together.

[0094] Scheme 4: obtaining a fourth beam value based on the first information and the first beam value of the first beam, and performing the beam selection for generating the first cell value based on the fourth beam value; wherein the first beam value is a predicted beam value based on a first AI model.

[0095] In an embodiment, obtaining the fourth beam value based on the first information and the first beam value of the first beam can be: multiplying the first beam value of the first beam by a value indicated by the first information to obtain the fourth beam value; wherein the value indicated by the first information is a positive number less than or equal to 1.

[0096] In an embodiment, obtaining the fourth beam value based on the first information and the first beam value of the first beam can be: subtracting a value indicated by the first information from the first beam value of the first beam to obtain the fourth beam value; wherein the value indicated by the first information is a number greater than or equal to 0.

[0097] Since the first beam value of the first beam is predicted, multiplying or subtracting the value indicated by the first information can reduce the possibility of the first beam being selected, thereby improving the accuracy of the first cell value.

[0098] In scheme 4, the terminal determines the first information based on the prediction accuracy information comprises: the terminal determines the first information based on the prediction accuracy information and second information; wherein the second information includes at least one of: a mapping relationship between the prediction accuracy information and the first information, and a first threshold.

[0099] In an embodiment, in a case where the prediction accuracy corresponding to the prediction accuracy information is less than or equal to the first threshold: when performing the beam selection for generating the first cell value, the first information takes a value of 0 or the first beam is not selected to generate the first cell value.

[0100] In an embodiment, before the terminal determines the first information based on the prediction accuracy information and the second information, the method further comprises: receiving, by the terminal, the second information from a network side device.

[0101] In an embodiment, the performing, based on the fourth beam value, the beam selection for generating the first cell value comprises: in the at least one first beam and at least one third beam of the first cell, selecting, based on the fourth beam value and a beam value corresponding to the third beam, a maximum of N beams higher than a third threshold to generate the first cell value, wherein the third beam is a beam for which the terminal performs actual measurement to obtain a beam value, and N is an integer greater than or equal to 1.

[0102] In this embodiment, the first beam in the first beam set and the third beam in the second beam set can participate in the beam selection for generating the first cell value together, wherein the beam value of the first beam in the first beam set has a prediction factor, and the third beam in the second beam set is actually measured, both of which participate in the beam selection together.

[0103] The prediction-related processing method provided by the embodiments of the present application comprises: a terminal obtaining prediction accuracy information; determining first information based on the prediction accuracy information; and performing at least one of the following: 1) generating a first cell value based on the first information and a first beam value of a first beam, improving the accuracy of the first cell value, and being beneficial to improving mobility performance; or performing layer three filtering on a first beam value of a first beam based on the first information and a layer three filtering coefficient of a filtered beam, and increasing the accuracy of the layer three filtered first beam value; 2) performing layer three filtering on a second cell value based on the first information and a layer three filtering coefficient of a filtered cell, and increasing the accuracy of the layer three filtered second cell value; 3) obtaining a third beam value based on the first information and a second beam value of a first beam, and performing beam selection for beam reporting based on the third beam value, thereby improving the accuracy of the beam selection; and 4) obtaining a fourth beam value based on the first information and a first beam value of a first beam, and performing beam selection for generating a first cell value based on the fourth beam value, thereby improving the accuracy of the first cell value.

[0104] Since the predicted beam value or cell value obtained through the AI model has a prediction accuracy problem, the embodiments of the present application determine and use different weight factors for generating a cell value or adjustment coefficients for layer three filtering based on the prediction accuracy, thereby alleviating the mobility performance problem caused by inaccurate prediction.

[0105] To further illustrate the prediction-related processing method provided by the embodiments of the present application, the following will illustrate several specific embodiments.

[0106] Embodiment One

[0107] The embodiment is directed to how to generate more accurate first cell values in the scenario of beam level measurement prediction. The main idea is that the UE obtains a first beam value of at least one first beam in a first beam set through a first AI model, the first beam set is a set of beams in a first cell for which beam value prediction is performed through the first AI model, the first beam value includes a predicted beam value of the first beam or a predicted beam value range of the first beam; the UE determines a weight factor corresponding to the first beam based on first prediction accuracy information of the first beam value of the first beam, the weight factor is a weight factor corresponding to the first beam when the first beam participates in combining the first cell value, and the UE generates a first cell value (including a cell value before layer three filtering) of the first cell based on the first beam value of the at least one first beam and the corresponding weight factor. Since the weight factor is related to the prediction accuracy of the first beam value of the first beam, the mobility performance problem caused by inaccurate prediction is reduced.

[0108] As shown in FIG. 3, the embodiment includes the following steps:

[0109] Step 1: The UE obtains a first beam value of at least one first beam in a first beam set through a first AI model.

[0110] The first beam set is a set of beams in a first cell for which beam value prediction is performed through the first AI model, and the first beam value can be a predicted beam value (for example, -75 dBm) of the first beam or a predicted beam value range (for example, a range from -70 dBm to -80 dBm) of the first beam.

[0111] Optionally, the first AI model also outputs first prediction accuracy information (or error range) of the first beam, that is, the UE performs inference of the AI model to output the first beam value of the first beam and the first prediction accuracy information of the first beam.

[0112] In this embodiment, the first prediction accuracy information can be a percentage, which can represent that the actual value is within the percentage range above and below the predicted value, such as 10%, which means that the actual value is within the range of 10% above and below the predicted value; or it can be a difference value, which can represent that the actual value is within the difference value range above and below the predicted value, such as 5 dBm, which means that the actual value is within the range of 5 dBm above and below the predicted value. It should be noted that the first AI model performs one inference, which can predict multiple first beams. Here, the first prediction accuracy information of the first beam output by the first AI model can be that the first AI model outputs one first prediction accuracy information for each of the multiple first beams, i.e., the first prediction accuracy information of each first beam can be different, or the first AI model outputs one first prediction accuracy information, which is applicable to each of the multiple first beams, i.e., the multiple first beams have the same first prediction accuracy information.

[0113] In this step, the UE can also perform measurement on at least one beam (hereinafter referred to as a second beam) in the second beam set under the first cell, and obtain a beam measurement value of the at least one second beam. The second beam set is a set of beams under the first cell that have beam measurement values obtained by actual measurement. The UE inputs the beam measurement value of the at least one second beam into the first AI model for model inference, and obtains a first beam value of the at least one first beam.

[0114] Step 2: The UE obtains the first prediction accuracy information of the first beam value of the first beam.

[0115] The first prediction accuracy information of the first beam value of the first beam can be at least one of the following:

[0116] 1) The prediction accuracy of the first beam value of the first beam itself, in which case different first beams can correspond to different prediction accuracies.

[0117] 2) The current prediction accuracy of the first AI model, for example, the UE or a network side device can monitor the first AI model to obtain the current prediction accuracy of the first AI model.

[0118] 3) The prediction accuracy associated with the first AI model itself, which can be associated with the first AI model and can be considered as attribute information of the first AI model.

[0119] The first prediction accuracy information of the first beam value of the first beam can be output by the first AI model, such as in the case of "the first AI model further outputs the first prediction accuracy information of the first beam" described in step 1; or obtained based on the output of the first AI model, such as in the case where the first beam value includes "a beam value range of the predicted first beam", the UE can obtain the first prediction accuracy information based on the beam value range, such as the difference between the upper and lower boundaries of the beam value range divided by 2 to obtain the first prediction accuracy information. For example, if the beam value range is "from -70dBm to -80dBm", the first prediction accuracy information is 5dBm deviation.

[0120] Step 3: The UE determines the weight factor corresponding to the first beam based on the first prediction accuracy information of the first beam value of the first beam, and the weight factor is the weight factor corresponding to the first beam when the first beam (selected) participates in producing the first cell value.

[0121] Regarding how the UE determines the weight factor corresponding to the first beam based on the first prediction accuracy information of the first beam value of the first beam, possible methods include:

[0122] Method 1: left to UE implementation, not standardized. Optionally, in the measurement report (such as when the UE sends the first cell value of the first cell to the network side device (such as a base station)), the UE indicates the weight factor used to the network side device.

[0123] Method 2: the UE determines the weight factor corresponding to the first beam based on the first prediction accuracy information of the first beam value of the first beam and second information, wherein the second information can be at least one of: a mapping relationship between the first prediction accuracy information (such as a prediction accuracy range, or a prediction accuracy category) and the weight factor, and a first threshold.

[0124] As shown in FIG. 4, the second information can be sent by the network side device to the UE, such as through Radio Resource Control (RRC) dedicated signaling when configuring the first AI model or measurement configuration, or broadcast in the system information of the cell; the second information can also be protocol specified.

[0125] The mapping relationship information between the first prediction accuracy information and the weight factor can be: for example, the prediction accuracy range is within 3dBm deviation, corresponding to the weight factor 0.8, the prediction accuracy range is between 3dBm to 5dBm deviation, corresponding to the weight factor 0.6, and the prediction accuracy range is above 5dBm deviation, corresponding to the weight factor 0.4; for another example, the prediction accuracy category is high prediction accuracy, corresponding to the weight factor 0.9, the prediction accuracy category is medium prediction accuracy, corresponding to the weight factor 0.7, and the prediction accuracy category is low prediction accuracy, corresponding to the weight factor 0.4.

[0126] Optionally, when the prediction accuracy corresponding to the first prediction accuracy information is lower than or equal to the first threshold, it is determined that the weight factor corresponding to the first beam in generating the first cell value is 0.

[0127] Step 4: The UE generates the first cell value of the first cell based on the first beam value of the at least one first beam and the corresponding weight factor.

[0128] Since the weight factor is related to the first prediction accuracy information of the first beam value of the first beam, for example, the lower the prediction accuracy of the first beam, the lower the weight factor used by the first beam, thereby reducing the problem of inaccurate cell value caused by inaccurate prediction of the first beam, thereby causing the problem of mobility performance.

[0129] Specifically, at least one first beam participates in beam selection, and the selected beam participates in consolidation to generate the first cell value of the first cell. For the beam selection operation, the first beam in the first beam set and the second beam in the second beam set participate in beam selection together, and for the first beam in the first beam set, considering that its first beam value is predicted, there are two methods:

[0130] Method A: Based on the predicted first beam value of at least one first beam in the first beam set, the beam selection is participated, for example, if the predicted first beam value of a first beam is higher than a third threshold (such as absThreshSS-BlocksConsolidation) and is one of the best N (such as nrofSS-BlocksToAverage) beams, then the first beam is selected to participate in consolidation to generate the first cell value of the first cell, which is simple and has little protocol impact.

[0131] Method B (corresponding to the previous scheme 4): The predicted first beam value of at least one first beam in the first beam set is multiplied by a coefficient less than or equal to 1 (such as the coefficient can be the weight factor corresponding to the first beam, or other parameters such as the parameters configured by the base station), or the predicted first beam value of at least one first beam in the first beam set is subtracted by a number greater than or equal to 0, and the fourth beam value of at least one first beam in the first beam set after multiplication or subtraction is used to participate in beam selection.

[0132] For example, among the at least one first beam and at least one third beam of the first cell, the maximum N beams whose fourth beam value and corresponding beam value of the third beam are higher than the third threshold are selected to generate the first cell value, wherein the third beam is a beam for which the terminal performs actual measurement to obtain the beam value, and N is an integer greater than or equal to 1.

[0133] Since the first beam value of the first beam is predicted, multiplying by a coefficient or subtracting a number can reduce the likelihood of the first beam being selected, thereby improving the accuracy of the cell value.

[0134] Optionally, in the case where the first prediction accuracy information of the first beam corresponds to a prediction accuracy less than or equal to a first threshold, the first beam does not participate in the generation of the first cell value, that is, even if the signal of the first beam is higher than the threshold for beam selection, since the prediction accuracy corresponding to the first beam is low, the first beam is not selected (i.e. excluded) to participate in the generation of the first cell value (does not occupy the quota of N), at this time, the maximum N (nrofSS-BlocksToAverage) beams whose signal is higher than the third threshold (absThreshSS-BlocksConsolidation) and whose prediction accuracy is higher than the first threshold are selected to participate in the generation of the first cell value.

[0135] It should be noted that in the case where the first prediction accuracy information output by the first AI model is a prediction value range, the first beam value described above can be the middle value, or the minimum value, or the maximum value of the prediction value range. Optionally, which one (middle value, minimum value, or maximum value) to be used can be configured by the network side device.

[0136] The number of selected beams is not fixed, and in the at least one selected beam, there can be at least one first beam in the first beam set, or there can be at least one second beam in the second beam set. For the operation of consolidating to generate the first cell value of the first cell, the method can be: the first cell value is equal to the sum of the product of each selected beam and its weight factor, and then divided by the sum of the weight factors, the formula can be: M c =(c1*B1+c2*B2+…+c m *B m ) / (c1+c2+…+c m )

[0137] Wherein, M c is the first cell value, B x is the beam measurement value of the selected first beam or second beam, c x is the weight factor corresponding to B x , m is the number of beams participating in the generation of the first cell value, 1≤x≤m, and the second beam is a beam for which the terminal performs actual measurement to obtain a beam measurement value and is selected to generate the first cell value.

[0138] For the above method, another method is: the first cell value is equal to the sum of the product of each selected beam and its final weight factor, wherein the final weight factor of a beam is the weight factor of the beam divided by the sum of the plurality of weight factors, and the formula can be: Mc = d1*B1 + d2*B2 +... + dm*Bm m * B m where d x = c x / (c1 + c2 +... + cm) m

[0139] M c is the first cell value, B x is the selected first beam value or the second beam measurement value, c x is the corresponding weight factor of B x , m is the number of beams participating in the generation of the first cell value, 1≤x≤m, and the second beam is the beam for which the terminal performs actual measurement to obtain the beam measurement value and is selected to generate the first cell value.

[0140] For the second beams in the second beam set (i.e., the actually measured beams), the weight factor of the second beam can be fixed as 1, so that the processing of the second beam remains consistent with the existing mechanism, or the network side device can also configure a weight factor for the second beam, thereby increasing the flexibility of calculation.

[0141] Embodiment Two

[0142] This embodiment (corresponding to the above scheme 2) is directed to the problem of how to perform layer three filtering in the presence of inaccurate second cell values before layer three filtering. As shown in FIG. 5, there are two scenarios as follows:

[0143] 1a. The UE performs measurement to obtain the actual measurement value of the beam in the second beam set of the first cell.

[0144] 2a. The UE performs AI inference based on the actual measurement value of the beam in the second beam set to obtain the predicted value of the beam in the first beam set of the first cell.

[0145] 3a. The UE generates the cell value before layer three filtering of the first cell based on the actual measurement value of the beam in the second beam set and the predicted value of the beam in the first beam set.

[0146] 1b. The UE performs AI inference through an AI model to obtain the cell value before layer three filtering of the first cell.

[0147] 4. The UE performs layer three filtering based on the cell value before layer three filtering of the first cell to obtain the cell value after layer three filtering of the first cell.

[0148] 5. The UE performs measurement event evaluation, conditional handover judgment, etc. based on the cell value after layer three filtering of the first cell.

[0149] ​Among them, steps 1a-3a are the scene of beam-level measurement prediction (hereinafter referred to as scene one), and step 1b is the scene of cell-level measurement prediction (i.e., the second AI model directly outputs the layer three pre-filtering cell value of the first cell, which is referred to as scene two). Embodiment one is a solution for step 3a, and the present embodiment is a solution for step 4.

[0150] In order to cope with the influence of signal fluctuation, layer three needs to perform layer three smoothing (filtering) on the measurement value of the cell, that is, to perform weighted average on the latest cell measurement value and the previous smoothing value, so as to obtain the smoothed cell measurement value, which is used for measurement event evaluation and cell measurement value reporting in the measurement report. The network side device can control the smoothing degree (network side device configuration) by adjusting the weighting coefficient (base station configures k value, and obtains filtering coefficient a based on k value).

[0151] The main idea of the embodiment is that in scene one or scene two, the UE obtains the second cell value (layer three pre-filtering cell value, i.e., M n ), and the second prediction accuracy information (or error range information) corresponding to the second cell value, the UE determines the first adjustment coefficient x1 based on the second prediction accuracy information corresponding to the second cell value, the first adjustment coefficient x1 is used to adjust the cell filtering coefficient a1, and the UE performs layer three filtering based on the second cell value of the first cell and the first adjustment coefficient.

[0152] As shown in FIG. 6, the embodiment includes the following steps:

[0153] Step 1: The UE obtains the second prediction accuracy information corresponding to the second cell value.

[0154] Step 2: The UE determines the first adjustment coefficient based on the second prediction accuracy information, and the first adjustment coefficient is used to adjust the cell filtering coefficient.

[0155] Step 3: The UE performs layer three filtering on the second cell value based on the first adjustment coefficient.

[0156] For step 1 of FIG. 6, how to obtain the second prediction accuracy information corresponding to the second cell value includes the following solutions:

[0157] For scene two, the second prediction accuracy information corresponding to the second cell value can be output by the second AI model at the same time as the output of the second cell value, or the current prediction accuracy of the second AI model can be obtained by monitoring the second AI model by the UE or the network side device; or it can be the prediction accuracy associated with the second AI model itself.

[0158] For scenario one, how the UE obtains the second prediction accuracy information corresponding to the second cell value before the third layer filtering of the first cell can be left to the UE to implement, or the first prediction accuracy information of the first AI model predicted by beam-level measurement can be used; or it can be the average value of the prediction accuracy corresponding to the first beam that participated in generating the second cell value (obtained from the first prediction accuracy information).

[0159] For step 2 in Figure 6, different second prediction accuracy information can correspond to different first adjustment coefficients. How can the UE determine the first adjustment coefficient based on the second prediction accuracy information corresponding to the second cell value? The following schemes are available:

[0160] Method 1: When the second prediction accuracy information is a percentage, use the second prediction accuracy information as the first adjustment coefficient.

[0161] Method 2: Leave it to the UE to implement, without standardization.

[0162] Method 3: The UE determines the first adjustment coefficient based on the second prediction accuracy information and the second information corresponding to the second cell value, wherein the second information may be at least one of the following: the mapping relationship between the second prediction accuracy information (such as prediction accuracy range or prediction accuracy category) and the first adjustment coefficient, and a first threshold.

[0163] The second information can be sent to the UE by the network-side equipment, such as when configuring the second AI model or measurement configuration, by sending it to the UE via RRC dedicated signaling, or by broadcasting system information of the cell; the second information can also be specified by the protocol.

[0164] Optionally, when the prediction accuracy corresponding to the second prediction accuracy information is lower than or equal to the first threshold, the third-level filtering is not performed, or in other words, the third-level filtering is performed, but the first adjustment coefficient value is 0.

[0165] For step 3 in Figure 6, the final filtering coefficient used for layer 3 filtering is a1*x1. Generally speaking, high prediction accuracy indicates high reliability of the second cell value, so the corresponding first adjustment coefficient x1 is high, where x1 is a coefficient less than or equal to 1.

[0166] The corresponding formula can be as follows: F n = (1 – a1 * x1) * F n-1 +a1*x1*M n ;

[0167] Among them, F n This is the value after three layers of filtering; F n-1 It is the value after the last layer 3 filtering; a1 is the cell filtering coefficient; x1 is the first adjustment coefficient; M n It is the value of the second cell.

[0168] Optionally, in order to be compatible with the existing mechanism, for M n In the case of completely basing the cell value on actual measurement, the above formula can also be uniformly used, and in this case, the first adjustment coefficient can be taken as 1, that is, no adjustment is needed.

[0169] Embodiment Three

[0170] Embodiments One and Two are directed to cell values, while this embodiment is directed to beam-based layer three filtering and selection reporting, mainly including:

[0171] Enhancement One (i.e., step 4 below) is similar to Embodiment Two, with the difference being that Embodiment Two is directed to cell value-based layer three filtering, while this embodiment is directed to beam value-based layer three filtering enhancement, that is, introducing an adjustment coefficient mechanism for beam-based layer three filtering: determining an adjustment coefficient based on the prediction accuracy information of the beam, and performing layer three filtering on the beam based on the adjustment coefficient.

[0172] Enhancement Two (i.e., step 5 below, see details of step 5 for specific enhancement scheme) is similar to the beam selection mechanism of step 4 of Embodiment One.

[0173] As shown in FIG. 7, this embodiment includes the following steps:

[0174] Steps 1 and 2: refer to steps 1 and 2 of Embodiment One.

[0175] Step 3: the UE determines a second adjustment coefficient based on the first prediction accuracy information corresponding to the first beam value of the first beam, and the second adjustment coefficient is used to adjust the beam filtering coefficient.

[0176] Different first prediction accuracy information can correspond to different second adjustment coefficients, and how the UE determines the second adjustment coefficient based on the first prediction accuracy information corresponding to the first beam value of the first beam can be:

[0177] Method 1: in the case of the first prediction accuracy information being a percentage, using the first prediction accuracy information as the second adjustment coefficient.

[0178] Method 2: left to UE implementation, without standardization.

[0179] Method 3: the UE determines the second adjustment coefficient based on the first prediction accuracy information and second information, wherein the second information can be at least one of: a mapping relationship between the first prediction accuracy information (such as a prediction accuracy range, or a prediction accuracy category) and the second adjustment coefficient, and a first threshold.

[0180] The second information can be sent by the network side device to the UE, such as being sent to the UE by RRC dedicated signaling when the first AI model or the measurement configuration is configured, or being broadcast by system information of the cell; or the second information can be defined by a protocol.

[0181] Optionally, when the prediction accuracy corresponding to the first prediction accuracy information is lower than or equal to the first threshold, the layer three filtering is not performed based on the first beam value, or in other words, the layer three filtering is performed but the second adjustment coefficient value is 0.

[0182] Optionally, the second information can be the same as the second information in Embodiment 2 to simplify the protocol complexity, or can be different to improve flexibility.

[0183] Step 4: The UE performs layer three filtering on the predicted first beam value of the first beam based on the second adjustment coefficient, that is, the final filtering coefficient used in the layer three filtering is a2*x2. Generally, high prediction accuracy indicates that the first beam value is highly reliable, and therefore corresponds to a high second adjustment coefficient x2. x2 is a coefficient less than or equal to 1.

[0184] Step 4 corresponds to the branch of “performing layer three filtering on the first beam value of the first beam based on the first information and the beam filtering coefficient of layer three filtering, the first information being a second adjustment coefficient corresponding to the first beam” in Scheme 1.

[0185] The corresponding formula can be as follows: n =(1-a2*x2)*F n-1 +a2*x2*M n

[0186] Wherein, F n is the value after layer three filtering; F n-1 is the value after the last layer three filtering; a2 is the beam filtering coefficient; x2 is the second adjustment coefficient; M n is the first beam value.

[0187] Optionally, in order to be compatible with the existing mechanism, for the case where M n is the beam value obtained based on actual measurement, the above formula can also be used uniformly, and x2 can be 1, that is, no adjustment is needed.

[0188] Step 5: The UE performs beam selection operation for beam reporting based on the layer 3 filtered second beam value of the first beam, the first beam in the first beam set and the second beam in the second beam set can participate in beam selection together, for the first beam in the first beam set, considering that its second beam value has a predicted factor, while the second beam in the second beam set is the actual measured beam value, the two are different, when participating in beam selection together, there are two methods as follows:

[0189] Method A: Participate in beam selection based on the layer 3 filtered second beam value of at least one first beam in the first beam set, for example, if the layer 3 filtered second beam value of a first beam is higher than a second threshold (such as absThreshSS-BlocksConsolidation) and is one of the best X (such as maxNrofRS-IndexesToReport) beams of the first cell, then the first beam is selected for beam reporting, this method is simple and has little protocol impact.

[0190] Method B (Scheme 3): The layer 3 filtered second beam value of at least one first beam in the first beam set is multiplied by a coefficient less than or equal to 1 (such as the second adjustment coefficient corresponding to the first beam determined in step 3, or other parameters such as parameters configured by the network side device), or the layer 3 filtered second beam value of at least one first beam in the first beam set is subtracted by a number greater than or equal to 0, and participate in beam selection based on the third beam value of at least one first beam in the first beam set multiplied by the coefficient or subtracted by a number.

[0191] For example, among at least one first beam and at least one third beam of the first cell, based on the third beam value and the beam value corresponding to the third beam, at most X beams are selected for beam reporting, the X beams include the beam with the highest beam value and at most X-1 beams higher than the second threshold, wherein the third beam is the beam for which the terminal performs actual measurement to obtain the beam value, and X is an integer greater than or equal to 1.

[0192] Since the second beam value of the first beam has a predicted factor, multiplying the coefficient or subtracting a number can reduce the possibility of the first beam being selected for reporting.

[0193] Optionally, when the prediction accuracy corresponding to the first beam is lower than or equal to a first threshold, the first beam is not selected for reporting, that is, even if the signal of the first beam is higher than the threshold for beam selection, the first beam is not selected (that is, excluded) for reporting (does not occupy the quota of X) due to the low prediction accuracy corresponding to the first beam. At this time, the scheme is to select the maximum X (maxNrofRS-IndexesToReport) beams whose signal is higher than a second threshold (absThreshSS-BlocksConsolidation) and whose prediction accuracy is higher than the first threshold for beam reporting.

[0194] Finally, the UE reports the beam information corresponding to the selected beam to the network side device in the measurement report. The beam information can be a beam index, or a second beam value filtered by layer 3, and optionally, for method B, a third beam value multiplied by the coefficient.

[0195] It should be noted that the above two enhancements can be implemented independently, for example, the UE performs method A of steps 4 and 5, or step 4 is not enhanced (that is, instead of step 4, the UE filters the predicted first beam value of the first beam by layer 3 based on the existing mechanism), but performs method B of step 5; or can be implemented simultaneously, for example, the UE performs method B of steps 4 and 5.

[0196] The prediction-related processing method according to the embodiments of the present application is described in detail above in combination with FIGS. 2 to 7. The prediction-related processing method according to another embodiment of the present application will be described in detail below in combination with FIG. 8. It can be understood that the network side device described from the network side device and the interaction with the terminal are the same as or corresponding to the description of the terminal side in the method shown in FIGS. 2 to 7. To avoid repetition, the relevant description is appropriately omitted.

[0197] FIG. 8 is a flowchart of a prediction-related processing method according to an embodiment of the present application, which can be applied to a network side device. As shown in FIG. 8, the method 800 includes the following steps.

[0198] S802: The network-side device sends second information to the terminal, where the second information is used by the terminal to determine the first information based on prediction accuracy information; where the first information is used for at least one of the following: 1) generating a first cell value based on a first beam value of a first beam, the first information being a weight factor corresponding to the first beam; or performing Layer 3 filtering on a first beam value of a first beam based on a beam filtering coefficient of Layer 3 filtering, the first information being a second adjustment coefficient corresponding to the first beam; where the prediction accuracy information is first prediction accuracy information corresponding to the first beam value, the first beam value being a beam value predicted based on a first AI model, and the second adjustment coefficient is used to adjust the beam filtering coefficient; 2) performing Layer 3 filtering on a second cell value based on a cell filtering coefficient of Layer 3 filtering; where the prediction accuracy information is second prediction accuracy information corresponding to the second cell value, and the first information is a first adjustment coefficient used to adjust the cell filtering coefficient; 3) obtaining a third beam value based on a second beam value of a first beam, and performing beam selection for beam reporting based on the third beam value; where the second beam value is a beam value obtained by performing Layer 3 filtering on a first beam value of the first beam predicted based on a first AI model; 4) obtaining a fourth beam value based on a first beam value of a first beam, and performing beam selection for generating a first cell value based on the fourth beam value; where the first beam value is a beam value predicted based on a first AI model.

[0199] In one embodiment, the second information can include at least one of the following: a mapping relationship between the prediction accuracy information and the first information, and a first threshold.

[0200] In one embodiment, the first threshold is used to: in a case where a prediction accuracy corresponding to the prediction accuracy information is less than or equal to the first threshold: in generating the first cell value, a weight factor corresponding to the first beam value is valued as 0 or the first beam is not selected to participate in the generation process of the first cell value; or, in performing Layer 3 filtering on the second cell value, the first adjustment coefficient is valued as 0 or Layer 3 filtering is not performed based on the second cell value; or, in performing Layer 3 filtering on the first beam value, the second adjustment coefficient is valued as 0 or Layer 3 filtering is not performed based on the first beam value; or, in performing beam selection for beam reporting, the first information is valued as 0 or the first beam is not selected for beam reporting; or, in performing beam selection for generating a first cell value, the first information is valued as 0 or the first beam is not selected to generate the first cell value.

[0201] The prediction-related processing method provided in the embodiments of this application includes the following steps: a network-side device sends second information to a terminal, the second information being used for the terminal to determine first information based on prediction accuracy information; and the first information is used for at least one of the following: 1) generating a first cell value based on a first beam value of a first beam, improving the accuracy of the first cell value, and improving the mobility performance; or performing layer three filtering on the first beam value of the first beam based on a beam filtering coefficient of layer three filtering, and increasing the accuracy of the first beam value after the layer three filtering; 2) performing layer three filtering on a second cell value based on a cell filtering coefficient of layer three filtering, and increasing the accuracy of the second cell value after the layer three filtering; 3) obtaining a third beam value based on a second beam value of the first beam, performing beam selection for beam reporting based on the third beam value, and improving the accuracy of the beam selection; and 4) obtaining a fourth beam value based on the first beam value of the first beam, performing beam selection for generating the first cell value based on the fourth beam value, and improving the accuracy of the first cell value.

[0202] The prediction-related processing method provided in the embodiments of this application includes the following steps: a network-side device sends second information to a terminal, the second information being used for the terminal to determine first information based on prediction accuracy information; and the first information is used for at least one of the following: 1) generating a first cell value based on a first beam value of a first beam, improving the accuracy of the first cell value, and improving the mobility performance; or performing layer three filtering on the first beam value of the first beam based on a beam filtering coefficient of layer three filtering, and increasing the accuracy of the first beam value after the layer three filtering; 2) performing layer three filtering on a second cell value based on a cell filtering coefficient of layer three filtering, and increasing the accuracy of the second cell value after the layer three filtering; 3) obtaining a third beam value based on a second beam value of the first beam, performing beam selection for beam reporting based on the third beam value, and improving the accuracy of the beam selection; and 4) obtaining a fourth beam value based on the first beam value of the first beam, performing beam selection for generating the first cell value based on the fourth beam value, and improving the accuracy of the first cell value.

[0203] The prediction-related processing method provided in the embodiments of this application includes the following steps: a network-side device sends second information to a terminal, the second information being used for the terminal to determine first information based on prediction accuracy information; and the first information is used for at least one of the following: 1) generating a first cell value based on a first beam value of a first beam, improving the accuracy of the first cell value, and improving the mobility performance; or performing layer three filtering on the first beam value of the first beam based on a beam filtering coefficient of layer three filtering, and increasing the accuracy of the first beam value after the layer three filtering; 2) performing layer three filtering on a second cell value based on a cell filtering coefficient of layer three filtering, and increasing the accuracy of the second cell value after the layer three filtering; 3) obtaining a third beam value based on a second beam value of the first beam, performing beam selection for beam reporting based on the third beam value, and improving the accuracy of the beam selection; and 4) obtaining a fourth beam value based on the first beam value of the first beam, performing beam selection for generating the first cell value based on the fourth beam value, and improving the accuracy of the first cell value.

[0204] The processing apparatus related to prediction includes a receiving module, a sending module and a processing module. The receiving module, the sending module and the processing module can be implemented by software or by hardware. When implemented by hardware, the processing module can be implemented by a processor. For example, the processor can include a general-purpose processor, a special-purpose processor, a central processing unit (CPU), a microprocessor, a digital signal processor (DSP), an artificial intelligent (AI) processor, a graphics processing unit (GPU), an application specific integrated circuit (ASIC), a network processor (NP), a field programmable gate array (FPGA) or other programmable logic device, a gate circuit, a transistor, a discrete hardware component, etc. The receiving module and the sending module can be implemented by a communication interface. The communication interface can include one or more of a transceiver, a pin, a circuit, a bus, a radio frequency unit, etc.

[0205] Specifically, referring to FIG. 9, when the prediction-related processing device is a terminal or a component in the terminal, the prediction-related processing device 900 includes a processing module 902 configured to obtain prediction accuracy information, determine first information based on the prediction accuracy information, and perform at least one of the following: 1) generate a first cell value based on the first information and a first beam value of a first beam, the first information being a weight factor corresponding to the first beam, or perform layer-three filtering on a first beam value of a first beam based on the first information and a layer-three filtered beam filtering coefficient, the first information being a second adjustment coefficient corresponding to the first beam; wherein the prediction accuracy information is first prediction accuracy information corresponding to the first beam value, the first beam value being a beam value predicted based on a first AI model, and the second adjustment coefficient is used to adjust the beam filtering coefficient; 2) perform layer-three filtering on a second cell value based on the first information and a layer-three filtered cell filtering coefficient; wherein the prediction accuracy information is second prediction accuracy information corresponding to the second cell value, and the first information is a first adjustment coefficient used to adjust the cell filtering coefficient; 3) obtain a third beam value based on the first information and a second beam value of the first beam, and perform beam selection for beam reporting based on the third beam value; wherein the second beam value is a beam value obtained by performing layer-three filtering on the first beam value of the first beam predicted based on the first AI model; and 4) obtain a fourth beam value based on the first information and the first beam value of the first beam, and perform beam selection for generating the first cell value based on the fourth beam value; wherein the first beam value is a beam value predicted based on the first AI model.

[0206] In the embodiments of the present application, the terminal obtains prediction accuracy information, determines first information based on the prediction accuracy information, and performs at least one of the following: 1) generates a first cell value based on the first information and a first beam value of a first beam, improves the accuracy of the first cell value, and is beneficial to improving the mobility performance; or performs layer-three filtering on a first beam value of a first beam based on the first information and a layer-three filtered beam filtering coefficient, and increases the accuracy of the layer-three filtered first beam value; 2) performs layer-three filtering on a second cell value based on the first information and a layer-three filtered cell filtering coefficient, and increases the accuracy of the layer-three filtered second cell value; 3) obtains a third beam value based on the first information and a second beam value of the first beam, and performs beam selection for beam reporting based on the third beam value, thereby improving the accuracy of the beam selection; and 4) obtains a fourth beam value based on the first information and the first beam value of the first beam, and performs beam selection for generating the first cell value based on the fourth beam value, thereby improving the accuracy of the first cell value.

[0207] In an embodiment, the first prediction accuracy information comprises at least one of: 1) a prediction accuracy of the first beam value; 2) a current prediction accuracy of the first AI model; and 3) a prediction accuracy associated with the first AI model.

[0208] In an embodiment, the processing module 902 is configured to determine the first information based on the prediction accuracy information and second information, wherein the second information comprises at least one of: a mapping relationship between the prediction accuracy information and the first information, and a first threshold.

[0209] In an embodiment, when the prediction accuracy corresponding to the prediction accuracy information is less than or equal to the first threshold: when the first cell value is generated, the weight factor corresponding to the first beam value is 0 or the first beam is not selected to participate in the generation process of the first cell value; or, when the second cell value is layer three filtered, the first adjustment coefficient is 0 or the layer three filtering is not performed based on the second cell value; or, when the first beam value is layer three filtered, the second adjustment coefficient is 0 or the layer three filtering is not performed based on the first beam value; or, when the beam selection for beam reporting is performed, the first information is 0 or the first beam is not selected for beam reporting; or, when the beam selection for generating the first cell value is performed, the first information is 0 or the first beam is not selected to generate the first cell value.

[0210] In an embodiment, the apparatus further comprises a receiving module configured to receive the second information from a network side device.

[0211] In an embodiment, the processing module 902 is configured to generate the first cell value based on one of the following formulas: M c = (c1*B1 + c2*B2 +…+c m *B m ) / (c1+c2+…+c m ); and M c =d1*B1+d2*B2+…+d m *B m,， , d x =c x / (c1+c2+…+c m ).

[0212] wherein M c is the first cell value, B x is a beam measurement value of the selected first beam value or second beam, c x is B xa corresponding weight factor, m is a number of beams participating in generating the first cell value, 1≤x≤m, the second beam is a beam for which the terminal performs actual measurement to obtain a beam measurement value and is selected to generate the first cell value.

[0213] In one embodiment, the second beam corresponds to a weight factor of 1.

[0214] In one embodiment, the second cell value is predicted based on a second AI model, and the second prediction accuracy information includes at least one of: 1) a prediction accuracy output by the second AI model; 2) a current prediction accuracy of the second AI model; and 3) a prediction accuracy associated with the second AI model.

[0215] In one embodiment, the second cell value is the first cell value; the second prediction accuracy information is the first prediction accuracy information; or the second prediction accuracy information is an average of prediction accuracies corresponding to a plurality of the first prediction accuracy information.

[0216] In one embodiment, the processing module 902 is configured to perform layer-3 filtering on the second cell value based on the following formula: F n = (1-a1*x1)*F n-1 +a1*x1*M n ;

[0217] wherein F n is a value after layer-3 filtering; F n-1 is a value after last layer-3 filtering; a1 is the cell filtering coefficient; x1 is the first adjustment coefficient; and M n is the second cell value.

[0218] In one embodiment, the processing module 902 is configured to perform layer-3 filtering on the first beam value based on the following formula: F n = (1-a2*x2)*F n-1 +a2*x2*M n ;

[0219] wherein F n is a value after layer-3 filtering; F n-1 is a value after last layer-3 filtering; a2 is the beam filtering coefficient; x2 is the second adjustment coefficient; and M n is the first beam value.

[0220] In an embodiment, the processing module 902 is configured to: multiply the second beam value of the first beam by a value indicated by the first information to obtain a third beam value; wherein the value indicated by the first information is a positive number less than or equal to 1; or subtract the value indicated by the first information from the second beam value of the first beam to obtain the third beam value; wherein the value indicated by the first information is a number greater than or equal to 0.

[0221] In an embodiment, the processing module 902 is configured to, among the at least one first beam and at least one third beam of the first cell, select up to X beams based on the third beam value and the beam value corresponding to the third beam, the X beams including a beam with the highest beam value and up to X-1 beams higher than a second threshold, wherein the third beam is a beam for which the terminal performs actual measurement to obtain a beam value, and X is an integer greater than or equal to 1.

[0222] In an embodiment, the processing module 902 is configured to: multiply the first beam value of the first beam by a value indicated by the first information to obtain a fourth beam value; wherein the value indicated by the first information is a positive number less than or equal to 1; or subtract the value indicated by the first information from the first beam value of the first beam to obtain the fourth beam value; wherein the value indicated by the first information is a number greater than or equal to 0.

[0223] In an embodiment, the processing module 902 is configured to, among the at least one first beam and at least one third beam of the first cell, select up to N beams higher than a third threshold based on the fourth beam value and the beam value corresponding to the third beam to generate the first cell value, wherein the third beam is a beam for which the terminal performs actual measurement to obtain a beam value, and N is an integer greater than or equal to 1.

[0224] Referring to FIG. 10, when the prediction-related processing apparatus is a network-side device or a component in the network-side device, the prediction-related processing apparatus 1000 includes a sending module 1002 configured to send second information to a terminal, the second information being used by the terminal to determine first information based on prediction accuracy information; wherein the first information is used for at least one of the following: 1) generating a first cell value based on a first beam value of a first beam, the first information being a weight factor corresponding to the first beam; or performing layer 3 filtering on a first beam value of the first beam based on a layer 3 filtered beam filtering coefficient, the first information being a second adjustment coefficient corresponding to the first beam; wherein the prediction accuracy information is first prediction accuracy information corresponding to the first beam value, the first beam value being a beam value predicted based on a first AI model, and the second adjustment coefficient is used to adjust the beam filtering coefficient; 2) performing layer 3 filtering on a second cell value based on a layer 3 filtered cell filtering coefficient; wherein the prediction accuracy information is second prediction accuracy information corresponding to the second cell value, and the first information is a first adjustment coefficient used to adjust the cell filtering coefficient; 3) obtaining a third beam value based on a second beam value of a first beam, and performing beam selection for beam reporting based on the third beam value; wherein the second beam value is a beam value obtained by performing layer 3 filtering on a first beam value of the first beam predicted based on a first AI model; 4) obtaining a fourth beam value based on a first beam value of a first beam, and performing beam selection for generating a first cell value based on the fourth beam value; wherein the first beam value is a beam value predicted based on a first AI model.

[0225] The prediction-related processing apparatus provided by the embodiments of the present application sends second information to a terminal, and the second information is used by the terminal to determine first information based on prediction accuracy information; wherein the first information is used for at least one of the following: 1) generating a first cell value based on a first beam value of a first beam, improving the accuracy of the first cell value, and being beneficial to improving mobility performance; or performing layer 3 filtering on a first beam value of the first beam based on a layer 3 filtered beam filtering coefficient, and increasing the accuracy of the first beam value after layer 3 filtering; 2) performing layer 3 filtering on a second cell value based on a layer 3 filtered cell filtering coefficient, and increasing the accuracy of the second cell value after layer 3 filtering; 3) obtaining a third beam value based on a second beam value of a first beam, and performing beam selection for beam reporting based on the third beam value, and improving the accuracy of beam selection; 4) obtaining a fourth beam value based on a first beam value of a first beam, and performing beam selection for generating a first cell value based on the fourth beam value, thereby improving the accuracy of the first cell value.

[0226] In one embodiment, the second information can include at least one of the following: a mapping relationship between the prediction accuracy information and the first information, and a first threshold.

[0227] In an embodiment, the first threshold is used to: in a case where the prediction accuracy corresponding to the prediction accuracy information is less than or equal to the first threshold, the weight factor corresponding to the first beam value is 0 or the first beam is not selected to participate in the generation process of the first cell value when the first cell value is generated; or the first adjustment coefficient is 0 or the layer three filtering is not performed based on the second cell value when the second cell value is layer three filtered; or the second adjustment coefficient is 0 or the layer three filtering is not performed based on the first beam value when the first beam value is layer three filtered; or the first information is 0 or the first beam is not selected for beam reporting when the beam selection for beam reporting is performed; or the first information is 0 or the first beam is not selected to generate the first cell value when the beam selection for generating the first cell value is performed.

[0228] The prediction-related processing apparatus provided in the embodiments of the present application can implement each process implemented by the method embodiments of FIGS. 2 to 8 and achieve the same technical effects. To avoid repetition, details are not described herein.

[0229] As shown in FIG. 11, the embodiments of the present application further provide a communication device 1100, which includes a processor 1101 and a memory 1102, and the memory 1102 stores programs or instructions executable on the processor 1101. For example, when the communication device 1100 is a terminal, the programs or instructions are executed by the processor 1101 to implement each step of the above-described prediction-related processing method embodiments and achieve the same technical effects. When the communication device 1100 is a network-side device, the programs or instructions are executed by the processor 1101 to implement each step of the above-described prediction-related processing method embodiments and achieve the same technical effects. To avoid repetition, details are not described herein.

[0230] The embodiments of the present application further provide a terminal, which includes a processor and a communication interface, the communication interface is coupled to the processor, and the processor is configured to run programs or instructions to implement the steps in the method embodiments shown in FIG. 2. The terminal embodiments correspond to the above-described terminal-side method embodiments, and each implementation process and implementation manner of the above-described method embodiments can be applied to the terminal embodiments and achieve the same technical effects. The terminal can be the prediction-related processing apparatus shown in FIG. 9. Specifically, FIG. 12 is a hardware structure schematic diagram of a terminal implementing the embodiments of the present application.

[0231] The terminal 1200 includes, but is not limited to, at least part of components such as a radio frequency unit 1201, a network module 1202, an audio output unit 1203, an input unit 1204, a sensor 1205, a display unit 1206, a user input unit 1207, an interface unit 1208, a memory 1209, and a processor 1210.

[0232] Those skilled in the art can understand that the terminal 1200 can further include a power supply (such as a battery) for supplying power to each component, and the power supply can be logically connected to the processor 1210 through a power management system, so as to realize functions such as management of charging, discharging, and power consumption management through the power management system. The terminal structure shown in FIG. 12 does not constitute a limitation on the terminal, and the terminal can include more or fewer components than those shown, or combine certain components, or different component arrangements, which are not described here.

[0233] It should be understood that in the embodiments of the present application, the input unit 1204 can include a graphics processor 12041 and a microphone 12042, and the graphics processor 12041 processes image data of a still picture or a video obtained by an image capture device (such as a camera) in a video capture mode or an image capture mode. The display unit 1206 can include a display panel 12061, which can be configured in the form of a liquid crystal display, an organic light-emitting diode, etc. The user input unit 1207 includes at least one of a touch panel 12071 and other input devices 12072. The touch panel 12071 is also called a touch screen. The touch panel 12071 can include two parts of a touch detection device and a touch controller. The other input devices 12072 can include, but are not limited to, a physical keyboard, function keys (such as volume control keys, on-off keys, etc.), trackballs, mice, joysticks, etc., which are not described here.

[0234] In the embodiments of the present application, the radio frequency unit 1201 can transmit downlink data from the network side device to the processor 1210 for processing after receiving the downlink data. In addition, the radio frequency unit 1201 can send uplink data to the network side device. Generally, the radio frequency unit 1201 includes, but is not limited to, an antenna, an amplifier, a transceiver, a coupler, a low noise amplifier, a duplexer, etc.

[0235] The memory 1209 can be used to store software programs or instructions and various data. The memory 1209 can mainly include a first storage area storing programs or instructions and a second storage area storing data, wherein the first storage area can store an operating system, at least one application program required by a function (such as a sound playing function, an image playing function, etc.), and the like. In addition, the memory 1209 can include a volatile memory or a non-volatile memory. The non-volatile memory can be a Read-Only Memory (ROM), a Programmable ROM (PROM), an Erasable PROM (EPROM), an Electrically EPROM (EEPROM), or a flash memory. The volatile memory can be a Random Access Memory (RAM), a Static RAM (SRAM), a Dynamic RAM (DRAM), a Synchronous DRAM (SDRAM), a Double Data Rate SDRAM (DDR SDRAM), an Enhanced SDRAM (ESDRAM), a Synch link DRAM (SLDRAM), and a Direct Rambus RAM (DRRAM). The memory 1209 in the embodiments of the present application includes but is not limited to these and any other suitable types of memory.

[0236] The processor 1210 can include one or more processing units; optionally, the processor 1210 integrates an application processor and a modem processor, wherein the application processor mainly processes operations related to an operating system, a user interface, and an application program, and the modem processor mainly processes wireless communication signals, such as a baseband processor. It can be understood that the above-mentioned modem processor can also not be integrated into the processor 1210.

[0237] The processor 1210 is configured to acquire prediction accuracy information, determine first information based on the prediction accuracy information, and perform at least one of the following: generate a first cell value based on the first information and a first beam value of a first beam, the first information being a weight factor corresponding to the first beam; or perform layer-three filtering on a first beam value of a first beam based on the first information and a layer-three filtered beam filtering coefficient, the first information being a second adjustment coefficient corresponding to the first beam; wherein the prediction accuracy information is first prediction accuracy information corresponding to the first beam value, the first beam value being a beam value predicted based on a first AI model, and the second adjustment coefficient is used to adjust the beam filtering coefficient; perform layer-three filtering on a second cell value based on the first information and a layer-three filtered cell filtering coefficient; wherein the prediction accuracy information is second prediction accuracy information corresponding to the second cell value, the first information being a first adjustment coefficient, and the first adjustment coefficient is used to adjust the cell filtering coefficient; obtain a third beam value based on the first information and a second beam value of the first beam, and perform beam selection for beam reporting based on the third beam value; wherein the second beam value is a beam value obtained by performing layer-three filtering on the first beam value of the first beam predicted based on the first AI model; obtain a fourth beam value based on the first information and the first beam value of the first beam, and perform beam selection for generating the first cell value based on the fourth beam value; wherein the first beam value is a beam value predicted based on the first AI model.

[0238] In the embodiments of the present application, the terminal acquires prediction accuracy information, determines first information based on the prediction accuracy information, and performs at least one of the following: 1) generates a first cell value based on the first information and a first beam value of a first beam, improves the accuracy of the first cell value, and is beneficial to improving the mobility performance; or performs layer-three filtering on a first beam value of a first beam based on the first information and a layer-three filtered beam filtering coefficient, and increases the accuracy of the layer-three filtered first beam value; 2) performs layer-three filtering on a second cell value based on the first information and a layer-three filtered cell filtering coefficient, and increases the accuracy of the layer-three filtered second cell value; 3) obtains a third beam value based on the first information and a second beam value of the first beam, and performs beam selection for beam reporting based on the third beam value, thereby improving the accuracy of the beam selection; and 4) obtains a fourth beam value based on the first information and the first beam value of the first beam, and performs beam selection for generating the first cell value based on the fourth beam value, thereby improving the accuracy of the first cell value.

[0239] It can be understood that the implementation processes of the implementation manners mentioned in the embodiments can refer to the related descriptions of the prediction-related processing method embodiments and achieve the same or corresponding technical effects. To avoid repetition, they will not be described here again.

[0240] The embodiment of the present application also provides a network side device, comprising a processor and a communication interface, the communication interface is coupled with the processor, and the processor is used to run programs or instructions to realize the steps of the method embodiment shown in FIG. 8. The network side device embodiment corresponds to the network side device method embodiment described above, and each implementation process and implementation manner of the method embodiment can be applied to the network side device embodiment and can achieve the same technical effects.

[0241] Specifically, the embodiment of the present application also provides a network side device, which can be a prediction-related processing apparatus shown in FIG. 10. As shown in FIG. 13, the network side device 1300 comprises an antenna 131, a radio frequency device 132, a baseband device 133, a processor 134 and a memory 135. The antenna 131 is connected with the radio frequency device 132. In the uplink direction, the radio frequency device 132 receives information through the antenna 131, and sends the received information to the baseband device 133 for processing. In the downlink direction, the baseband device 133 processes the information to be sent and sends it to the radio frequency device 132, and the radio frequency device 132 processes the received information and sends it out through the antenna 131.

[0242] The radio frequency device 132 is configured to send second information to a terminal, the second information being used by the terminal to determine first information based on prediction accuracy information; wherein the first information is used for at least one of the following: generating a first cell value based on a first beam value of a first beam, the first information being a weight factor corresponding to the first beam; or performing layer three filtering on a first beam value of a first beam based on a layer three filtering beam filtering coefficient, the first information being a second adjustment coefficient corresponding to the first beam; wherein the prediction accuracy information is first prediction accuracy information corresponding to the first beam value, the first beam value being a beam value predicted based on a first AI model, and the second adjustment coefficient is used to adjust the beam filtering coefficient; performing layer three filtering on a second cell value based on a layer three filtering cell filtering coefficient; wherein the prediction accuracy information is second prediction accuracy information corresponding to the second cell value, the first information is a first adjustment coefficient, and the first adjustment coefficient is used to adjust the cell filtering coefficient; obtaining a third beam value based on a second beam value of a first beam, and performing beam selection for beam reporting based on the third beam value; wherein the second beam value is a beam value obtained by performing layer three filtering on a first beam value of the first beam predicted based on a first AI model; obtaining a fourth beam value based on a first beam value of a first beam, and performing beam selection for generating a first cell value based on the fourth beam value; wherein the first beam value is a beam value predicted based on a first AI model.

[0243] The method performed by the network side device in the above embodiments can be implemented in the baseband device 133, which includes a baseband processor.

[0244] The baseband device 133 may, for example, include at least one baseband board on which a plurality of chips are disposed, as shown in FIG. 13. One of the chips is, for example, a baseband processor, which is connected to the memory 135 through a bus interface to invoke a program in the memory 135 and perform the operations of the network device shown in the above method embodiments.

[0245] The network side device may, for example, further include a network interface 136, which is, for example, a Common Public Radio Interface (CPRI).

[0246] Specifically, the network side device 1300 of the embodiments of the present application further includes instructions or programs stored in the memory 135 and executable on the processor 134, which invokes the instructions or programs in the memory 135 to perform the method performed by the modules shown in FIG. 10 and achieve the same technical effects. To avoid repetition, the details are not described here.

[0247] The embodiments of the present application also provide a readable storage medium having programs or instructions stored thereon, which are executed by a processor to implement each process of the above-mentioned prediction-related processing method embodiments and achieve the same technical effects. To avoid repetition, the details are not described here.

[0248] The processor is the processor in the terminal in the above embodiments. The readable storage medium includes a computer readable storage medium, such as a computer readable only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc. In some examples, the readable storage medium can be a non-transitory readable storage medium.

[0249] The embodiments of the present application further provide a chip including a processor and a communication interface, the communication interface being coupled to the processor, and the processor being configured to execute programs or instructions to implement each process of the above-mentioned prediction-related processing method embodiments and achieve the same technical effects. To avoid repetition, the details are not described here.

[0250] It should be understood that the chip mentioned in the embodiments of the present application can also be referred to as a system-level chip, a system chip, a chip system, or a system-on-chip chip, etc.

[0251] The embodiment of the present application further provides a computer program / program product stored in a storage medium, which is executed by at least one processor to implement each process of the above-mentioned prediction-related processing method embodiment and achieve the same technical effects. To avoid repetition, details are not described herein.

[0252] The embodiment of the present application further provides a prediction-related processing system, which comprises a terminal and a network-side device. The terminal can be used to execute the steps of the above-mentioned prediction-related processing method, and the network-side device can be used to execute the steps of the above-mentioned prediction-related processing method.

[0253] It should be noted that, in this document, the terms "comprising", "including", or any other variant thereof are intended to cover non-exclusive inclusions, so that processes, methods, articles, or devices that include a series of elements not only include those elements, but also include other elements not explicitly listed, or further include elements inherent to such processes, methods, articles, or devices. Without more limitations, the element defined by the statement "including a" does not exclude the presence of another identical element in the process, method, article, or device including the element. In addition, it should be pointed out that the scope of the methods and devices in the embodiments of the present application is not limited to performing functions in the order shown or discussed, but can also include performing functions in a substantially simultaneous manner or in reverse order, for example, the described method can be performed in an order different from that described, and various steps can also be added, omitted or combined. In addition, the features described with reference to certain examples can be combined in other examples.

[0254] From the above description of the embodiments, those skilled in the art can clearly understand that the above-mentioned embodiment method can be realized by means of computer software product and general hardware platform, of course, it can also be realized by hardware. The computer software product is stored in a storage medium (such as ROM, RAM, magnetic disc, optical disc, etc.), which includes a plurality of instructions for making the terminal or network-side device execute the method described in each embodiment of the present application.

[0255] The embodiments of the present application are described above in combination with the drawings, but the present application is not limited to the above-mentioned specific embodiments, which are only illustrative and not restrictive. Those skilled in the art can make many forms of embodiments under the inspiration of the present application without departing from the scope of the present application and the protection scope of the claims.

Claims

1. A processing method for prediction correlation, comprising: obtaining, by a terminal, prediction accuracy information; determining, by the terminal, first information based on the prediction accuracy information; performing, by the terminal, at least one of the following: generating a first cell value based on the first information and a first beam value of a first beam, the first information being a weight factor corresponding to the first beam; or performing layer three filtering on a first beam value of a first beam based on the first information and a layer three filtered beam filtering coefficient, the first information being a second adjustment coefficient corresponding to the first beam; wherein the prediction accuracy information is first prediction accuracy information corresponding to the first beam value, the first beam value being a beam value predicted based on a first artificial intelligence (AI) model, and the second adjustment coefficient is used to adjust the beam filtering coefficient; performing layer three filtering on a second cell value based on the first information and a layer three filtered cell filtering coefficient; wherein the prediction accuracy information is second prediction accuracy information corresponding to the second cell value, and the first information is a first adjustment coefficient used to adjust the cell filtering coefficient; obtaining a third beam value based on the first information and a second beam value of the first beam, and performing beam selection for beam reporting based on the third beam value; wherein the second beam value is a beam value obtained by performing layer three filtering on the first beam value of the first beam predicted based on the first AI model; obtaining a fourth beam value based on the first information and a first beam value of the first beam, and performing beam selection for generating a first cell value based on the fourth beam value; wherein the first beam value is a beam value predicted based on the first AI model.

2. The method of claim 1, wherein, The first prediction accuracy information comprises at least one of the following: prediction accuracy of the first beam value; current prediction accuracy of the first AI model; prediction accuracy associated with the first AI model.

3. The method of claim 1, wherein, The determining, by the terminal, first information based on the prediction accuracy information comprises: determining, by the terminal, first information based on the prediction accuracy information and second information; wherein the second information comprises at least one of the following: a mapping relationship between the prediction accuracy information and the first information, and a first threshold.

4. The method of claim 3, wherein, In a case where prediction accuracy corresponding to the prediction accuracy information is less than or equal to the first threshold: in generating the first cell value, a weight factor corresponding to the first beam value is 0 or the first beam is not selected to participate in a generation process of the first cell value; or, in performing layer three filtering on the second cell value, the first adjustment coefficient is 0 or layer three filtering is not performed based on the second cell value; or, in performing layer three filtering on the first beam value, the second adjustment coefficient is 0 or layer three filtering is not performed based on the first beam value; or, in performing beam selection for beam reporting, the first information is 0 or the first beam is not selected for beam reporting; or, in performing beam selection for generating the first cell value, the first information is 0 or the first beam is not selected to generate the first cell value.

5. The method of claim 3 or 4, wherein, The method further comprises, before the terminal determines the first information based on the prediction accuracy information and second information: The terminal receives the second information from a network side device.

6. The method according to any one of claims 1 to 4, wherein, The generating the first cell value based on the first information and a first beam value of a first beam comprises: The first cell value is generated based on one of the following formulas: M c = (c1*B1 + c2*B2 +... + c m *B m ) / (c1 + c2 +... + c m ); M c = d1*B1 + d2*B2 +... + d m *B m,， , d x = c x / (c1 + c2 +... + c m ); wherein M c is the first cell value, B x is the selected first beam value or the beam measurement value of the second beam, c x is B x is the corresponding weight factor, m is the number of beams participating in the generation of the first cell value, 1≤x≤m, and the second beam is the beam for which the terminal performs an actual measurement to obtain a beam measurement value and is selected to generate the first cell value.

7. The method of claim 6, wherein, The weight factor corresponding to the second beam is 1.

8. The method of claim 1, wherein, The second cell value is predicted based on a second AI model, and the second prediction accuracy information comprises at least one of: The prediction accuracy of the second AI model output; The current prediction accuracy of the second AI model; The prediction accuracy associated with the second AI model.

9. The method of claim 1, wherein, The second cell value is the first cell value; The second prediction accuracy information is the first prediction accuracy information; or the second prediction accuracy information is an average of prediction accuracies corresponding to a plurality of the first prediction accuracy information.

10. The method of claim 1, 3, 8, or 9, wherein, The performing layer three filtering on the second cell value based on the first information and a cell filtering coefficient of layer three filtering comprises: The performing layer three filtering on the second cell value based on the following formula: F n = (1 - a1 * x1) * F n-1 + a1 * x1 * M n ; where F n is the value after layer three filtering; F n-1 is the value from the last pass through the layer three filter; a1 is the cell filtering coefficient; x1 is the first adjustment coefficient; M n is the second cell value.

11. The method of claim 1, wherein, The performing layer three filtering on the first beam value based on the first information and a beam filtering coefficient of layer three filtering comprises: The performing layer three filtering on the first beam value based on the following formula: F n = (1 - a2*x2)*F n-1 + a2*x2*M n ; where F n is the value after layer three filtering; F n-1 is the value from the last pass through the layer three filter; a2 is the beam filtering coefficient; x2 is the second adjustment coefficient; M n is the first beam value.

12. The method of claim 1, wherein, The obtaining a third beam value based on the first information and a second beam value of a first beam comprises: Multiplying the second beam value of the first beam by a value indicated by the first information to obtain the third beam value, wherein the value indicated by the first information is a positive number less than or equal to 1; or Subtracting the value indicated by the first information from the second beam value of the first beam to obtain the third beam value, wherein the value indicated by the first information is a number greater than or equal to 0.

13. The method of claim 1 or 12, wherein, The performing beam selection for beam reporting based on the third beam value comprises: Among at least one first beam and at least one third beam of the first cell, selecting at most X beams for beam reporting based on the third beam value and a beam value corresponding to the third beam, the X beams including a beam with the highest beam value and at most X-1 beams higher than a second threshold, wherein the third beam is a beam for which the terminal performs actual measurement to obtain a beam value, and X is an integer greater than or equal to 1.

14. The method of claim 1, wherein, The obtaining a fourth beam value based on the first information and a first beam value of a first beam comprises: Multiplying the first beam value of the first beam by a value indicated by the first information to obtain the fourth beam value, wherein the value indicated by the first information is a positive number less than or equal to 1; or Subtracting the value indicated by the first information from the first beam value of the first beam to obtain the fourth beam value, wherein the value indicated by the first information is a number greater than or equal to 0.

15. The method of claim 1 or 14, wherein, The performing beam selection for generating the first cell value based on the fourth beam value comprises: In at least one of the first beams and at least one third beam of the first cell, a maximum of N beams higher than a third threshold are selected based on the fourth beam value and a beam value corresponding to the third beam to generate the first cell value, wherein the third beam is a beam for which the terminal performs actual measurement to obtain a beam value, and N is an integer greater than or equal to 1.

16. A processing method related to prediction, comprising: The network side device sends second information to the terminal, and the second information is used by the terminal to determine first information based on prediction accuracy information; wherein the first information is used for at least one of the following: Generate a first cell value based on a first beam value of a first beam, and the first information is a weight factor corresponding to the first beam; or perform layer three filtering on a first beam value of a first beam based on a layer three filtering beam filtering coefficient, and the first information is a second adjustment coefficient corresponding to the first beam; wherein the prediction accuracy information is first prediction accuracy information corresponding to the first beam value, the first beam value is a beam value predicted based on a first AI model, and the second adjustment coefficient is used to adjust the beam filtering coefficient; Perform layer three filtering on a second cell value based on a layer three filtering cell filtering coefficient; wherein the prediction accuracy information is second prediction accuracy information corresponding to the second cell value, and the first information is a first adjustment coefficient used to adjust the cell filtering coefficient; Obtain a third beam value based on a second beam value of a first beam, and perform beam selection for beam reporting based on the third beam value; wherein the second beam value is a beam value obtained by performing layer three filtering on a first beam value of the first beam based on a first AI model; Obtain a fourth beam value based on a first beam value of a first beam, and perform beam selection for generating a first cell value based on the fourth beam value; wherein the first beam value is a beam value predicted based on a first AI model.

17. The method of claim 16, wherein, The second information includes at least one of the following: a mapping relationship between the prediction accuracy information and the first information, and a first threshold.

18. The method of claim 17, wherein, In the case where the prediction accuracy corresponding to the prediction accuracy information is less than or equal to the first threshold: In generating the first cell value, the weight factor corresponding to the first beam value is 0 or the first beam is not selected to participate in the generation process of the first cell value; Or, In performing layer three filtering on the second cell value, the first adjustment coefficient is 0 or layer three filtering is not performed based on the second cell value; Or, In performing layer three filtering on the first beam value, the second adjustment coefficient is 0 or layer three filtering is not performed based on the first beam value; Or, In performing beam selection for beam reporting, the first information is 0 or the first beam is not selected for beam reporting; Or, In performing beam selection for generating a first cell value, the first information is 0 or the first beam is not selected to generate the first cell value.

19. A processing device related to prediction, applied to a terminal, comprising: The processing module is configured to obtain prediction accuracy information; determine first information based on the prediction accuracy information; and perform at least one of the following: generate a first cell value based on the first information and a first beam value of a first beam, the first information being a weight factor corresponding to the first beam; or perform layer three filtering on a first beam value of a first beam based on the first information and a layer three filtered beam filtering coefficient, the first information being a second adjustment coefficient corresponding to the first beam; wherein the prediction accuracy information is first prediction accuracy information corresponding to the first beam value, the first beam value being a beam value predicted based on a first AI model, and the second adjustment coefficient is used to adjust the beam filtering coefficient; perform layer three filtering on a second cell value based on the first information and a layer three filtered cell filtering coefficient; wherein the prediction accuracy information is second prediction accuracy information corresponding to the second cell value, and the first information is a first adjustment coefficient used to adjust the cell filtering coefficient; obtain a third beam value based on the first information and a second beam value of the first beam, and perform beam selection for beam reporting based on the third beam value; wherein the second beam value is a beam value obtained by performing layer three filtering on the first beam value of the first beam predicted based on the first AI model; obtain a fourth beam value based on the first information and a first beam value of the first beam, and perform beam selection for generating a first cell value based on the fourth beam value; wherein the first beam value is a beam value predicted based on the first AI model.

20. The apparatus of claim 19, wherein, The first prediction accuracy information includes at least one of the following: prediction accuracy of the first beam value; current prediction accuracy of the first AI model; prediction accuracy associated with the first AI model.

21. The apparatus of claim 19, wherein, The processing module is configured to determine the first information based on the prediction accuracy information and second information; wherein the second information includes at least one of the following: a mapping relationship between the prediction accuracy information and the first information, and a first threshold.

22. The apparatus of claim 21, wherein, In a case where prediction accuracy corresponding to the prediction accuracy information is less than or equal to the first threshold: when generating the first cell value, a weight factor corresponding to the first beam value is valued as 0 or the first beam is not selected to participate in a generation process of the first cell value; or, when performing layer three filtering on the second cell value, the first adjustment coefficient is valued as 0 or layer three filtering is not performed based on the second cell value; or, when performing layer three filtering on the first beam value, the second adjustment coefficient is valued as 0 or layer three filtering is not performed based on the first beam value; or, when performing beam selection for beam reporting, the first information is valued as 0 or the first beam is not selected for beam reporting; or, when performing beam selection for generating a first cell value, the first information is valued as 0 or the first beam is not selected to generate the first cell value.

23. The apparatus of claim 21 or 22, wherein, The receiving module is further configured to receive the second information from a network side device.

24. The apparatus of any one of claims 19 to 23, wherein, The processing module is configured to generate the first cell value based on one of the following formulas: M c = (c1*B1 + c2*B2 +... + c m *B m ) / (c1 + c2 +... + c m ); or M c = d1*B1 + d2*B2 +... + d m *B m,， , d x = c x / (c1 + c2 +... + c m ). wherein M c is the first cell value, B x is the selected first beam value or a beam measurement value of a second beam, c x is B x a corresponding weight factor, m is the number of beams participating in the generation of the first cell value, 1≤x≤m, and the second beam is a beam for which the terminal performs an actual measurement to obtain a beam measurement value and is selected to generate the first cell value.

25. The apparatus of claim 24, wherein, The weight factor corresponding to the second beam is 1.

26. The apparatus of claim 19, wherein, The second cell value is predicted based on a second AI model, and the second prediction accuracy information includes at least one of the following: The prediction accuracy output by the second AI model; The current prediction accuracy of the second AI model; The prediction accuracy associated with the second AI model.

27. The apparatus of claim 19, wherein, The second cell value is the first cell value; The second prediction accuracy information is the first prediction accuracy information; or the second prediction accuracy information is an average of prediction accuracies corresponding to a plurality of the first prediction accuracy information.

28. The apparatus of claims 19, 21, 26, or 27, wherein, The processing module is configured to perform layer three filtering on the second cell value based on the following formula: F n = (1 - a1 * x1) * F n-1 + a1 * x1 * M n ; where F n is the value after layer three filtering; F n-1 is the value from the last pass through the layer three filter; a1 is the cell filtering coefficient; x1 is the first adjustment coefficient; M n is the second cell value.

29. The apparatus of claim 19, wherein, The processing module is configured to perform layer three filtering on the first beam value based on the following formula: F n = (1 - a2*x2)*F n-1 + a2*x2*M n ; where F n is the value after layer three filtering; F n-1 is the value from the last pass through the layer three filter; a2 is the beam filtering coefficient; x2 is the second adjustment coefficient; M n is the first beam value.

30. The apparatus of claim 19, wherein, The processing module is configured to: multiply the second beam value of the first beam by the value indicated by the first information to obtain a third beam value; wherein the value indicated by the first information is a positive number less than or equal to 1; or subtract the value indicated by the first information from the second beam value of the first beam to obtain a third beam value; wherein the value indicated by the first information is a number greater than or equal to 0.

31. The apparatus of claim 19 or 30, wherein, The processing module is configured to, among at least one first beam and at least one third beam of the first cell, select up to X beams based on the third beam value and the beam value corresponding to the third beam, the X beams including a beam with the highest beam value and up to X-1 beams higher than a second threshold, wherein the third beam is a beam for which the terminal performs actual measurement to obtain a beam value, and X is an integer greater than or equal to 1.

32. The apparatus of claim 19, wherein, The processing module is configured to: multiply the first beam value of the first beam by the value indicated by the first information to obtain a fourth beam value; wherein the value indicated by the first information is a positive number less than or equal to 1; or subtract the value indicated by the first information from the first beam value of the first beam to obtain a fourth beam value; wherein the value indicated by the first information is a number greater than or equal to 0.

33. The apparatus of claim 19 or 32, wherein, The processing module is configured to, among at least one first beam and at least one third beam of the first cell, select up to N beams higher than a third threshold based on the fourth beam value and the beam value corresponding to the third beam to generate the first cell value, wherein the third beam is a beam for which the terminal performs actual measurement to obtain a beam value, and N is an integer greater than or equal to 1.

34. A processing apparatus related to prediction, comprising: a sending module configured to send second information to a terminal, the second information being used by the terminal to determine first information based on prediction accuracy information; wherein the first information is used for at least one of the following: generate a first cell value based on a first beam value of a first beam, the first information being a weight factor corresponding to the first beam; or perform layer 3 filtering on the first beam value of the first beam based on a layer 3 filtering beam filtering coefficient, the first information being a second adjustment coefficient corresponding to the first beam; wherein the prediction accuracy information is first prediction accuracy information corresponding to the first beam value, the first beam value being a beam value predicted based on a first AI model, and the second adjustment coefficient is used to adjust the beam filtering coefficient; perform layer 3 filtering on a second cell value based on a layer 3 filtering cell filtering coefficient; wherein the prediction accuracy information is second prediction accuracy information corresponding to the second cell value, and the first information is a first adjustment coefficient used to adjust the cell filtering coefficient; obtain a third beam value based on a second beam value of a first beam, and perform beam selection for beam reporting based on the third beam value; wherein the second beam value is a beam value obtained by performing layer 3 filtering on a first beam value of the first beam predicted based on a first AI model. obtain a fourth beam value based on a first beam value of a first beam, and perform beam selection for generating a first cell value based on the fourth beam value; wherein the first beam value is a beam value predicted based on a first AI model.

35. The apparatus of claim 34, wherein, The second information includes at least one of the following: a mapping relationship between the prediction accuracy information and the first information, and a first threshold.

36. The apparatus of claim 35, wherein, In a case where the prediction accuracy corresponding to the prediction accuracy information is less than or equal to the first threshold, the first beam value corresponds to a weight factor with a value of 0, or the first beam is not selected to participate in the generation process of the first cell value. Or, In a case where the prediction accuracy corresponding to the prediction accuracy information is less than or equal to the first threshold, the first adjustment coefficient has a value of 0, or layer 3 filtering is not performed based on the second cell value. Or, In a case where the prediction accuracy corresponding to the prediction accuracy information is less than or equal to the first threshold, the second adjustment coefficient has a value of 0, or layer 3 filtering is not performed based on the first beam value. Or, In a case where the prediction accuracy corresponding to the prediction accuracy information is less than or equal to the first threshold, the first information has a value of 0, or the first beam is not selected for beam reporting. Or, In a case where the prediction accuracy corresponding to the prediction accuracy information is less than or equal to the first threshold, the first information has a value of 0, or the first beam is not selected to generate the first cell value.

37. A terminal comprising a processor and a memory, the memory storing programs or instructions executable on the processor, the programs or instructions being executed by the processor to implement the steps of the method of any one of claims 1 to 15.

38. A network side device comprising a processor and a memory, the memory storing programs or instructions executable on the processor, the programs or instructions being executed by the processor to implement the steps of the method of any one of claims 16 to 18. ​ 39. A readable storage medium, on which a program or instructions are stored, the program or instructions, when executed by a processor, implement the method of any one of claims 1-18.

Images