Data filtering processing method and apparatus, terminal, and network side device

Abstract

The present application relates to the technical field of communications, and discloses a data filtering processing method and apparatus, a terminal, and a network side device. The data filtering processing method in embodiments of the present application comprises: a terminal performs measurement to obtain first data of a target object; the terminal determines whether second data of the target object is generated on the basis of an artificial intelligence (AI) model or on the basis of a layer 3 filtering mechanism; and the terminal performs a target operation, the target operation comprising at least one of the following: when determining that the second data is generated on the basis of the AI model, using a first weight coefficient to perform layer 3 filtering on the first data and the second data; and when determining that the second data is generated on the basis of the layer 3 filtering mechanism, using a second weight coefficient to perform layer 3 filtering on the first data and the second data, wherein the target object is a beam or a cell, the first data is an actual measurement value before layer 3 filtering or an actual measurement value after layer 1 filtering, and the second data is a most recently obtained signal value after layer 3 filtering.

Description

Data filtering processing methods, devices, terminals and network-side equipment

[0001] Cross-reference to related applications

[0002] This application claims priority to Chinese Patent Application No. 202411590149.X, filed in China on November 8, 2024, the entire contents of which are incorporated herein by reference. Technical Field

[0003] This application belongs to the field of communication technology, and specifically relates to a data filtering processing method, apparatus, terminal and network-side equipment. Background Technology

[0004] With the development of communication technology, artificial intelligence (AI) models are introduced into communication systems to generate predicted values ​​after Layer 3 filtering in order to reduce measurement. However, due to the inherent errors in AI model predictions, subsequent Layer 3 filtering based on these predicted values ​​can lead to misproperties, resulting in poor Layer 3 filtering performance. Therefore, related technologies suffer from the problem of poor Layer 3 filtering effectiveness. Summary of the Invention

[0005] This application provides a data filtering processing method, apparatus, terminal, and network-side device that can solve the problem of poor filtering effect at layer 3.

[0006] Firstly, a data filtering processing method is provided, including:

[0007] The terminal performs the measurement to obtain the first data of the target object;

[0008] The terminal determines whether the second data of the target object is generated based on an artificial intelligence (AI) model or based on a layer 3 filtering mechanism;

[0009] The terminal performs a target operation, which includes at least one of the following:

[0010] If it is determined that the second data is generated based on an AI model, the first data and the second data are filtered using a first weighting coefficient in layer 3.

[0011] If it is determined that the second data is generated based on a layer 3 filtering mechanism, layer 3 filtering is performed on the first data and the second data using a second weighting coefficient.

[0012] The target object is a beam or a cell; the first data is the actual measurement value before layer 3 filtering or the actual measurement value after layer 1 filtering; the second data is the signal value after the most recently obtained layer 3 filtering.

[0013] Secondly, a data filtering processing method is provided, including:

[0014] The network-side device sends the first and second information to the terminal;

[0015] Wherein, the first information is used to determine the first weight coefficient, and the second information is used to determine the second weight coefficient. The first weight coefficient is used by the terminal to perform layer 3 filtering on the first data and the second data of the target object when the terminal determines that the second data of the target object is generated based on an AI model. The second weight coefficient is used by the terminal to perform layer 3 filtering on the first data and the second data of the target object when the terminal determines that the second data of the target object is generated based on a layer 3 filtering mechanism.

[0016] The target object is a beam or a cell; the first data is the actual measurement value before layer 3 filtering or the actual measurement value after layer 1 filtering obtained by the terminal during measurement; the second data is the signal value after the most recent layer 3 filtering.

[0017] Thirdly, a data filtering and processing apparatus is provided, comprising:

[0018] The measurement module is used to perform measurements and obtain initial data about the target object.

[0019] The determination module is used to determine whether the second data of the target object is generated based on an artificial intelligence (AI) model or based on a layer 3 filtering mechanism.

[0020] An execution module is configured to perform a target operation, wherein the target operation includes at least one of the following:

[0021] If it is determined that the second data is generated based on an AI model, the first data and the second data are filtered using a first weighting coefficient in layer 3.

[0022] If it is determined that the second data is generated based on a layer 3 filtering mechanism, layer 3 filtering is performed on the first data and the second data using a second weighting coefficient.

[0023] The target object is a beam or a cell; the first data is the actual measurement value before layer 3 filtering or the actual measurement value after layer 1 filtering; the second data is the signal value after the most recently obtained layer 3 filtering.

[0024] Fourthly, a data filtering processing apparatus is provided, comprising:

[0025] The sending module is used to send first information and second information to the terminal;

[0026] Wherein, the first information is used to determine the first weight coefficient, and the second information is used to determine the second weight coefficient. The first weight coefficient is used by the terminal to perform layer 3 filtering on the first data and the second data of the target object when the terminal determines that the second data of the target object is generated based on an AI model. The second weight coefficient is used by the terminal to perform layer 3 filtering on the first data and the second data of the target object when the terminal determines that the second data of the target object is generated based on a layer 3 filtering mechanism.

[0027] The target object is a beam or a cell; the first data is the actual measurement value before layer 3 filtering or the actual measurement value after layer 1 filtering obtained by the terminal during measurement; the second data is the signal value after the most recent layer 3 filtering.

[0028] Fifthly, a data filtering processing apparatus is provided, the apparatus being configured to perform the steps of the method described in the first aspect, or to implement the steps of the method described in the second aspect.

[0029] In a sixth aspect, a terminal is provided, the terminal including 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 as described in the first aspect.

[0030] In a seventh aspect, a terminal is provided, including a processor and a communication interface, wherein the processor is configured to perform measurement to obtain first data of a target object; determine whether second data of the target object is generated based on an artificial intelligence (AI) model or based on a layer 3 filtering mechanism; and perform a target operation, the target operation including at least one of the following:

[0031] If it is determined that the second data is generated based on an AI model, the first data and the second data are filtered using a first weighting coefficient in layer 3.

[0032] If it is determined that the second data is generated based on a layer 3 filtering mechanism, layer 3 filtering is performed on the first data and the second data using a second weighting coefficient.

[0033] The target object is a beam or a cell; the first data is the actual measurement value before layer 3 filtering or the actual measurement value after layer 1 filtering; the second data is the signal value after the most recently obtained layer 3 filtering.

[0034] Eighthly, a network-side device is provided, the network-side device including 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 as described in the first aspect.

[0035] In a ninth aspect, a network-side device is provided, including a processor and a communication interface, wherein the communication interface is used to send first information and second information to a terminal;

[0036] Wherein, the first information is used to determine the first weight coefficient, and the second information is used to determine the second weight coefficient. The first weight coefficient is used by the terminal to perform layer 3 filtering on the first data and the second data of the target object when the terminal determines that the second data of the target object is generated based on an AI model. The second weight coefficient is used by the terminal to perform layer 3 filtering on the first data and the second data of the target object when the terminal determines that the second data of the target object is generated based on a layer 3 filtering mechanism.

[0037] The target object is a beam or a cell; the first data is the actual measurement value before layer 3 filtering or the actual measurement value after layer 1 filtering obtained by the terminal during measurement; the second data is the signal value after the most recent layer 3 filtering.

[0038] In a tenth aspect, a readable storage medium is provided, on which a program or instructions are stored, which, when executed by a processor, implement the steps of the method described in the first aspect, or implement the steps of the method described in the second aspect.

[0039] Eleventhly, a wireless communication system is provided, comprising: a terminal and a network-side device, wherein the terminal can be used to perform the steps of the method as described in the first aspect, and the network-side device can be used to perform the steps of the method as described in the second aspect.

[0040] In a twelfth aspect, a chip is provided, the chip including a processor and a communication interface coupled to the processor, the processor being configured to run programs or instructions to implement the method as described in the first aspect, or to implement the method as described in the second aspect.

[0041] In a thirteenth aspect, a computer program / program product is provided, which is stored in a storage medium and is executed by at least one processor to implement the steps of the method as described in the first aspect, or to implement the steps of the method as described in the second aspect.

[0042] In this embodiment, a terminal performs measurement to obtain first data of a target object; the terminal determines whether second data of the target object is generated based on an artificial intelligence (AI) model or a layer 3 filtering mechanism; the terminal performs a target operation, which includes at least one of the following: if the second data is determined to be generated based on an AI model, performing layer 3 filtering on the first data and the second data using a first weighting coefficient; if the second data is determined to be generated based on a layer 3 filtering mechanism, performing layer 3 filtering on the first data and the second data using a second weighting coefficient; wherein the target object is a beam or a cell, the first data is the actual measurement value before layer 3 filtering or the actual measurement value after layer 1 filtering, and the second data is the most recently obtained signal value after layer 3 filtering. In this way, different weighting coefficients can be set based on different second data to achieve layer 3 filtering, thereby reducing the impact of prediction errors generated by the AI ​​model on subsequent layer 3 filtering. Therefore, this embodiment improves the layer 3 filtering effect. Attached Figure Description

[0043] Figure 1 is a block diagram of a wireless communication system applicable to an embodiment of this application;

[0044] Figure 2 is a schematic diagram of the structure of the measurement model applicable to the embodiments of this application;

[0045] Figure 3 is a schematic diagram of the filtering scenarios that can be applied to the embodiments of this application;

[0046] Figures 4A to 4C are examples of time-domain prediction in embodiments of this application;

[0047] Figure 5 is a flowchart illustrating one of the data filtering processing methods provided in this application embodiment;

[0048] Figure 6A is a second schematic flowchart of a data filtering processing method provided in an embodiment of this application;

[0049] Figure 6B is a third schematic flowchart of a data filtering processing method provided in an embodiment of this application;

[0050] Figure 7 is a flowchart illustrating the determination of the first weight coefficient and the second weight coefficient in a data filtering processing method provided in an embodiment of this application;

[0051] Figure 8 is a fourth flowchart illustrating a data filtering processing method provided in an embodiment of this application;

[0052] Figure 9 is a schematic diagram of the structure of a data filtering processing device provided in an embodiment of this application;

[0053] Figure 10 is a schematic diagram of another data filtering processing device provided in an embodiment of this application;

[0054] Figure 11 is a schematic diagram of the structure of a communication device provided in an embodiment of this application;

[0055] Figure 12 is a schematic diagram of the structure of a terminal provided in an embodiment of this application;

[0056] Figure 13 is a schematic diagram of the structure of a network-side device provided in an embodiment of this application. Detailed Implementation

[0057] The terms "first," "second," etc., used in this application are used to distinguish similar objects and not to describe a specific order or sequence. It should be understood that such terms can be used interchangeably where appropriate so that embodiments of this application can be implemented in orders other than those illustrated or described herein, and the objects distinguished by "first" and "second" are generally of the same class, not limited in number; for example, the first object can be one or more. Furthermore, "or" in this application indicates at least one of the connected objects. For example, the scope of protection for "A or B" covers at least three scenarios: Scenario 1: including A but not B; Scenario 2: including B but not A; Scenario 3: including both A and B. In addition, the terms "A and / or B," "at least one of A and B," and "at least one of A or B" also cover at least the above three scenarios. The character " / " generally indicates that the preceding and following objects are in an "or" relationship.

[0058] The term "instruction" in this application can be either a direct instruction (or explicit instruction) or an indirect instruction (or implicit instruction). A direct instruction can be understood as one in which the sender explicitly informs the receiver of specific information, the operation to be performed, or the requested result, etc., in the instruction sent. An indirect instruction can be understood as one in which the receiver determines the corresponding information based on the instruction sent by the sender, or makes a judgment and determines the operation to be performed or the requested result, etc., based on the judgment result.

[0059] It is worth noting that the technologies described in this application are 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 this application are often used interchangeably, and the described technologies can be used with the systems and radio technologies mentioned above, as well as with other systems and radio technologies. The following description describes New Radio (NR) systems for illustrative purposes, and the term NR is used in most of the following description; however, these technologies can also be applied to systems other than NR systems, such as 6th generation (6G) radio systems. th Generation 6G communication system.

[0060] Figure 1 shows a block diagram of a wireless communication system applicable to an embodiment of this application. The wireless communication system includes a terminal 11 and a network-side device 12. The terminal 11 can be a mobile phone, tablet computer, laptop computer, notebook computer, personal digital assistant (PDA), handheld computer, netbook, ultra-mobile personal computer (UMPC), mobile internet device (MID), augmented reality (AR), virtual reality (VR) device, robot, wearable device, flight vehicle, vehicle user equipment (VUE), shipboard equipment, pedestrian user equipment (PUE), smart home (home devices with wireless communication capabilities, such as refrigerators, televisions, washing machines, or furniture), game console, personal computer (PC), ATM, or self-service machine, etc. Wearable devices include: smartwatches, smart bracelets, smart headphones, smart glasses, smart jewelry (smart bracelets, smart chains, smart rings, smart necklaces, smart anklets, smart anklets, etc.), smart wristbands, smart clothing, etc. Among these, in-vehicle devices can also be referred to as in-vehicle terminals, in-vehicle controllers, in-vehicle modules, in-vehicle components, in-vehicle chips, or in-vehicle units, etc. It should be noted that the specific type of terminal 11 is not limited in this application embodiment. Network-side equipment 12 may include access network equipment or core network equipment, wherein access network equipment may also be referred to as Radio Access Network (RAN) equipment, radio access network function, or radio access network unit. Access network equipment may include base stations, Wireless Local Area Network (WLAN) access points (APs), or Wireless Fidelity (WiFi) nodes, etc.The term "base station" can be referred to as Node B (NB), Evolved Node B (eNB), Next Generation Node B (gNB), New Radio Node B (NR Node B), Access Point, Relay Base Station (RBS), Serving Base Station (SBS), Base Transceiver Station (BTS), Radio Base Station, Radio Transceiver, Basic Service Set (BSS), Extended Service Set (ESS), Home Node B (HNB), Home Evolved Node B, Transmit / Receive Point (TRP), or any other suitable term in the relevant field, as long as the same technical effect is achieved. The term "base station" is not limited to any specific technical terminology. It should be noted that this application embodiment only uses a base station in an NR system as an example for description and does not limit the specific type of base station.

[0061] For ease of understanding, the following describes some aspects of the embodiments of this application:

[0062] I. Derivation of cell measurement values ​​based on measurement.

[0063] Beamforming is a wireless communication technique used to focus wireless signals in a specific direction to improve signal coverage and quality. In 5G NR systems, beamforming is an important technique that helps cells improve signal coverage and quality.

[0064] 5G systems employ beamforming technology. Within a single cell, there can be multiple Synchronization Signal Blocks (SSBs), each of which is a beam, potentially pointing in different directions. Besides SSBs, other beam types exist, such as Channel State Information-Reference Signals (CSI-RS). Beam measurements are required to obtain the signal quality of the beam or cell (in this embodiment, signal quality includes, but is not limited to, Reference Signal Received Power (RSRP), Reference Signal Received Quality (RSRQ), and Signal to Interference plus Noise Ratio (SINR)). In 5G systems, a measurement-based model is shown in Figure 2, where:

[0065] A: Measurements inside the physical layer (specific beam sample).

[0066] Layer 1 (L1) filtering: Performs internal first-layer filtering on the input of the measurement at point A. The precision of the filtering depends on the specific implementation. The actual way the measurement is performed at the physical layer (input A and L1 filtering) is not limited by standards.

[0067] A 1 After L1 filtering, L1 reports the measured value to L3 (i.e., the beam-level measured value).

[0068] Beam combining / selection: Combines beam-level measurements to generate cell quality. The behavior of beam combining / selection is standardized, and the configuration of this module is provided by Radio Resource Control (RRC) signaling. The generation period at point B is equal to that at point A. 1 One measurement cycle at the location.

[0069] B: Measurements derived from the beam-level measurements reported to L3 after beam combining / selection (i.e., cell quality).

[0070] L3 filtering for cell quality: Filters the measurements provided at point B. The behavior of L3 filtering is standardized, and its configuration is provided by RRC signaling. The filtering reporting cycle at point C is equal to one measurement cycle at point B.

[0071] C: Measurement after L3 filtering. The reporting rate is the same as at point B. This measurement is used as input for evaluating the reporting standard for one or more reports.

[0072] Reporting Standards Evaluation: Check if an actual measurement report is required at point D. The evaluation can be based on multiple measurement streams from reference point C, such as comparing different measurements. Here, this is done by inputting C and C... 1 Note: The terminal should at least at point C, C... 1 When reporting new measurement results, the reporting criteria are evaluated. The reporting criteria are standardized, and the configuration is provided by RRC signaling (terminal measurement).

[0073] D: Send measurement report information (messages) via wireless interface.

[0074] L3 beam filtering: for A 1 The measurements provided at point E (i.e., beam-specific measurements) are filtered. Beam filtering behavior is standardized, and its configuration is provided by RRC signaling. The filtering reporting period at point E is equal to that at point A. 1 One measurement cycle at the location.

[0075] E: Measurements after beam filtering (i.e., beam-specific measurements). Reporting rate and A 1 The reporting rate is the same for all points. This measurement is used as input to select the X measurements to be reported.

[0076] Beam selection for beam reporting: Select X measurements from the measurements provided at point E. The beam selection behavior is standardized, and the configuration of this module is provided by RRC signaling.

[0077] F: Beam measurement information contained in the measurement report (transmitted) on the wireless interface.

[0078] Specifically, after receiving the measurement configuration sent by the base station, the terminal performs measurements on the relevant frequency points of the cell. First, the terminal's physical layer performs measurements to obtain samples of the measurement signal quality of K beams of the cell. The measurement signal quality includes one of the following:

[0079] RSRP: Represents the reference signal received power, which is an indicator of signal strength;

[0080] RSRQ: Represents the quality of the received reference signal, and is an indicator for measuring signal quality;

[0081] SINR: Represents the ratio of signal to interference plus noise, and is an indicator for measuring signal interference.

[0082] The physical layer of the terminal performs L1 filtering on each beam. Specifically, it filters the samples from different time points (different sampling periods) of each beam. For example, it averages the values ​​of 5 consecutive samples to obtain the beam measurement value. Then, the physical layer of the UE reports the filtered beam measurement value of each beam to the L3 layer of the terminal.

[0083] The terminal's L3 algorithm selects and merges multiple beam measurements from the cell based on parameters configured by the base station to generate the cell measurement value. Specifically, if relevant parameters (nrofSS-BlocksToAverage and absThreshSS-BlocksConsolidation) are configured, the measurement values ​​of up to N beams (nrofSS-BlocksToAverage) above the threshold (absThreshSS-BlocksConsolidation) are linearly averaged to generate the cell measurement value. If the best beam is less than the threshold, the measurement value of that best beam is used as the cell measurement value. If neither of the above parameters is configured, the measurement value of the best beam is used as the cell measurement value.

[0084] Because signals fluctuate, to avoid inaccuracies in cell measurements caused by signal fluctuations, L3 filtering (smoothing) can be applied to cell measurements. Specifically, based on a weighted averaging method, the most recently received measurement is averaged with the previous smoothed value (the L3-filtered value) to obtain an updated L3-filtered measurement. The L3-filtered measurement is used for evaluating measurement events and for reporting measurements in measurement reports. The base station can control the degree of smoothing by adjusting the weighting coefficients. The formula is as follows: F n = (1–a)*F n-1 +a*M n ;

[0085] Among them, M n It is the most recently received measurement value by L3, i.e., the measurement value before L3 filtering; F n This is an updated measurement value after L3 filtering, used for evaluating measurement report reporting criteria or for measurement reporting; F n-1 It is the old (last) measurement after L3 filtering.

[0086] a = 1 / 2 (k / 4) It is the weighting coefficient, where k is the filtering coefficient configured by the base station (e.g., filterCoefficient cell).

[0087] If the base station is configured to report beam indexes or beam measurement values ​​in the measurement report, the terminal needs to perform the part within the black box at the bottom of the diagram above. That is, the beam measurement values ​​also need to be subjected to the same L3 filtering as described above. Then, the terminal needs to report the beam indexes or corresponding L3-filtered beam measurement values ​​of up to X (maxNrofRS-IndexesToReport) beams above the threshold (absThreshSS-BlocksConsolidation) of the triggered cell in the measurement report.

[0088] From the perspective of a cell or beam, the mechanisms of sampling, L1 filtering, and L3 filtering are shown in Figure 3, where:

[0089] For L3 filtering of beams, the terminal first performs L1 sampling measurement to obtain L1 samples at multiple time points for each beam of a cell. The UE performs L1 filtering on the L1 samples at multiple time points for each beam to obtain the L1 filtered RSRP (taking RSRP as an example) for each beam and submits it to L3. L3 performs beam L3 filtering on each beam to obtain the L3 filtered RSRP for each beam.

[0090] For L3 filtering at the cell level, the terminal first performs L1 sampling measurements to acquire multiple time-point L1 samples for each beam of the cell. The terminal then performs L1 filtering on these samples to obtain the L1 filtered RSRP (for example, RSRP for each beam) and submits it to L3. L3 performs beam selection and beam combining on these beams to generate the cell's L1-filtered RSRP (since this generation is performed at L3, the cell's L1-filtered RSRP can also be called the cell's pre-L3 filtered RSRP). L3 then performs L3 filtering on this L1-filtered RSRP to obtain the cell's L3-filtered RSRP.

[0091] II. Artificial Intelligence.

[0092] AI has been widely applied in various fields. Integrating artificial intelligence into wireless communication networks to significantly improve technical indicators such as throughput, latency, and user capacity is an important task for future wireless communication networks.

[0093] The AI ​​model in this application may also be referred to as an AI unit, AI model, machine learning (ML) model, ML unit, AI structure, AI function, AI characteristic, machine learning model, neural network, neural network function, neural network functionality, etc. Alternatively, the AI ​​model may refer to a processing unit capable of implementing specific algorithms, formulas, processing flows, capabilities, etc., related to AI. Or, the AI ​​model may be a processing method, algorithm, function, module, or unit for a specific dataset. Alternatively, the AI ​​model may be a processing method, algorithm, function, module, or unit running on AI or ML-related hardware such as a Graphics Processing Unit (GPU), Neural Processing Unit (NPU), Tensor Processing Unit (TPU), or Application-Specific Integrated Circuit (ASIC). This application does not impose specific limitations in this regard. Optionally, the specific dataset includes at least one of the input and output of the AI ​​model.

[0094] III. AI for Mobility.

[0095] A key use case for AI for Mobility is measurement prediction in Radio Resource Management (RRM). This has two goals: Goal 1 is to reduce measurements by predicting the signal quality of some cells or beams in the spatial, frequency, or time domains to replace actual measurements, thus saving terminal power. Goal 2 is to improve mobility performance, primarily achieved through time-domain prediction, i.e., predicting the signal quality of cells or beams at future times, enabling more timely and accurate handover decisions. For Goal 2, the terminal typically still performs actual measurements when the predicted time arrives.

[0096] RRM measurement prediction includes cell-level measurement prediction and beam-level measurement prediction. For example, after various input parameters are fed into the AI ​​model, it can output cell-level or beam-level predicted values.

[0097] The AI ​​model can be viewed as a black box. Its internal implementation is not visible. What can be seen is that each time the AI ​​model performs inference, it needs to input some parameters and output some results.

[0098] For cell-level measurement prediction, the current standard is studying the following three sub-use cases:

[0099] Sub use case 1: Predict L1 beam-level measurement results based on actual L1 beam-level measurement results, and then generate L3 cell-level measurement results;

[0100] Sub use case 2: L3 cell-level measurement results are predicted based on actual L3 cell-level measurement results;

[0101] Sub use case 3: L3 cell-level measurement results are predicted based on actual L1 beam-level measurement results.

[0102] For beam-level measurement prediction, the current standard is studying the following three types:

[0103] Sub use case 4: Predict the L1 filtered beam level measurement results based on the actual L1 beam level measurement results, and then generate the L3 beam level measurement values;

[0104] Sub use case 5: L3 beam level measurement results are predicted based on actual L3 beam level measurement results;

[0105] Sub use case 6: L3 beam level measurement results are predicted based on actual L1 beam level measurement values.

[0106] For time-domain prediction, there are two cases:

[0107] Scenario A: The time instance corresponding to the predicted value will be measured in the future, as shown in Figure 4A;

[0108] Scenario B: The time instance corresponding to the predicted value is no longer actually measured subsequently, thus reducing the amount of measurement and saving power for the terminal. See Figures 4B and 4C.

[0109] In Figures 4A to 4C, t1 represents the sampling period or measurement period; t2 represents the observation window; and t3 represents the prediction window. Each small window represents an actual measurement or an inference value for a beam or cell in a time instance. Solid-line windows represent actual measurements within the observation window range of that model inference (serving as the input for that model inference); dashed-line windows represent inference values ​​within the prediction window range of that model inference (serving as the output for that model inference); and dashed-line gray-filled windows represent predicted values ​​from previous model inference outputs within the observation window range of that model inference (serving as or not serving as the input for that model inference). The interval between two adjacent windows is one sampling period or one measurement period, corresponding to one time instance.

[0110] For sub-use case 2 above, the predicted cell value output by the AI ​​model is an L3-filtered cell value. If prediction is performed using method A, the relevant L3 filtering mechanism can be followed. That is, the predicted cell value output by the AI ​​model can be considered as additional information and does not need to participate in the L3 filtering mechanism. In other words, the most recently received (L1-filtered or L3-filtered) actual measurement value and the previous L3-filtered value are simply L3-filtered. However, if prediction is performed using method B, no actual measurement is performed in the time instance within the prediction window, and the predicted value output by the AI ​​model is directly L3-filtered. Since this L3-filtered predicted value may be inaccurate, how to perform L3 filtering on subsequent actual measurement values ​​is a problem. Taking Figure 4C as an example, when the L1-filtered (or L3-filtered) actual cell measurement value is obtained at T6, how to perform L3 filtering to obtain the updated L3-filtered cell value at time T6? Three solutions have been proposed in related technologies:

[0111] Option 1: Perform L3 filtering on the received cell measurement value (i.e., the actual L1-filtered cell measurement value at point T6) and the previous L3-filtered cell value (i.e., the predicted value at point T5) to obtain the updated L3-filtered cell value.

[0112] Option 2: Instead of considering the previous L3 filtered cell prediction value (because it is a prediction value), directly use the cell measurement value received by L3 (i.e. the actual measurement value of the L1-filtered cell at point T6) as the updated L3 filtered cell value.

[0113] Option 3: Perform L3 filtering on the received cell measurement value (i.e., the actual L1-filtered cell measurement value at point T6) and the L3-filtered cell value obtained from the previous actual measurement value (i.e., the L3-filtered cell value obtained by L3 filtering at point T4) to obtain the updated L3-filtered cell value.

[0114] For Scheme 1, if the prediction accuracy is poor in a certain instance, the resulting L3 filtered cell prediction value will have a large deviation. The larger the deviation, the larger the error will be propagated to subsequent L3 filtered cell values, thus affecting mobility performance.

[0115] For Scheme 2, although it avoids the problem of error propagation caused by inaccurate predictions, it does not actually perform L3 filtering, and therefore does not achieve the intended signal smoothing effect.

[0116] For Scheme 3, the frequency of L3 filtering operations is reduced, and signal changes are reflected more slowly compared to methods that do not use AI.

[0117] Therefore, the data filtering processing method of this application is proposed. The data filtering processing method provided by the embodiments of this application will be described in detail below with reference to the accompanying drawings and through some embodiments and application scenarios.

[0118] Referring to Figure 5, this application embodiment provides a data filtering processing method, as shown in Figure 5, the data filtering processing method includes:

[0119] Step 501: The terminal performs measurement to obtain the first data of the target object;

[0120] Step 502, the terminal determines whether the second data of the target object is generated based on an artificial intelligence (AI) model or based on a layer 3 filtering mechanism;

[0121] Step 503, the terminal performs a target operation, the target operation including at least one of the following:

[0122] If it is determined that the second data is generated based on an AI model, the first data and the second data are filtered using a first weighting coefficient in layer 3.

[0123] If it is determined that the second data is generated based on a layer 3 filtering mechanism, layer 3 filtering is performed on the first data and the second data using a second weighting coefficient.

[0124] The target object is a beam or a cell; the first data is the actual measurement value before layer 3 filtering or the actual measurement value after layer 1 filtering; the second data is the signal value after the most recently obtained layer 3 filtering.

[0125] It should be noted that the above statement "the first data is the actual measurement value before layer 3 filtering or the actual measurement value after layer 1 filtering" can be understood as follows: if the target object is a beam, the first data is the actual measurement value after layer 1 filtering and before layer 3 filtering, i.e., A in Figure 2. 1 The beam measurement value of the point; if the target object is a cell, the first data is the actual measurement value before layer three filtering, that is, the cell measurement value of point B in Figure 2.

[0126] It should be noted that the phrase "when the second data is generated based on the layer 3 filtering mechanism" can also be replaced with "when the second data is an actual measured value" or "when the second data is not generated based on an AI model".

[0127] It should be noted that the phrase "when the second data is generated based on an AI model" can also be replaced with "when the second data is not generated based on a layer 3 filtering mechanism".

[0128] In this embodiment, the signal value after L3 filtering may include the measured value obtained by performing the L3 filtering operation and the predicted value directly generated by the AI ​​model. The predicted value can be directly regarded as a signal value after L3 filtering. For example, taking Figure 4B as an example, T0, T1, T4 and T5 can be understood as the measured values ​​generated based on the L3 filtering mechanism, and T2, T3, T6 and T7 can be understood as the predicted values ​​generated by the AI ​​model.

[0129] For example, let's take Figure 4B as an example. After acquiring the first data at T1, the second data is determined to be the layer 3 filtered signal value corresponding to time T0. That is, the second data is generated based on the layer 3 filtering mechanism. At this time, the second weighting coefficient can be used to perform layer 3 filtering on the first and second data to obtain the layer 3 filtered signal value corresponding to T1. After acquiring the first data at T4, the second data is determined to be the layer 3 filtered signal value corresponding to time T3. That is, the second data is generated based on the AI ​​model. At this time, the first weighting coefficient can be used to perform layer 3 filtering on the first and second data to obtain the layer 3 filtered signal value corresponding to T4.

[0130] Optionally, the first weighting coefficient may be different from the second weighting coefficient. For example, in some embodiments, the first weighting coefficient is greater than the second weighting coefficient. Due to the introduction of the AI ​​model, the signal value after the previous layer 3 filtering may be a predicted value output by the AI ​​model or a measured value (e.g., a measured value generated by the L3 cell filtering mechanism). Considering that the predicted value of the previous L3 filtered signal generated by the AI ​​model may have a large deviation (the larger the deviation, the larger the error will be transmitted to the subsequent L3 filtered signal value, thus affecting mobility performance), in order to solve this problem, in this embodiment, for the above two cases, unlike the prior art which uses the same weighting coefficient, different weighting coefficients can be used. This enables the terminal to use a first weighting coefficient greater than the second weighting coefficient, thereby reducing the impact of the prediction error generated by the AI ​​model on subsequent layer 3 filtering. In this embodiment, when the previous L3 filtered signal value is a predicted value (generated based on an AI model), the method of this embodiment enables the terminal to use a larger weighting coefficient so that the previous L3 filtered signal value has a lower weight in L3 cell filtering (or, in other words, makes the actual measured value of L1-filtered account for a higher proportion), thereby reducing the impact of inaccurate prediction values.

[0131] It should be understood that when the target object is a cell, after the terminal performs the measurement, the terminal's Layer 3 (from the terminal's physical layer) obtains the L1-filtered (or, before Layer 3 filtering) actual measurement value of the first cell. In other words, the terminal's Layer 3 (from the terminal's physical layer) receives the L1-filtered actual measurement values ​​of each beam under the first cell. Layer 3 then performs beam selection and merging to generate the L1-filtered actual measurement value of the first cell.

[0132] When the target object is a beam, after the terminal performs the measurement, the terminal's layer 3 (from the terminal's physical layer) receives the L1-filtered actual measurement values ​​of each beam under the first cell.

[0133] It should be understood that when the target object is a cell, the above-mentioned layer 3 filtering can be layer 3 cell filtering; when the target object is a beam, the above-mentioned layer 3 filtering can be layer 3 beam filtering.

[0134] It should be noted that, in the embodiments of this application, the aforementioned signal value can be understood or replaced as cell value or beam value. Specifically, when the target object is a cell, the signal value can be understood as the cell value; when the target object is a beam, the signal value can be understood as the beam value. The cell value can also be referred to as cell quality, which refers to the measured value of the cell (i.e., the cell measured value generated based on the Layer 3 filtering mechanism) or the predicted value of the cell (i.e., the cell predicted value generated based on the AI ​​model). The beam value can also be referred to as beam quality, which refers to the measured value of the beam (i.e., the beam measured value generated based on the Layer 3 filtering mechanism) or the predicted value of the beam (i.e., the beam predicted value generated based on the AI ​​model). The measured value can also be called the measurement quality, the measured result, etc.; the predicted value can also be called the prediction quality, the prediction result, etc. The measured value, predicted value, cell value, or beam value can be the reference signal received strength (RSRP), the reference signal received quality (RSRQ), or the signal-to-interference-plus-noise ratio (SINR), and there is no limitation here.

[0135] In this embodiment, a terminal performs measurement to obtain first data of a target object. The terminal determines whether the second data of the target object is generated based on an artificial intelligence (AI) model or a layer 3 filtering mechanism. The terminal performs a target operation, which includes at least one of the following: if the second data is determined to be generated based on an AI model, layer 3 filtering is performed on the first data and the second data using a first weighting coefficient; if the second data is determined to be generated based on a layer 3 filtering mechanism, layer 3 filtering is performed on the first data and the second data using a second weighting coefficient. The target object is a beam or cell; the first data is the actual measurement value before layer 3 filtering or the actual measurement value after layer 1 filtering; the second data is the most recently obtained signal value after layer 3 filtering. By using their respective weighting coefficients in these two cases, different weighting coefficients can be set based on the different second data to achieve layer 3 filtering, thereby reducing the impact of prediction errors generated by the AI ​​model on subsequent layer 3 filtering. Therefore, this embodiment improves the layer 3 filtering effect.

[0136] Optionally, in some embodiments, the target measurement value F is obtained by performing Layer 3 filtering on the first data and the second data using a first weighting coefficient. n Satisfy: F n = (1–a1)*F n-1 +a1*M n ;

[0137] Where a1 is the first weighting coefficient, F n-1 The second data refers to the predicted values ​​after layer 3 filtering generated by the AI ​​model, M. n This refers to the first data.

[0138] Optionally, in some embodiments, the target measurement value F is obtained by performing Layer 3 filtering on the first data and the second data using a second weighting coefficient. n Satisfy: F n = (1–a2)*F n-1 +a2*M n ;

[0139] Where a2 is the second weighting coefficient, F n-1 The second data is the measurement value generated based on the layer 3 filtering mechanism, M. n This refers to the first data.

[0140] Taking Figure 4B as an example, the terminal obtains the L1-filtered actual measurement value (i.e., the first data) of the first cell through actual measurement in T4. L3 cell filtering is required. At this time, the previous L3 filtered signal value of the first cell is the predicted value of T3. Therefore, the L3 filtered cell measurement value of T4 is obtained by using the first weight coefficient a1 based on the predicted value of T3 (L3 filtered) and the actual measurement value of T4 (L1-filtered).

[0141] At T5, the terminal obtains the L1-filtered actual measurement value (i.e., the first data) of the first cell through actual measurement. L3 cell filtering is required. At this time, the previous L3 filtered signal value of the first cell (i.e., the second data) is the L3 filtered cell measurement value of T4 (or, obtained after L3 cell filtering). Therefore, the L3 filtered cell measurement value of T5 is obtained by using the second weight coefficient a2 based on the L3 filtered cell measurement value of T4 and the L1-filtered actual measurement value of T5.

[0142] Taking Figure 4C as an example, the terminal obtains the L1-filtered actual measurement value (i.e., the first data) of the first cell through actual measurement in T6. L3 cell filtering is required. At this time, the previous L3 filtered signal value of the first cell (i.e., the second data) is the predicted value of T5. Therefore, the L3 filtered cell measurement value of T6 is obtained by using the first weight coefficient a1 based on the predicted value of T5 (L3 filtered) and the actual measurement value of T6 (L1-filtered).

[0143] Optionally, in some embodiments, before performing layer 3 filtering on the first data and the second data using a first weighting coefficient, the method further includes:

[0144] The terminal determines the first weighting coefficient.

[0145] In this embodiment of the application, the second weighting coefficient can be obtained by referring to the above-mentioned weighting coefficient a; the first weighting coefficient can be determined by the terminal based on the terminal implementation.

[0146] Optionally, in some embodiments, the terminal determines the first weighting coefficient by:

[0147] The terminal determines the first weighting coefficient based on the prediction accuracy corresponding to the second data or the prediction accuracy of the AI ​​model.

[0148] In this embodiment, the first weighting coefficient can be determined based on the prediction accuracy of the previous L3 filtered prediction. The worse the prediction accuracy, the larger the determined first weighting coefficient, resulting in a lower weight for the previous L3 filtered cell prediction during layer 3 filtering, thereby reducing the impact of inaccurate predictions. Alternatively, the first weighting coefficient can be determined based on the prediction accuracy of the AI ​​model. For example, the worse the prediction accuracy, the larger the determined first weighting coefficient, resulting in a lower weight for the previous L3 filtered prediction during layer 3 filtering, thereby reducing the impact of inaccurate predictions.

[0149] Optionally, in some embodiments, the terminal may also determine the first weighting coefficient and the second weighting coefficient based on the configuration information of the network-side device. For example, the method further includes: the terminal receiving at least one of first information and second information from the network-side device;

[0150] Wherein, the first information is used to determine the first weight coefficient, and the second information is used to determine the second weight coefficient.

[0151] Optionally, the first information includes any of the following:

[0152] The first weighting coefficient;

[0153] A first filtering coefficient, which is associated with the first weighting coefficient;

[0154] Adjustment factor;

[0155] Offset value;

[0156] The mapping relationship between prediction accuracy and adjustment coefficients or offset values;

[0157] The adjustment coefficient or the offset value is used to determine the first weight coefficient in combination with the second weight coefficient.

[0158] In this embodiment of the application, the adjustment coefficient can be used to adjust the second weight coefficient to obtain the first weight coefficient, and the offset value can be used to offset the second weight coefficient to obtain the first weight coefficient.

[0159] Optionally, in some embodiments, the method further includes any one of the following:

[0160] The terminal is based on a1 = 1 / 2 (k1 / 4) Determine the first weight coefficient, where a1 is the first weight coefficient and k1 is the first filtering coefficient;

[0161] The terminal determines the first weight coefficient based on a1 = a2 * x, where a1 is the first weight coefficient, a2 is the second weight coefficient, and x is the adjustment coefficient;

[0162] The terminal determines the first weight coefficient based on a1 = a2 + y, where a1 is the first weight coefficient, a2 is the second weight coefficient, and y is the offset value;

[0163] The terminal determines the adjustment coefficient based on the obtained prediction accuracy and the mapping relationship, and determines the first weight coefficient based on a1 = a2 * x, where a1 is the first weight coefficient, a2 is the second weight coefficient, and x is the adjustment coefficient;

[0164] The terminal determines the offset value based on the obtained prediction accuracy and the mapping relationship, and determines the first weight coefficient based on a1 = a2 + y, where a1 is the first weight coefficient, a2 is the second weight coefficient, and y is the offset value.

[0165] In this embodiment, when the first information includes a first weighting coefficient, the first information can be used as the first weighting coefficient. When the first information includes content other than the first weighting coefficient, the first weighting coefficient can be calculated based on the first information, or the first weighting coefficient can be determined by combining the first information and the second weighting coefficient. Since the method for determining the first weighting coefficient is clearly defined, the method is simple and easy to implement.

[0166] Optionally, if the first information includes a mapping relationship between prediction accuracy and adjustment coefficients or offset values, the terminal can obtain the prediction accuracy. This prediction accuracy can be the prediction accuracy associated with the AI ​​model itself, the current prediction accuracy of the AI ​​model monitored by the terminal, or the prediction accuracy of the previous L3 filtered prediction. Based on the above mapping relationship information and the prediction accuracy, the terminal obtains the adjustment coefficients or offset values, and then determines the first weight coefficient based on the adjustment coefficients or offset values ​​and the second weight coefficient. Different prediction accuracies can correspond to different adjustment coefficients or offset values. The worse the prediction accuracy, the larger the corresponding adjustment coefficient or offset value, resulting in a lower weight for the previous L3 filtered prediction value during layer 3 filtering, thereby reducing the impact of inaccurate predictions.

[0167] Optionally, in some embodiments, the adjustment coefficient is greater than 1, or the offset value is greater than 0.

[0168] Optionally, the second information includes any of the following:

[0169] Second weighting coefficient;

[0170] The second filtering coefficient is associated with the second weighting coefficient.

[0171] In this embodiment of the application, when the second information includes a second weighting coefficient, the second information can be directly used as the second weighting coefficient. Optionally, when the second information includes the second filtering coefficient, the method further includes:

[0172] The terminal is based on a2 = 1 / 2 (k2 / 4) Determine the second weighting coefficient, where a2 is the second weighting coefficient and k2 is the second filtering coefficient.

[0173] It should be understood that, in the embodiments of this application, the determination method of the second weighting coefficient is clearly defined, and the determination method is simple and easy to implement.

[0174] It should be noted that, for a target object that is a cell, corresponding values ​​for a first weighting coefficient and a second weighting coefficient can be set; similarly, for a target object that is a beam, corresponding values ​​for a first weighting coefficient and a second weighting coefficient can be set. The first weighting coefficient value for a target object that is a cell can be the same as or different from the first weighting coefficient value for a target object that is a beam, and the second weighting coefficient value for a target object that is a cell can be the same as or different from the second weighting coefficient value for a target object that is a beam.

[0175] To better understand this application, the following examples will be used to illustrate it in detail.

[0176] In some embodiments, when performing L3 cell filtering on a first cell, if the previous L3 filtered signal value of the first cell is a predicted value (generated based on an AI model), L3 cell filtering is performed using a first weighting coefficient based on the actual measured value of the first cell before L1-filtering (or before L3 filtering) and the previous L3 filtered cell predicted value; if the previous L3 filtered signal value is a measured value (e.g., a signal value generated by the L3 cell filtering mechanism), L3 cell filtering is performed using a second weighting coefficient based on the actual measured value of the cell before L1-filtering (or before L3 filtering) and the previous L3 filtered cell predicted value. The flowchart is shown in Figures 6A and 6B, and specifically includes the following steps:

[0177] Step 61: The terminal performs measurement. The terminal's Layer 3 (from the terminal's physical layer) receives (or obtains) the L1-filtered (or L3-unfiltered) actual cell measurement value of the first cell. Step 61 can also be replaced by the terminal performing measurement. The terminal's Layer 3 (from the UE's physical layer) receives the L1-filtered actual beam measurement values ​​of each beam under the first cell. Layer 3 performs beam selection and merging to generate the L1-filtered actual cell measurement value of the first cell.

[0178] Step 62, the UE performs a judgment on whether "the previous L3 filtered signal value of the first cell is a predicted value (generated based on the AI ​​model) (as shown in Figure 6A)" or whether "the previous L3 filtered signal value of the first cell is a measured value (generated through the L3 cell filtering mechanism) (as shown in Figure 6B)".

[0179] If the previous L3 filtered cell value of the first cell is a predicted value, or if the previous L3 filtered cell value of the first cell is not a measured value, the terminal executes step 63.

[0180] If the previous L3 filtered cell value of the first cell is not a predicted value, or if the previous L3 filtered cell value of the first cell is a measured value, the terminal executes step 64.

[0181] Due to the introduction of the AI ​​model, the previous L3 filtered signal value may be the output of the AI ​​model or a measured value (e.g., a signal value generated by the L3 cell filtering mechanism). Considering that the predicted value of the previous L3 filtered cell generated by the AI ​​model may have a large deviation (the larger the deviation, the greater the error will be propagated to subsequent L3 filtered signal values, thus affecting mobility performance), to address this issue, in this embodiment, different weighting coefficients can be used for the two cases (corresponding to steps 63 and 64, respectively). Preferably, comparatively, when the previous L3 filtered signal value of the first cell is a predicted value (generated based on the AI ​​model), a larger weighting coefficient is used to make the previous L3 filtered signal value account for a lower proportion in L3 cell filtering (or, to make the actual measured value of the L1-filtered cell account for a higher proportion), thereby mitigating the impact of inaccurate predictions.

[0182] Step 63: Based on the actual measured values ​​of the L1-filtered cells of the first cell and the predicted values ​​of the cells from the previous L3-filtered test, L3 cell filtering is performed using the first weighting coefficient a1. The formula can be as follows: F n = (1–a1)*F n-1 +a1*M n .

[0183] Optionally, the first weighting coefficient a1 is greater than or equal to the second weighting coefficient a2, thereby mitigating the impact of inaccurate predictions.

[0184] Step 64: Based on the actual cell measurement values ​​of the L1-filtered cell in the first cell and the cell measurement values ​​of the previous L3-filtered cell, perform L3 cell filtering using the second weighting coefficient a2. The formula can be as follows: F n = (1–a2)*F n-1 +a2*M n .

[0185] Taking Figure 4B as an example, the terminal obtains the L1-filtered actual measurement value (i.e., the first data) of the first cell through actual measurement in T4. L3 cell filtering is required. At this time, the previous L3 filtered signal value of the first cell is the predicted value of T3. Therefore, the L3 filtered cell measurement value of T4 is obtained by using the first weight coefficient a1 based on the predicted value of T3 (L3 filtered) and the actual measurement value of T4 (L1-filtered).

[0186] At T5, the terminal obtains the L1-filtered actual measurement value (i.e., the first data) of the first cell through actual measurement. L3 cell filtering is required. At this time, the previous L3 filtered signal value of the first cell (i.e., the second data) is the L3 filtered cell measurement value of T4 (or, obtained after L3 cell filtering). Therefore, the L3 filtered cell measurement value of T5 is obtained by using the second weight coefficient a2 based on the L3 filtered cell measurement value of T4 and the L1-filtered actual measurement value of T5.

[0187] Taking Figure 4C as an example, the terminal obtains the L1-filtered actual measurement value (i.e., the first data) of the first cell through actual measurement in T6. L3 cell filtering is required. At this time, the previous L3 filtered signal value of the first cell (i.e., the second data) is the predicted value of T5. Therefore, the L3 filtered cell measurement value of T6 is obtained by using the first weight coefficient a1 based on the predicted value of T5 (L3 filtered) and the actual measurement value of T6 (L1-filtered).

[0188] Optionally, before step 63 or 64, the terminal obtains a first weight coefficient a1 and a second weight coefficient a2. One possible method is that the second weight coefficient reuses the weight coefficient a described in related technologies. The terminal determines the first weight coefficient based on its own implementation. For example, it determines the first weight coefficient based on the prediction accuracy corresponding to the previous L3 filtered cell prediction value. The worse the prediction accuracy, the larger the determined first weight coefficient, so that the weight of the previous L3 filtered cell prediction value is lower when filtering L3 cells, thereby reducing the impact of inaccurate prediction values.

[0189] Another possible method is for the terminal to determine this based on information from the base station configuration. Referring to Figure 7, this specifically includes the following steps:

[0190] Step 71: The terminal receives first information and second information sent by the base station. The first information is used to obtain the first weight coefficient a1, and the second information is used to obtain the second weight coefficient a2.

[0191] The first information includes any one of the following:

[0192] The first weighting coefficient;

[0193] The first filtering coefficient k1 is associated with the first weighting coefficient;

[0194] Adjustment factor x;

[0195] Offset value y;

[0196] The mapping relationship between prediction accuracy and adjustment coefficients or offset values;

[0197] The adjustment coefficient or the offset value is used to determine the first weight coefficient in combination with the second weight coefficient.

[0198] The second information includes any one of the following:

[0199] Second weighting coefficient;

[0200] The second filtering coefficient k2 is associated with the second weighting coefficient.

[0201] Step 72: Obtain a first weight coefficient a1 based on the first information. The first weight coefficient a1 is used as a weight coefficient when performing L3 cell filtering in the case that the cell value of the previous L3 filtered cell in the first cell is the predicted value.

[0202] Specifically, for example:

[0203] When the first information is the first weight coefficient a1, the first information is directly used as the first weight coefficient a1. Optionally, a1 is greater than or equal to a2, thereby reducing the impact of inaccurate prediction values.

[0204] When the first piece of information is the first filtering coefficient k1, it can be based on the formula a1 = 1 / 2 (k1 / 4) The first weighting coefficient is obtained, preferably k1 is less than or equal to k2, thereby reducing the impact of inaccurate predictions;

[0205] If the first information is the adjustment coefficient x, first execute step 73 to obtain the second weight coefficient a2. The first weight coefficient can be obtained based on the formula a1=a2*x. Optionally, x is greater than or equal to 1, thereby reducing the impact of inaccurate prediction values.

[0206] If the first information is the offset value y, first execute the following step 73 to obtain the second weight coefficient a2. The first weight coefficient can be obtained based on the formula a1=a2+y. Optionally, y is greater than or equal to 0, thereby reducing the impact of inaccurate prediction values.

[0207] When the first information is the "mapping relationship between prediction accuracy and adjustment coefficient or offset value", the terminal obtains the prediction accuracy. This prediction accuracy can be the prediction accuracy associated with the AI ​​model itself, the current prediction accuracy of the AI ​​model monitored by the terminal, or the prediction accuracy of the previous L3 filtered cell prediction value. Based on the above mapping relationship information and the prediction accuracy, the terminal obtains the adjustment coefficient x or offset y. The terminal then executes step 73 to obtain the second weight coefficient a2, and obtains the first weight coefficient based on the formula a1 = a2 * x or a1 = a2 + y. In this method, different prediction accuracies can correspond to different adjustment coefficients or offsets. The worse the prediction accuracy, the larger the corresponding x or y, which makes the weight of the previous L3 filtered cell prediction value lower during L3 cell filtering, thereby reducing the impact of inaccurate prediction values.

[0208] Step 73: The terminal obtains the second weight coefficient a2 based on the second information. The second weight coefficient a2 is used as the weight coefficient when performing L3 cell filtering in the case where the cell value of the previous L3 filtered cell in the first cell is the measured value.

[0209] If the second information is the second weighting coefficient a2, then the first information is directly used as the second weighting coefficient a2.

[0210] When the second information is the second filtering coefficient k2, it can be based on the formula a2 = 1 / 2 (k2 / 4) The second weighting coefficient a2 is obtained. Optionally, k2 here can reuse k (i.e., the filterCoefficient cell configured by the base station) described in the above related techniques, that is, a2 = 1 / 2 (k / 4) .

[0211] The above embodiments describe a scheme for filtering L3 cells. Research has revealed similar issues that need to be addressed regarding beam filtering. For example, in some embodiments, a scheme for filtering L3 beams can be provided. The main idea is that when performing L3 beam filtering for the first beam, if the previous L3 filtered beam value of the first beam is a predicted value (generated by an AI model), L3 beam filtering is performed using a third weighting coefficient (since L3 cell filtering and L3 beam filtering each use their own parameters, this third weighting coefficient is equivalent to the first weighting coefficient in the above embodiment) based on the actual measured value of the L1-filtered beam of the first beam and the previous predicted value of the L3 filtered beam. If the previous L3 filtered beam value is a measured value (e.g., a beam value generated by the L3 beam filtering mechanism), L3 beam filtering is performed using a fourth weighting coefficient (since L3 cell filtering and L3 beam filtering each use their own parameters, this fourth weighting coefficient is equivalent to the second weighting coefficient in the above embodiment) based on the actual measured value of the L1-filtered beam and the previous measured value of the L3 filtered beam. Detailed steps can be found in the steps of the scheme for Layer 3 cell filtering, and will not be repeated here. The difference between the two is that, for the Layer 3 beam filtering scheme, the terminal's Layer 3 does not need to perform operations such as "Layer 3 performs beam selection and merging to generate the actual measurement value of the L1-filtered cell of the first cell". Instead, after receiving the actual measurement value of the L1 filtered beam, Layer 3 directly uses the value to perform L3 beam filtering.

[0212] It should be noted that in scenarios where the predicted cell value or beam value output by the AI ​​model is an L3-filtered signal value, inaccurate prediction of the L3-filtered signal value will adversely affect subsequent L3 filtering. The solution proposed in this application uses different L3 filtering weight factors (first weight coefficient and second weight coefficient) for different scenarios, thereby mitigating the adverse effects of inaccurate prediction on subsequent L3 filtering and further improving mobility performance.

[0213] Referring to Figure 8, this application embodiment also provides a data filtering processing method, as shown in Figure 8, the data filtering processing method includes:

[0214] Step 801: The network-side device sends the first information and the second information to the terminal;

[0215] Wherein, the first information is used to determine the first weight coefficient, and the second information is used to determine the second weight coefficient. The first weight coefficient is used by the terminal to perform layer 3 filtering on the first data and the second data of the target object when the terminal determines that the second data of the target object is generated based on an AI model. The second weight coefficient is used by the terminal to perform layer 3 filtering on the first data and the second data of the target object when the terminal determines that the second data of the target object is generated based on a layer 3 filtering mechanism.

[0216] The target object is a beam or a cell; the first data is the actual measurement value before layer 3 filtering or the actual measurement value after layer 1 filtering obtained by the terminal during measurement; the second data is the signal value after the most recent layer 3 filtering.

[0217] Optionally, the first weighting coefficient is greater than the second weighting coefficient.

[0218] Optionally, the first information includes any of the following:

[0219] The first weighting coefficient;

[0220] A first filtering coefficient, which is associated with the first weighting coefficient;

[0221] Adjustment factor;

[0222] Offset value;

[0223] The mapping relationship between prediction accuracy and adjustment coefficients or offset values;

[0224] The adjustment coefficient or the offset value is used to determine the first weight coefficient in combination with the second weight coefficient.

[0225] Optionally, the method for determining the first weighting coefficient includes any of the following:

[0226] When the first information includes the first filtering coefficient, the first weighting coefficient is determined as follows: based on a1 = 1 / 2 (k1 / 4) Determine the first weight coefficient, where a1 is the first weight coefficient and k1 is the first filtering coefficient;

[0227] When the first information includes the adjustment coefficient, or includes the mapping relationship between prediction accuracy and adjustment coefficient, the first weight coefficient is determined as follows: the first weight coefficient is determined according to a1 = a2 * x, where a1 is the first weight coefficient, a2 is the second weight coefficient, and x is the adjustment coefficient;

[0228] When the first information includes the offset value, or includes the mapping relationship between prediction accuracy and offset value, the first weight coefficient is determined as follows: the first weight coefficient is determined according to a1 = a2 + y, where a1 is the first weight coefficient, a2 is the second weight coefficient, and y is the offset value.

[0229] Optionally, the adjustment coefficient is greater than 1, or the offset value is greater than 0.

[0230] Optionally, the second information includes any of the following:

[0231] Second weighting coefficient;

[0232] The second filtering coefficient is associated with the second weighting coefficient.

[0233] Optionally, when the second information includes the second filtering coefficient, the second weighting coefficient is determined as follows:

[0234] According to a2 = 1 / 2 (k2 / 4) Determine the second weighting coefficient, where a2 is the second weighting coefficient and k2 is the second filtering coefficient.

[0235] The data filtering processing method provided in this application can be executed by a data filtering processing device. This application uses an example of a data filtering processing device executing the data filtering processing method to illustrate the data filtering processing device provided in this application.

[0236] This application provides a data filtering processing apparatus. As an example, the data filtering processing apparatus may be a communication device or a component within a communication device, such as a chip. The communication device may be a terminal, a network-side device, or a server, etc. Exemplarily, the terminal may include, but is not limited to, the type of terminal 11 listed above, and the network-side device may include, but is not limited to, the type of network-side device 12 listed above. This application does not impose specific limitations.

[0237] The data filtering and processing device includes a receiving module, a transmitting module, and a processing module. These modules can be implemented in software or hardware. When implemented in hardware, the processing module can be implemented by a processor. For example, the processor can include general-purpose processors, special-purpose processors, such as a Central Processing Unit (CPU), microprocessor, Digital Signal Processor (DSP), Artificial Intelligence (AI) processor, Graphics Processing Unit (GPU), Application Specific Integrated Circuit (ASIC), Network Processor (NP), Field Programmable Gate Array (FPGA), or other programmable logic devices, gate circuits, transistors, discrete hardware components, etc. The receiving and transmitting modules can be implemented by a communication interface, which can include one or more of the following: transceiver, pins, circuits, bus, radio frequency unit, etc.

[0238] Specifically, referring to Figure 9, when the data filtering processing device is a terminal or a component within a terminal, the data filtering processing device 900 includes:

[0239] Processing module 901 is used to perform measurements and obtain the first data of the target object;

[0240] The processing module 901 is further configured to determine whether the second data of the target object is generated based on an artificial intelligence (AI) model or based on a layer 3 filtering mechanism;

[0241] The processing module 901 is further configured to perform a target operation, the target operation including at least one of the following:

[0242] If it is determined that the second data is generated based on an AI model, the first data and the second data are filtered using a first weighting coefficient in layer 3.

[0243] If it is determined that the second data is generated based on a layer 3 filtering mechanism, layer 3 filtering is performed on the first data and the second data using a second weighting coefficient.

[0244] The target object is a beam or a cell; the first data is the actual measurement value before layer 3 filtering or the actual measurement value after layer 1 filtering; the second data is the signal value after the most recently obtained layer 3 filtering.

[0245] Optionally, the first weighting coefficient is greater than the second weighting coefficient.

[0246] Optionally, the target measurement value F is obtained by performing layer 3 filtering on the first data and the second data using a first weighting coefficient. n Satisfy: F n = (1–a1)*F n-1 +a1*M n ;

[0247] Where a1 is the first weighting coefficient, F n-1 The second data refers to the predicted values ​​after layer 3 filtering generated by the AI ​​model, M. n This refers to the first data.

[0248] Optionally, the target measurement value F is obtained by performing layer 3 filtering on the first data and the second data using a second weighting coefficient. n Satisfy: F n = (1–a2)*F n-1 +a2*M n ;

[0249] Where a2 is the second weighting coefficient, F n-1 The second data is the measurement value generated based on the layer 3 filtering mechanism, M. n This refers to the first data.

[0250] Optionally, the processing module 901 is further configured to determine the first weight coefficient before performing layer 3 filtering on the first data and the second data using the first weight coefficient.

[0251] Optionally, the processing module 901 is specifically used to determine the first weight coefficient based on the prediction accuracy corresponding to the second data or the prediction accuracy of the AI ​​model.

[0252] Optionally, the data filtering processing device further includes:

[0253] A receiving module is configured to receive at least one of first information and second information from a network-side device;

[0254] Wherein, the first information is used to determine the first weight coefficient, and the second information is used to determine the second weight coefficient.

[0255] Optionally, the first information includes any of the following:

[0256] The first weighting coefficient;

[0257] A first filtering coefficient, which is associated with the first weighting coefficient;

[0258] Adjustment factor;

[0259] Offset value;

[0260] The mapping relationship between prediction accuracy and adjustment coefficients or offset values;

[0261] The adjustment coefficient or the offset value is used to determine the first weight coefficient in combination with the second weight coefficient.

[0262] Optionally, the processing module 901 is further configured to perform any of the following:

[0263] Based on a1 = 1 / 2 (k1 / 4) Determine the first weight coefficient, where a1 is the first weight coefficient and k1 is the first filtering coefficient;

[0264] The first weight coefficient is determined based on a1 = a2 * x, where a1 is the first weight coefficient, a2 is the second weight coefficient, and x is the adjustment coefficient;

[0265] The first weight coefficient is determined based on a1 = a2 + y, where a1 is the first weight coefficient, a2 is the second weight coefficient, and y is the offset value;

[0266] The adjustment coefficient is determined based on the obtained prediction accuracy and the mapping relationship, and the first weight coefficient is determined based on a1 = a2 * x, where a1 is the first weight coefficient, a2 is the second weight coefficient, and x is the adjustment coefficient.

[0267] The offset value is determined based on the obtained prediction accuracy and the mapping relationship, and the first weight coefficient is determined based on a1 = a2 + y, where a1 is the first weight coefficient, a2 is the second weight coefficient, and y is the offset value.

[0268] Optionally, the adjustment coefficient is greater than 1, or the offset value is greater than 0.

[0269] Optionally, the second information includes any of the following:

[0270] Second weighting coefficient;

[0271] The second filtering coefficient is associated with the second weighting coefficient.

[0272] Optionally, the processing module 901 is further configured to, when the second information includes the second filtering coefficient, base the filter on a2 = 1 / 2. (k2 / 4) Determine the second weighting coefficient, where a2 is the second weighting coefficient and k2 is the second filtering coefficient.

[0273] Referring to Figure 10, when the data filtering processing device is a network-side device or a component within a network-side device, the data filtering processing device 1000 includes:

[0274] The sending module 1001 is used to send first information and second information to the terminal.

[0275] Wherein, the first information is used to determine the first weight coefficient, and the second information is used to determine the second weight coefficient. The first weight coefficient is used by the terminal to perform layer 3 filtering on the first data and the second data of the target object when the terminal determines that the second data of the target object is generated based on an AI model. The second weight coefficient is used by the terminal to perform layer 3 filtering on the first data and the second data of the target object when the terminal determines that the second data of the target object is generated based on a layer 3 filtering mechanism.

[0276] The target object is a beam or a cell; the first data is the actual measurement value before layer 3 filtering or the actual measurement value after layer 1 filtering obtained by the terminal during measurement; the second data is the signal value after the most recent layer 3 filtering.

[0277] Optionally, the first information includes any of the following:

[0278] The first weighting coefficient;

[0279] A first filtering coefficient, which is associated with the first weighting coefficient;

[0280] Adjustment factor;

[0281] Offset value;

[0282] The mapping relationship between prediction accuracy and adjustment coefficients or offset values;

[0283] The adjustment coefficient or the offset value is used to determine the first weight coefficient in combination with the second weight coefficient.

[0284] Optionally, the method for determining the first weighting coefficient includes any of the following:

[0285] When the first information includes the first filtering coefficient, the first weighting coefficient is determined as follows: based on a1 = 1 / 2 (k1 / 4) Determine the first weight coefficient, where a1 is the first weight coefficient and k1 is the first filtering coefficient;

[0286] When the first information includes the adjustment coefficient, or includes the mapping relationship between prediction accuracy and adjustment coefficient, the first weight coefficient is determined as follows: the first weight coefficient is determined according to a1 = a2 * x, where a1 is the first weight coefficient, a2 is the second weight coefficient, and x is the adjustment coefficient;

[0287] When the first information includes the offset value, or includes the mapping relationship between prediction accuracy and offset value, the first weight coefficient is determined as follows: the first weight coefficient is determined according to a1 = a2 + y, where a1 is the first weight coefficient, a2 is the second weight coefficient, and y is the offset value.

[0288] Optionally, the adjustment coefficient is greater than 1, or the offset value is greater than 0.

[0289] Optionally, the second information includes any of the following:

[0290] Second weighting coefficient;

[0291] The second filtering coefficient is associated with the second weighting coefficient.

[0292] Optionally, when the second information includes the second filtering coefficient, the second weighting coefficient is determined as follows:

[0293] According to a2 = 1 / 2 (k2 / 4) Determine the second weighting coefficient, where a2 is the second weighting coefficient and k2 is the second filtering coefficient.

[0294] Optionally, the first weighting coefficient is greater than the second weighting coefficient.

[0295] The data filtering processing device provided in this application embodiment can implement the various processes implemented in the method embodiment of FIG5 or FIG8 and achieve the same technical effect. To avoid repetition, it will not be described again here.

[0296] As shown in Figure 11, this application embodiment also provides a communication device 1100, including a processor 1101 and a memory 1102. The memory 1102 stores a program or instructions that can run on the processor 1101. When the program or instructions are executed by the processor 1101, they implement the various steps of the above-described data filtering processing method embodiment and can achieve the same technical effect. To avoid repetition, they will not be described again here.

[0297] This application also provides a terminal, including a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is used to run programs or instructions to implement the steps in the method embodiment shown in FIG5. This terminal embodiment corresponds to the above-described terminal-side method embodiment, and all implementation processes and methods of the above-described method embodiments can be applied to this terminal embodiment and can achieve the same technical effect. The terminal may be the data filtering processing device shown in FIG9. Specifically, FIG12 is a schematic diagram of the hardware structure of a terminal implementing an embodiment of this application.

[0298] The terminal 1200 includes, but is not limited to, at least some of the following components: radio frequency unit 1201, network module 1202, audio output unit 1203, input unit 1204, sensor 1205, display unit 1206, user input unit 1207, interface unit 1208, memory 1209, and processor 1210.

[0299] Those skilled in the art will understand that terminal 1200 may also include a power supply (such as a battery) for powering various components. The power supply can be logically connected to processor 1210 through a power management system, thereby enabling functions such as charging, discharging, and power consumption management through the power management system. The terminal structure shown in Figure 12 does not constitute a limitation on the terminal. The terminal may include more or fewer components than shown, or combine certain components, or have different component arrangements, which will not be elaborated here.

[0300] It should be understood that, in this embodiment, the input unit 1204 may include a graphics processor 12041 and a microphone 12042. The graphics processor 12041 processes image data of still images or videos obtained by an image capture device (such as a camera) in video capture mode or image capture mode. The display unit 1206 may include a display panel 12061, which may be configured in the form of a liquid crystal display, an organic light-emitting diode, or the like. The user input unit 1207 includes a touch panel 12071 and at least one of other input devices 12072. The touch panel 12071 is also called a touch screen. The touch panel 12071 may include a touch detection device and a touch controller. Other input devices 12072 may include, but are not limited to, physical keyboards, function keys (such as volume control buttons, power buttons, etc.), trackballs, mice, and joysticks, which will not be described in detail here.

[0301] In this embodiment, after receiving downlink data from the network-side device, the radio frequency unit 1201 can transmit it to the processor 1210 for processing; in addition, the radio frequency unit 1201 can send uplink data to the network-side device. Typically, the radio frequency unit 1201 includes, but is not limited to, antennas, amplifiers, transceivers, couplers, low-noise amplifiers, duplexers, etc.

[0302] The memory 1209 can be used to store software programs or instructions, as well as various data. The memory 1209 may primarily include a first storage area for storing programs or instructions and a second storage area for storing data. The first storage area may store the operating system, application programs or instructions required for at least one function (such as sound playback, image playback, etc.). Furthermore, the memory 1209 may include volatile memory or non-volatile memory. The non-volatile memory may be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. Volatile memory can be random access memory (RAM), static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDRSDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM), and direct memory bus RAM (DRRAM). The memory 1209 in this embodiment includes, but is not limited to, these and any other suitable types of memory.

[0303] Processor 1210 may include one or more processing units; optionally, processor 1210 integrates an application processor and a modem processor, wherein the application processor mainly handles operations involving the operating system, user interface, and applications, and the modem processor mainly handles wireless communication signals, such as a baseband processor. It is understood that the aforementioned modem processor may also not be integrated into processor 1210.

[0304] The processor 1210 is configured to perform measurements to obtain first data of the target object; determine whether the second data of the target object is generated based on an artificial intelligence (AI) model or a layer 3 filtering mechanism; and perform a target operation, the target operation including at least one of the following:

[0305] If it is determined that the second data is generated based on an AI model, the first data and the second data are filtered using a first weighting coefficient in layer 3.

[0306] If it is determined that the second data is generated based on a layer 3 filtering mechanism, layer 3 filtering is performed on the first data and the second data using a second weighting coefficient.

[0307] The target object is a beam or a cell; the first data is the actual measurement value before layer 3 filtering or the actual measurement value after layer 1 filtering; the second data is the signal value after the most recently obtained layer 3 filtering.

[0308] It is understood that the implementation process of each implementation method mentioned in this embodiment can refer to the relevant description of the data filtering processing method in the method embodiment, and achieve the same or corresponding technical effect. To avoid repetition, it will not be described again here.

[0309] This application also provides a network-side device, including a processor and a communication interface. The communication interface is coupled to the processor, and the processor is used to run programs or instructions to implement the steps of the method embodiment shown in FIG8. This network-side device embodiment corresponds to the above-described network-side device method embodiment. All implementation processes and methods of the above-described method embodiments can be applied to this network-side device embodiment and can achieve the same technical effect.

[0310] Specifically, this application embodiment also provides a network-side device, which may be the data filtering and processing device shown in FIG10. As shown in FIG13, the network-side device 1300 includes: an antenna 1301, a radio frequency device 1302, a baseband device 1303, a processor 1304, and a memory 1305. The antenna 1301 is connected to the radio frequency device 1302. In the uplink direction, the radio frequency device 1302 receives information through the antenna 1301 and sends the received information to the baseband device 1303 for processing. In the downlink direction, the baseband device 1303 processes the information to be transmitted and sends it to the radio frequency device 1302, which processes the received information and then transmits it through the antenna 1301.

[0311] The method executed by the network-side device in the above embodiments can be implemented in the baseband device 1303, which includes a baseband processor.

[0312] The baseband device 1303 may include at least one baseband board, on which multiple chips are disposed, as shown in FIG13. One of the chips is, for example, a baseband processor, which is connected to the memory 1305 via a bus interface to call the program in the memory 1305 to execute the network-side device operation shown in the above method embodiment.

[0313] The network-side device may also include a network interface 1306, such as a Common Public Radio Interface (CPRI).

[0314] The radio frequency device 1302 is used to: send first information and second information to the terminal;

[0315] Wherein, the first information is used to determine the first weight coefficient, and the second information is used to determine the second weight coefficient. The first weight coefficient is used by the terminal to perform layer 3 filtering on the first data and the second data of the target object when the terminal determines that the second data of the target object is generated based on an AI model. The second weight coefficient is used by the terminal to perform layer 3 filtering on the first data and the second data of the target object when the terminal determines that the second data of the target object is generated based on a layer 3 filtering mechanism.

[0316] The target object is a beam or a cell; the first data is the actual measurement value before layer 3 filtering or the actual measurement value after layer 1 filtering obtained by the terminal during measurement; the second data is the signal value after the most recent layer 3 filtering.

[0317] Specifically, the network-side device 1300 in this application embodiment further includes: instructions or programs stored in memory 1305 and executable on processor 1304. Processor 1304 calls the instructions or programs in memory 1305 to execute the methods executed by each module shown in FIG10 and achieve the same technical effect. To avoid repetition, it will not be described in detail here.

[0318] This application also provides a readable storage medium storing a program or instructions. When the program or instructions are executed by a processor, they implement the various processes of the above-described data filtering processing method embodiments and achieve the same technical effect. To avoid repetition, they will not be described again here.

[0319] The processor mentioned above is the processor in the terminal described in the above embodiments. The readable storage medium includes computer-readable storage media, such as computer read-only memory (ROM), random access memory (RAM), magnetic disk, or optical disk. In some examples, the readable storage medium may be a non-transient readable storage medium.

[0320] This application embodiment also provides a chip, which includes a processor and a communication interface. The communication interface is coupled to the processor. The processor is used to run programs or instructions to implement the various processes of the above-described data filtering processing method embodiments and can achieve the same technical effect. To avoid repetition, it will not be described again here.

[0321] It should be understood that the chip mentioned in the embodiments of this application may also be referred to as a system-on-a-chip, system chip, chip system, or system-on-a-chip, etc.

[0322] This application also provides a computer program / program product, which includes computer instructions. The computer program / program product is executed by at least one processor to implement the various processes of the above-described data filtering processing method embodiments and can achieve the same technical effect. To avoid repetition, it will not be described again here.

[0323] This application also provides a wireless communication system, including: a terminal and a network-side device, wherein the terminal can be used to perform the steps of the data filtering processing method on the terminal side as described above, and the network-side device can be used to perform the steps of the data filtering processing method on the network-side device as described above.

[0324] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element. Furthermore, it should be noted that the scope of the methods and apparatuses in the embodiments of this application is not limited to performing functions in the order shown or discussed, but may also include performing functions substantially simultaneously or in the reverse order, depending on the functions involved. For example, the described methods may be performed in a different order than described, and various steps may be added, omitted, or combined. Additionally, features described with reference to certain examples may be combined in other examples.

[0325] From the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of computer software products plus necessary general-purpose hardware platforms, and of course, they can also be implemented by hardware. The computer software product is stored in a storage medium (such as ROM, RAM, magnetic disk, optical disk, etc.) and includes several instructions to cause the terminal or network-side device to execute the methods described in the various embodiments of this application.

[0326] The embodiments of this application have been described above with reference to the accompanying drawings. However, this application is not limited to the specific embodiments described above. The specific embodiments described above are merely illustrative and not restrictive. Those skilled in the art can make many other implementations under the guidance of this application without departing from the spirit and scope of the claims. All of these implementations are within the protection scope of this application.

Claims

1. A data filtering processing method, comprising: The terminal performs the measurement to obtain the first data of the target object; The terminal determines whether the second data of the target object is generated based on an artificial intelligence (AI) model or based on a layer 3 filtering mechanism; The terminal performs a target operation, which includes at least one of the following: If it is determined that the second data is generated based on an AI model, the first data and the second data are filtered using a first weighting coefficient in layer 3. If it is determined that the second data is generated based on a layer 3 filtering mechanism, layer 3 filtering is performed on the first data and the second data using a second weighting coefficient. The target object is a beam or a cell; the first data is the actual measurement value before layer 3 filtering or the actual measurement value after layer 1 filtering; the second data is the signal value after the most recently obtained layer 3 filtering.

2. The method according to claim 1, wherein, The first weighting coefficient is greater than the second weighting coefficient.

3. The method according to claim 1 or 2, wherein, The target measurement value F is obtained by performing Layer 3 filtering on the first data and the second data using a first weighting coefficient. n Satisfy: F n = (1–a1)*F n-1 +a1*M n ; Where a1 is the first weighting coefficient, F n-1 The second data refers to the predicted values ​​after layer 3 filtering generated by the AI ​​model, M. n This refers to the first data.

4. The method according to claim 1 or 2, wherein, The target measurement value F is obtained by performing Layer 3 filtering on the first and second data using a second weighting coefficient. n Satisfy: F n = (1–a2)*F n-1 +a2*M n ; Where a2 is the second weighting coefficient, F n-1 The second data is the measurement value generated based on the layer 3 filtering mechanism, M. n This refers to the first data.

5. The method according to any one of claims 1 to 4, wherein, Before performing Layer 3 filtering on the first data and the second data using the first weighting coefficient, the method further includes: The terminal determines the first weighting coefficient.

6. The method according to claim 5, wherein, The terminal determines the first weighting coefficient, including: The terminal determines the first weighting coefficient based on the prediction accuracy corresponding to the second data or the prediction accuracy of the AI ​​model.

7. The method according to any one of claims 1 to 4, wherein the method further comprises: The terminal receives at least one of the first information and the second information from the network-side device; Wherein, the first information is used to determine the first weight coefficient, and the second information is used to determine the second weight coefficient.

8. The method according to claim 7, wherein, The first information includes any one of the following: The first weighting coefficient; A first filtering coefficient, which is associated with the first weighting coefficient; Adjustment factor; Offset value; The mapping relationship between prediction accuracy and adjustment coefficients or offset values; The adjustment coefficient or the offset value is used to determine the first weight coefficient in combination with the second weight coefficient.

9. The method according to claim 8, wherein, The method further includes any one of the following: The terminal is based on a1 = 1 / 2 (k1 / 4) Determine the first weight coefficient, where a1 is the first weight coefficient and k1 is the first filtering coefficient; The terminal determines the first weight coefficient based on a1 = a2 * x, where a1 is the first weight coefficient, a2 is the second weight coefficient, and x is the adjustment coefficient; The terminal determines the first weight coefficient based on a1 = a2 + y, where a1 is the first weight coefficient, a2 is the second weight coefficient, and y is the offset value; The terminal determines the adjustment coefficient based on the obtained prediction accuracy and the mapping relationship, and determines the first weight coefficient based on a1 = a2 * x, where a1 is the first weight coefficient, a2 is the second weight coefficient, and x is the adjustment coefficient; The terminal determines the offset value based on the obtained prediction accuracy and the mapping relationship, and determines the first weight coefficient based on a1 = a2 + y, where a1 is the first weight coefficient, a2 is the second weight coefficient, and y is the offset value.

10. The method according to claim 9, wherein, The adjustment coefficient is greater than 1, or the offset value is greater than 0.

11. The method according to any one of claims 7 to 10, wherein, The second information includes any one of the following: Second weighting coefficient; The second filtering coefficient is associated with the second weighting coefficient.

12. The method according to claim 11, wherein, When the second information includes the second filtering coefficient, the method further includes: The terminal is based on a2 = 1 / 2 (k2 / 4) Determine the second weighting coefficient, where a2 is the second weighting coefficient and k2 is the second filtering coefficient.

13. A data filtering processing method, comprising: The network-side device sends the first and second information to the terminal; Wherein, the first information is used to determine the first weight coefficient, and the second information is used to determine the second weight coefficient. The first weight coefficient is used by the terminal to perform layer 3 filtering on the first data and the second data of the target object when the terminal determines that the second data of the target object is generated based on an AI model. The second weight coefficient is used by the terminal to perform layer 3 filtering on the first data and the second data of the target object when the terminal determines that the second data of the target object is generated based on a layer 3 filtering mechanism. The target object is a beam or a cell; the first data is the actual measurement value before layer 3 filtering or the actual measurement value after layer 1 filtering obtained by the terminal during measurement; the second data is the signal value after the most recent layer 3 filtering.

14. The method according to claim 13, wherein, The first information includes any one of the following: The first weighting coefficient; A first filtering coefficient, which is associated with the first weighting coefficient; Adjustment factor; Offset value; The mapping relationship between prediction accuracy and adjustment coefficients or offset values; The adjustment coefficient or the offset value is used to determine the first weight coefficient in combination with the second weight coefficient.

15. The method according to claim 14, wherein, The method for determining the first weighting coefficient includes any of the following: When the first information includes the first filtering coefficient, the first weighting coefficient is determined as follows: based on a1 = 1 / 2 (k1 / 4) Determine the first weight coefficient, where a1 is the first weight coefficient and k1 is the first filtering coefficient; When the first information includes the adjustment coefficient, or includes the mapping relationship between prediction accuracy and adjustment coefficient, the first weight coefficient is determined as follows: the first weight coefficient is determined according to a1 = a2 * x, where a1 is the first weight coefficient, a2 is the second weight coefficient, and x is the adjustment coefficient; When the first information includes the offset value, or includes the mapping relationship between prediction accuracy and offset value, the first weight coefficient is determined as follows: the first weight coefficient is determined according to a1 = a2 + y, where a1 is the first weight coefficient, a2 is the second weight coefficient, and y is the offset value.

16. The method according to claim 15, wherein, The adjustment coefficient is greater than 1, or the offset value is greater than 0.

17. The method according to any one of claims 13 to 16, wherein, The second information includes any one of the following: Second weighting coefficient; The second filtering coefficient is associated with the second weighting coefficient.

18. The method according to claim 17, wherein, When the second information includes the second filtering coefficient, the second weighting coefficient is determined as follows: According to a2 = 1 / 2 (k2 / 4) Determine the second weighting coefficient, where a2 is the second weighting coefficient and k2 is the second filtering coefficient.

19. A data filtering processing apparatus, comprising: The processing module is used to perform measurements and obtain the first data of the target object; The processing module is also used to determine whether the second data of the target object is generated based on an artificial intelligence (AI) model or based on a layer 3 filtering mechanism; The processing module is further configured to perform a target operation, the target operation including at least one of the following: If it is determined that the second data is generated based on an AI model, the first data and the second data are filtered using a first weighting coefficient in layer 3. If it is determined that the second data is generated based on a layer 3 filtering mechanism, layer 3 filtering is performed on the first data and the second data using a second weighting coefficient. The target object is a beam or a cell; the first data is the actual measurement value before layer 3 filtering or the actual measurement value after layer 1 filtering; the second data is the signal value after the most recently obtained layer 3 filtering.

20. The apparatus according to claim 19, wherein, The target measurement value F is obtained by performing Layer 3 filtering on the first data and the second data using a first weighting coefficient. n Satisfy: F n = (1–a1)*F n-1 +a1*M n ; Where a1 is the first weighting coefficient, F n-1 The second data refers to the predicted values ​​after layer 3 filtering generated by the AI ​​model, M. n This refers to the first data.

21. The apparatus according to claim 19, wherein, The target measurement value F is obtained by performing Layer 3 filtering on the first and second data using a second weighting coefficient. n Satisfy: F n = (1–a2)*F n-1 +a2*M n ; Where a2 is the second weighting coefficient, F n-1 The second data is the measurement value generated based on the layer 3 filtering mechanism, M. n This refers to the first data.

22. The apparatus according to any one of claims 19 to 21, further comprising: A receiving module is configured to receive at least one of first information and second information from a network-side device; Wherein, the first information is used to determine the first weight coefficient, and the second information is used to determine the second weight coefficient.

23. A data filtering processing apparatus, comprising: The sending module is used to send first information and second information to the terminal; Wherein, the first information is used to determine the first weight coefficient, and the second information is used to determine the second weight coefficient. The first weight coefficient is used by the terminal to perform layer 3 filtering on the first data and the second data of the target object when the terminal determines that the second data of the target object is generated based on an AI model. The second weight coefficient is used by the terminal to perform layer 3 filtering on the first data and the second data of the target object when the terminal determines that the second data of the target object is generated based on a layer 3 filtering mechanism. The target object is a beam or a cell; the first data is the actual measurement value before layer 3 filtering or the actual measurement value after layer 1 filtering obtained by the terminal during measurement; the second data is the signal value after the most recent layer 3 filtering.

24. The apparatus according to claim 23, wherein, The first information includes any one of the following: The first weighting coefficient; A first filtering coefficient, which is associated with the first weighting coefficient; Adjustment factor; Offset value; The mapping relationship between prediction accuracy and adjustment coefficients or offset values; The adjustment coefficient or the offset value is used to determine the first weight coefficient in combination with the second weight coefficient.

25. The apparatus according to claim 23 or 24, wherein, The second information includes any one of the following: Second weighting coefficient; The second filtering coefficient is associated with the second weighting coefficient.

26. A terminal 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 data filtering processing method as claimed in any one of claims 1 to 12.

27. A network-side device, 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 data filtering processing method as described in any one of claims 13 to 18.

28. A readable storage medium storing a program or instructions that, when executed by a processor, implement the steps of the data filtering processing method as claimed in any one of claims 1 to 18.

29. A computer program product comprising computer instructions that, when executed by a processor, implement the steps of the data filtering processing method as described in any one of claims 1 to 18.

Images