Cell camping processing method and apparatus, and terminal and network-side device

Abstract

The present application belongs to the technical field of communications. Disclosed are a cell camping processing method and apparatus, and a terminal and a network-side device. The cell camping processing method in the embodiments of the present application comprises: a first device obtaining a target result on the basis of a first artificial intelligence (AI) model, wherein the first device is a terminal, a network-side device or a server, the target result is used for cell camping, and the target result includes at least one of the following: a frequency-domain position where a synchronization signal is sent, a time-domain position where the synchronization signal is sent, a beam sending direction in which the synchronization signal is sent, and information of a first cell, the first cell being a cell that can be camped on.

Description

Cell camping processing method and device, terminal and network side equipment

[0001] Cross-reference to Related Applications

[0002] The present application claims priority to the Chinese patent application No. 202410717888.4 filed on June 4, 2024 in China, the content of which is incorporated herein by reference in its entirety. TECHNICAL FIELD

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

[0004] With the development of communication technology, in a communication system, when a terminal is powered on to perform cell search, the terminal will usually first read the information of a Subscriber Identity Module (SIM) card, and find a suitable cell to camp on according to the prior information (such as previously stored cell and frequency point information) stored in the SIM card. If the terminal does not store prior information, or does not find a suitable camping cell based on the stored prior information (for example, the stored prior information has become invalid or is not applicable), the terminal will trigger a frequency scanning and network searching process on the frequency bands supported by the SIM card, and perform initial cell selection. This process takes a long time, resulting in a long delay in cell camping of the terminal. SUMMARY

[0005] Embodiments of the present application provide a cell camping processing method and device, a terminal and a network side equipment, which can solve the problem of long delay in cell camping of the terminal due to long time of initial cell search and selection.

[0006] In a first aspect, a cell camping processing method is provided, comprising:

[0007] A first device obtains a target result based on a first artificial intelligence (AI) model;

[0008] The first device is a terminal, a network side equipment or a server, the target result is used for cell camping, and the target result includes at least one of the following: a frequency domain position of synchronization signal transmission; a time domain position of synchronization signal transmission; a beam transmission direction of synchronization signal transmission; information of a first cell, the first cell being a cell that can be camped on.

[0009] In a second aspect, a cell camping processing method is provided, comprising:

[0010] A second device performs at least one of the following:

[0011] The second device sends at least part of the information in the first information to the first device, the first information being used for inference of the first AI model.

[0012] The second operation;

[0013] The second operation includes at least one of the following:

[0014] The second device performs training of the first AI model, obtains the first AI model, and sends the first AI model to the first device;

[0015] The second device performs training of the first AI model, obtains a second training result, and sends the second training result to the first device, the second training result being used for the first device to perform training of the first AI model;

[0016] The first device is a terminal, a network side device or a server, the second device is a terminal, a network side device or a server, the first AI model is used to determine a target result, the target result is used to perform cell camping, and the target result includes at least one of the following: a frequency domain position of synchronization signal transmission; a time domain position of synchronization signal transmission; a beam transmission direction of synchronization signal transmission; information of a first cell, the first cell being a cell that can be camped.

[0017] In a third aspect, a cell camping processing apparatus is provided, applied to a first device, and includes:

[0018] A first processing module is configured to obtain a target result based on a first artificial intelligence (AI) model.

[0019] The first device is a terminal, a network side device or a server, the target result is used to perform cell camping, and the target result includes at least one of the following: a frequency domain position of synchronization signal transmission; a time domain position of synchronization signal transmission; a beam transmission direction of synchronization signal transmission; information of a first cell, the first cell being a cell that can be camped.

[0020] In a fourth aspect, a cell camping processing apparatus is provided, applied to a second device, and includes:

[0021] An execution module is configured to perform at least one of the following:

[0022] The execution module is configured to perform at least one of the following:

[0023] The second operation;

[0024] The second operation includes at least one of the following:

[0025] training the first AI model, obtaining the first AI model, and sending the first AI model to the first device;

[0026] training the first AI model, obtaining a second training result, and sending the second training result to the first device, the second training result being used for training the first AI model by the first device;

[0027] The first device is a terminal, a network side device, or a server, the second device is a terminal, a network side device, or a server, the first AI model is used to determine a target result, the target result is used for cell camping, and the target result includes at least one of the following: a frequency domain position of synchronization signal transmission; a time domain position of synchronization signal transmission; a beam transmission direction of synchronization signal transmission; information of a first cell, the first cell being a cell that can be camped.

[0028] In a fifth aspect, a device for cell camping processing is provided, which is configured to perform the steps of the method of the first aspect or implement the steps of the method of the second aspect.

[0029] In a sixth aspect, a terminal is provided, which includes a processor and a memory, the memory storing a program or instructions executable on the processor, and the program or instructions, when executed by the processor, implement the steps of the method of the first aspect.

[0030] In a seventh aspect, a terminal is provided, which includes a processor and a communication interface, wherein,

[0031] When the terminal is the first device, the processor is configured to obtain a target result based on a first artificial intelligence (AI) model;

[0032] The first device is a terminal, a network side device, or a server, the target result is used for cell camping, and the target result includes at least one of the following: a frequency domain position of synchronization signal transmission; a time domain position of synchronization signal transmission; a beam transmission direction of synchronization signal transmission; information of a first cell, the first cell being a cell that can be camped.

[0033] When the terminal is the second device, the communication interface is configured to perform at least one of the following:

[0034] Send at least part of the first information to the first device, the first information being used for inference of the first AI model;

[0035] The second operation includes at least one of the following:

[0036] The second operation includes at least one of the following:

[0037] training the first AI model, obtaining the first AI model, and sending the first AI model to the first device;

[0038] training the first AI model, obtaining a second training result, and sending the second training result to the first device, the second training result being used by the first device to train the first AI model;

[0039] The first device is a network-side device or a server, the first AI model is used to determine a target result, the target result is used to perform cell camping, and the target result includes at least one of the following: a frequency domain position of synchronization signal transmission; a time domain position of synchronization signal transmission; a beam transmission direction of synchronization signal transmission; information of a first cell, the first cell being a cell that can be camped.

[0040] In an eighth aspect, a network-side device is provided, which includes a processor and a memory, the memory storing programs or instructions executable on the processor, and the programs or instructions, when executed by the processor, implement the steps of the method of the first aspect.

[0041] In a ninth aspect, a network-side device is provided, which includes a processor and a communication interface, and wherein

[0042] When the network-side device is a first device, the processor is configured to obtain a target result based on a first artificial intelligence (AI) model;

[0043] The target result is used to perform cell camping, and the target result includes at least one of the following: a frequency domain position of synchronization signal transmission; a time domain position of synchronization signal transmission; a beam transmission direction of synchronization signal transmission; information of a first cell, the first cell being a cell that can be camped.

[0044] When the network-side device is a second device, the communication interface is configured to perform at least one of the following:

[0045] Send at least part of the first information to the first device, the first information being used for inference of the first AI model;

[0046] A second operation;

[0047] The second operation includes at least one of the following:

[0048] training the first AI model, obtaining the first AI model, and sending the first AI model to the first device;

[0049] training the first AI model, obtaining a second training result, and sending the second training result to the first device, the second training result being used by the first device to train the first AI model;

[0050] The first device is a terminal or a server, the first AI model is used to determine a target result, the target result is used for cell camping, and the target result includes at least one of the following: a frequency domain position of synchronization signal transmission; a time domain position of synchronization signal transmission; a beam transmission direction of synchronization signal transmission; and information of a first cell, the first cell being a cell that can be camped.

[0051] In a tenth aspect, a readable storage medium is provided, and the readable storage medium stores a program or instructions, which, when executed by a processor, implement the steps of the method according to the first aspect or implement the steps of the method according to the second aspect.

[0052] In an eleventh aspect, a wireless communication system is provided, and the wireless communication system includes a first device and a second device, the first device being configured to implement the steps of the method according to the first aspect, and the second device being configured to implement the steps of the method according to the second aspect.

[0053] In a twelfth aspect, a chip is provided, and the chip includes a processor and a communication interface, the communication interface being coupled to the processor, and the processor being configured to run a program or instructions to implement the method according to the first aspect or implement the method according to the second aspect.

[0054] In a thirteenth aspect, a computer program / program product is provided, and the computer program / program product is stored in a storage medium, and the computer program / program product is executed by at least one processor to implement the steps of the method according to the first aspect or implement the steps of the method according to the second aspect.

[0055] In the embodiments of the present application, a first device obtains a target result based on a first artificial intelligence (AI) model, the first device is a terminal, a network side device or a server, the target result is used for cell camping, and the target result includes at least one of the following: a frequency domain position of synchronization signal transmission; a time domain position of synchronization signal transmission; a beam transmission direction of synchronization signal transmission; and information of a first cell, the first cell being a cell that can be camped. In this way, the terminal can perform initial cell search and selection based on the time-frequency domain position, the beam transmission direction and the information of the first cell in the target result, thereby avoiding frequency sweeping for network search on a full frequency band supported by the terminal. Therefore, the embodiments of the present application shorten the time for initial cell search and selection, thereby reducing the time delay of cell camping of the terminal, and at the same time, reducing the energy consumption of initial cell search and selection. BRIEF DESCRIPTION OF DRAWINGS

[0056] FIG. 1 is a block diagram of a wireless communication system to which embodiments of the present application can be applied;

[0057] FIGS. 2a-2c are examples of multiplexing patterns of SSB and CORESET 0;

[0058] FIG. 3 is a schematic diagram of a neuron structure;

[0059] FIG. 4 is a flow diagram of a cell camping method according to an embodiment of the present application;

[0060] FIG. 5 is a flow diagram of another cell camping method according to an embodiment of the present application;

[0061] FIG. 6 is a schematic diagram of a cell camping apparatus according to an embodiment of the present application;

[0062] FIG. 7 is a schematic diagram of another cell camping apparatus according to an embodiment of the present application;

[0063] FIG. 8 is a schematic diagram of a communication device according to an embodiment of the present application;

[0064] FIG. 9 is a schematic diagram of a terminal according to an embodiment of the present application;

[0065] FIG. 10 is a schematic diagram of a network-side device according to an embodiment of the present application. DETAILED DESCRIPTION

[0066] The terms "first", "second", and the like in the present application are used to distinguish similar objects, and are not used to describe a particular order or sequence. It should be understood that the terms used in this way can be interchanged, so that the embodiments of the present application can be implemented in an order other than that illustrated or described here, and the objects distinguished by "first", "second" are generally of a kind, and are not limited to the number of objects, for example, the first object can be one or more. In addition, "or" in the present application means at least one of the connected objects. For example, the protection scope of "A or B" at least covers three schemes, namely, scheme one: including A and not including B; scheme two: including B and not including A; scheme three: including A and B. In addition, the terms "A and / or B", "at least one of A and B", "at least one of A or B" also at least cover the above three schemes, respectively. The character " / " generally represents that the objects before and after are in an "or" relationship.

[0067] The term "indication" in this application can be a direct indication (or explicit indication) or an indirect indication (or implicit indication). The direct indication can be understood as that the sender explicitly informs the receiver of specific information, operations to be performed or requested results, etc. in the sent indication. The indirect indication can be understood as that the receiver determines the corresponding information according to the indication sent by the sender, or judges and determines the operations to be performed or the requested results according to the judgment result.

[0068] It is worth noting that the technology described in the embodiments of the present application is not limited to the Long Term Evolution (LTE) / LTE-Advanced (LTE-A) system, but can also be used in other wireless communication systems, such as Code Division Multiple Access (CDMA), Time Division Multiple Access (TDMA), Frequency Division Multiple Access (FDMA), Orthogonal Frequency Division Multiple Access (OFDMA), Single-carrier Frequency-Division Multiple Access (SC-FDMA) or other systems. The terms "system" and "network" in the embodiments of the present application are often used interchangeably, and the described technology can be used in the above-mentioned systems and radio technologies, and also in other systems and radio technologies. The following description describes a New Radio (NR) system for example purposes, and NR terminology is used in most of the following description, but these technologies can also be applied to systems other than the NR system, such as a 6th Generation (6G) communication system. th

[0069] ​FIG. 1 shows a block diagram of a wireless communication system to which embodiments of the present application can be applied. The wireless communication system includes a terminal 11 and a network-side device 12. The terminal 11 can be a terminal-side device such as a mobile phone, a Tablet Personal Computer, a Laptop Computer, a notebook computer, a Personal Digital Assistant (PDA), a palmtop computer, a netbook, an Ultra-mobile Personal Computer (UMPC), a Mobile Internet Device (MID), an Augmented Reality (AR) device, a Virtual Reality (VR) device, a robot, a wearable device, a flight vehicle, a Vehicle User Equipment (VUE), a shipboard device, a Pedestrian User Equipment (PUE), a smart home (a home device with a wireless communication function such as a refrigerator, a television, a washing machine, or furniture), a game console, a Personal Computer (PC), a kiosk, or a self-service machine. The wearable device includes a smart watch, a smart bracelet, a smart earphone, smart glasses, smart jewelry (a smart bracelet, a smart necklace, a smart ring, a smart necklace, a smart anklet, a smart necklace, etc.), a smart wristband, smart clothes, etc. The vehicle-mounted device can also be referred to as a vehicle-mounted terminal, a vehicle-mounted controller, a vehicle-mounted module, a vehicle-mounted component, a vehicle-mounted chip, or a vehicle-mounted unit, etc. It should be noted that the specific type of the terminal 11 is not limited in the embodiments of the present application. The network-side device 12 can include an access network device or a core network device. The access network device can also be referred to as a Radio Access Network (RAN) device, a radio access network function, or a radio access network unit. The access network device can include a base station, a Wireless Local Area Network (WLAN) Access Point (AP), or a Wireless Fidelity (WiFi) node, etc.The base station can be referred to as a Node B (NB), an evolved Node B (eNB), a next generation Node B (gNB), a New Radio Node B (NR Node B), an access point, a relay station (RBS), a serving base station (SBS), a base transceiver station (BTS), a radio base station, a radio transceiver, a basic service set (BSS), an extended service set (ESS), a home Node B (HNB), a home evolved Node B, a transmit / receive point (TRP), or some other suitable terminology in the art, so long as 5 30 the base station is understood to be a base station that achieves the same technical effect, and the base station is not limited to a specific technical term. It should be noted that in the embodiments of the present application, only the base station in the NR system is taken as an example for introduction, and the specific type of the base station is not limited.

[0070] For the convenience of understanding, some contents related to the embodiments of the present application are described as follows:

[0071] 1. Cell search

[0072] The cell search is a process in which the terminal acquires time and frequency synchronization with the cell and decodes the cell identification (ID) of the cell. The main purposes of the cell search include:

[0073] 1. Acquiring frequency and symbol synchronization (downlink synchronization) with the cell.

[0074] 2. Acquiring system frame timing, i.e., the starting position of the downlink frame.

[0075] 3. Determining the physical cell identification (PCI) of the cell.

[0076] NR cell search is based on Primary Synchronization Signal (PSS) and Secondary Synchronization Signal (SSS) and Physical Broadcast Channel (PBCH) Demodulation Reference Signal (DMRS) located on the synchronization raster. The overall procedure of NR cell search can be divided into the following steps:

[0077] 1. The terminal tunes to a specific frequency and only measures the Received Signal Strength Indication (RSSI).

[0078] 2. The terminal attempts to detect SSB and decode the Primary Synchronisation Signal (PSS) and Secondary Synchronisation Signal (SSS). If the terminal fails at this step, it goes to step 1, and if it passes at this step, it goes to the next step.

[0079] 3. Once the terminal successfully detects PSS or SSS, the terminal attempts to decode PBCH.

[0080] 4. Once the terminal successfully detects PBCH, it decodes the Master Information Block (MIB).

[0081] 5. Based on pdcch-ConfigSIB1 in the MIB, find the location of Control Resource Set 0 (ORESET#0, i.e., CORESET for Physical Downlink Control Channel (PDCCH) or Downlink Control Information (DCI) for SIB1 transmission) and Search Space information.

[0082] 6. Blindly decode DCI 1_0 scrambled with System Information Radio Network Temporary Identifier (SI-RNTI) in the Search Space.

[0083] 7. Detect and decode the Physical Downlink Shared Channel (PDSCH) carrying System Information Block (SIB) 1 based on the content of DCI 1_0.

[0084] 8. Decode SIB1 and other SIBs (if SIB1 carries information about other SIBs).

[0085] A terminal not only needs to perform cell search at power on, but also needs to search for neighbor cells, acquire synchronization and estimate the received quality of the cell signal in order to decide whether to handover (when the UE is in RRC_CONNECTED state) or cell re-select (when the UE is in RRC_IDLE state) in order to support mobility.

[0086] The Synchronization Signal and PBCH block (SSB) subcarrier spacing (SCS) is determined by the frequency range: 15 or 30 kHz SCS is supported for below 6 GHz (i.e. FR1), and 120 or 240 kHz SCS is supported for above 6 GHz (i.e. FR2). The terminal learns N_ID_(2) from the PSS and N_ID_(1) from the SSS, and then the physical cell identifier (PCI) of the cell ID is:

[0087] where N_ID_(2) takes a value in the range {0, 1, 2} and N_ID_(1) takes a value in the range {0, 1, … 335}, and NR has 336 x 3 = 1008 N_cell_IDs, which take values in the range {0, 1, …, 1007}. For most frequency bands of FR1, only one SSB SCS is supported, and the terminal determines the SSB SCS at the same time as it determines the frequency band. However, some frequency bands n5 / n41 / n66 / n90 support two SSB SCSs (15 kHz and 30 kHz), and the terminal needs to perform blind detection with two SCSs to determine the SSB SCS of the cell. FR2 n257 / 258 / 259 / 260 / 261 all support 120 / 240 kHz, and in this case the terminal can only try one SCS at a time to determine the SCS.

[0088] II. Sync raster.

[0089] Channel raster can be understood as the optional location of the center frequency of the carrier. When defining the channel raster, the protocol first defines the global frequency raster. The channel raster is a range and step restriction based on the global frequency raster according to the operating band. In 5G NR, the global frequency raster is defined as a set of RF reference frequencies (FREF), and the frequency range is 0-100GHz, which is mainly used to identify the frequency domain location of the RF channel, SSB or other resources.

[0090] The NR Absolute Radio Frequency Channel Number (NR-ARFCN) encodes the frequency range of the RF reference frequency, and the value range of 0-100GHz is FR1 [0…2016666] and FR2 [2016667…3279165]. The relationship between NR-ARFCN and RF reference frequency FREF is shown in equation (1). The ARFCN frequency point number corresponds to the channel raster. The channel raster has different interval densities in different NR bands. REF = F REF-Offs + ΔF Global (N REF – N REF-Offs ) (1)

[0091] The NR-ARFCN parameters of the global frequency raster are shown in Table 1.

[0092] Table 1:

[0093] In NR, if the terminal searches for synchronization signals according to the channel raster, the time required is very long and very power-consuming because the channel bandwidth can be very large. Therefore, NR introduces the concept of synchronization raster, and the synchronization signal is placed according to the synchronization raster.

[0094] The GSCN frequency point number corresponds to the synchronization raster. GSCN defines the frequency range of 0-100GHz, and each GSCN corresponds to a detection frequency point of SSB. When performing full-band search, the terminal can only blindly detect the SSB at the GSCN position. Similarly, as shown in Table 2, 0-100GHz corresponds to 0-26639 GSCNs.

[0095] Table 2:

[0096] The default value of the operating band supporting only SCS interval channel raster is M = 3.

[0097] GSCN can be used to describe the synchronization channel of each band. The synchronization raster is a subset of GSCN, and the frequency interval of the synchronization raster of different bands is different. On the n41 band, the frequency interval of the synchronization raster is 3 GSCNs. On the n79 band, the interval of the synchronization raster is 16 GSCNs.

[0098] Three, synchronization signal block.

[0099] In NR, PSS or SSS and PBCH are always bound, so it is also called SSB. One SSB occupies a total of 4 symbols in the time domain (time indices l = 0 ~ 3), and is distributed in 240 consecutive subcarriers (20 RBs) in the frequency domain. The center frequency of the 121st subcarrier SC from bottom to top is the synchronization reference frequency (SSREF) corresponding to the GSCN of the SSB. In NR, the time domain position and the frequency domain position of the SSB are no longer fixed, but are flexible and variable. In the frequency domain, the SSB is no longer fixed in the middle of the frequency band; in the time domain, the position and the number of SSBs transmitted can vary. Therefore, in NR, only by demodulating the PSS or SSS signal, the complete synchronization of the frequency domain and the time domain resources cannot be obtained, and the demodulation of the PBCH must be completed to finally achieve the synchronization of the time-frequency resources.

[0100] Cell-defining or non cell-defining SSB.

[0101] In the NR system, the cell-defining SSB (CD-SSB) is defined as the SSB associated with SIB1 (that is, Remaining Minimum SI (RMSI)). SIB1 defines the scheduling information of other SIBs, and contains information for terminal initial access. The frequency position of the CD-SSB must be on the system synchronization raster.

[0102] The non cell-defining SSB (NCD-SSB) is correspondingly defined as the SSB not associated with SIB1. The NCD-SSB can be used for secondary cell synchronization, or can be used as a measurement signal configured for the terminal. The NCD-SSB does not necessarily locate on the system synchronization raster. If the NCD-SSB is located on the system synchronization raster, it can indicate the GSCN of the CD-SSB through the information carried thereby.

[0103] When a terminal detects an SSB during cell search, it first needs to determine whether the SSB is a CD-SSB or an NCD-SSB. This is determined based on the subcarrier offset k provided by the SSB's PBCH, which represents the subcarrier offset k between the SSB and the common resource block grid. SSB The determination is made based on whether the subcarrier offset is within the valid subcarrier offset range. The valid subcarrier offset range includes 0-23 subcarriers and 0-11 subcarriers, represented by 5 bits and 4 bits respectively, corresponding to frequency ranges FR1 and FR2. If k SSB If the value is within the effective subcarrier offset range, then the SSB is a CD-SSB; otherwise, it is an NCD-SSB.

[0104] In FR1, if k SSB >23, or in FR2, if k SSB >11 indicates that the SSB does not exist in the Type 0 Common Search Space (CSS), meaning the current SSB is not associated with SIB1. However, to help the UE find the Cell Defining SSB more quickly, these k SSB It can also be used as an index, in conjunction with the RMSIPDCCH Config (i.e., the MIB's PDCCH Config SIB1), to (indirectly) indicate the GSCN of the next SSB.

[0105] When the value k SSB =31(FR1) or k SSB When 15 (FR2) is reached, the terminal assumes that CD-SSB does not exist within a certain GSCN range.

[0106] Optionally, the SSB or synchronization signal in the embodiments of this application may also be called any module that includes at least one of a synchronization signal, a broadcast signal, a broadcast channel (PBCH), a downlink broadcast channel for other system messages, or a control channel thereof.

[0107] IV. SIB1.

[0108] Type0-PDCCH Public Search Space Collection (CSS set):

[0109] The search space set is used for monitoring SIB1 system information, corresponding to DCI scrambled with SI-RNTI in the primary cell (primary cell) in the master cell group (MCG), configured by IE: pdcch-ConfigSIB1 in signaling MIB or IE: searchSpaceZero in signaling PDCCH-ConfigCommon or IE: searchSpaceZero or searchSpaceSIB1 in signaling PDCCH-ConfigCommon.

[0110] SSB and CORESET 0:

[0111] The SSB and CORESET 0 multiplexing pattern is divided into three types: Pattern 1 (as shown in FIG. 2a) is time division multiplexing (CORESET 0 frequency range contains SSB), Pattern 2 (as shown in FIG. 2b) and Pattern 3 (as shown in FIG. 2c) are frequency division multiplexing (CORESET 0 and SSB in the same system frame). Pattern 2 and Pattern 3 differ in that: in the time domain, the CORESET 0 of Pattern 2 is slightly ahead of the SSB position.

[0112] After the terminal decodes the SSB, it can know the specific time-frequency resource position to blindly detect the scheduling information of SIB1.

[0113] After detecting PBCH, the terminal has completed downlink synchronization, and before performing uplink synchronization, the terminal needs to further receive SIB1 to obtain configuration information related to uplink synchronization.

[0114] SIB1 is transmitted in PDSCH and scheduled by PDCCH, and the resource allocation range of PDSCH is within the frequency range of the initial BWP:

[0115] (1) PDCCH time-frequency domain resource allocation of SIB1 (DCI information scheduling SIB1 is carried in CORESET 0).

[0116] The PDCCH of SIB1 is mapped in the common search space (CCS) of type 0-PDCCH;

[0117] In the frequency domain, the CSS of Type 0-PDCCH is mapped in CORESET 0, and the frequency range of CORESET 0 is exactly the same as the initial BWP;

[0118] The low 4 bits of the signaling 'pdcch-ConfigSIB1' carried in the PBCH indicate the configuration of the type 0-PDCCH CSS; the high 4 bits indicate the configuration of the CORESET 0,

[0119] (2) PDSCH time-frequency domain resource allocation of SIB1.

[0120] The conventional PDSCH uses the radio resource control (RRC) configured time domain resource allocation (TDRA) table, and the index in the table is indicated by the PDCCCH to perform time domain resource allocation. However, since the terminal has not established the RRC connection when receiving the SIB1 PDSCH, it is necessary to define the default TDRA.

[0121] The three modes of multiplexing of CORESET 0 and SSB correspond to three default TDRA tables respectively;

[0122] In the frequency domain, the SIB1 performs frequency domain resource allocation within the initial access bandwidth range, and uses resource allocation type type 1,

[0123] Five, AI.

[0124] AI can be represented as machine learning (ML), and AI has been widely applied in various fields. Integrating artificial intelligence into wireless communication networks and significantly improving technical indicators such as throughput, latency, and user capacity are important tasks for future wireless communication networks. AI modules have various implementation methods, such as neural networks, decision trees, support vector machines, and Bayesian classifiers.

[0125] Optionally, the neural network is composed of neurons, and a schematic diagram of a neuron is shown in FIG. 3, where a1, a2, … aK are inputs, w is a weight, i.e., a multiplicative coefficient, b is a bias, i.e., an additive coefficient, and σ(.) is an activation function. Common activation functions include Sigmoid, tanh, rectified linear unit (ReLU), etc. Among them, z = a1w1+···+a k w k +···+a K w K +b.

[0126] The parameters of the neural network are optimized by an optimization algorithm. The optimization algorithm is a kind of algorithm that can help us minimize or maximize the objective function, which can also be called the loss function. The objective function is often a mathematical combination of model parameters and data. For example, given data X and its corresponding label Y, we construct a neural network model f(.). With the model, we can get the predicted output f(x) according to the input x, and we can calculate the difference between the predicted value and the true value (f(x)-Y), which is the loss function. Our goal is to find the appropriate W, b to make the value of the above loss function reach the minimum, and the smaller the loss value is, the closer our model is to the true situation.

[0127] The common optimization algorithm at present is basically based on the error back propagation (BP) algorithm. The basic idea of the BP algorithm is that the learning process consists of two processes of forward propagation of signals and backward propagation of errors. When the forward propagation is performed, the input sample is transmitted from the input layer to the output layer through the processing of each hidden layer. If the actual output of the output layer does not match the expected output, the backward propagation of errors is performed. The error back propagation is to transmit the output error to the input layer through the hidden layer in a certain form, and allocate the error to all units of each layer, so as to obtain the error signal of each unit, which is used as the basis for correcting the weights of each unit. The process of adjusting the weights of each layer through the forward propagation of signals and the backward propagation of errors is repeated. The process of continuously adjusting the weights is the learning and training process of the network. This process continues until the error of the network output is reduced to an acceptable level, or until the preset number of learning times is reached.

[0128] The common optimization algorithm includes gradient descent, stochastic gradient descent (SGD), mini-batch gradient descent, momentum method, Nesterov with momentum, adaptive gradient descent (Adagrad), Adadelta, root mean square prop (RMSprop), and adaptive moment estimation (Adam), etc.

[0129] These optimization algorithms, when the error back propagation is performed, are based on the error or loss obtained from the loss function, and the derivative or partial derivative of the current neuron is added to the learning rate, the previous gradient, the derivative or partial derivative, etc. to obtain the gradient, and the gradient is transmitted to the previous layer.

[0130] Generally speaking, according to the solution type, the selected AI algorithm and the adopted AI model also have some differences. According to the currently published articles and public research results, the main method to improve the performance of 5G network by means of AI is to enhance or replace the existing algorithms or processing modules by means of neural network-based algorithms and AI models. In a specific scenario, neural network-based algorithms and AI models can achieve better performance than deterministic algorithms. Commonly used neural networks include deep neural networks, convolutional neural networks, and recurrent neural networks, etc. With the help of existing AI tools, the construction, training and verification of neural networks can be realized.

[0131] Optionally, in practice, it is difficult to achieve convergence by directly training the neural network due to insufficient real-time collected data sets. The common practice is to pre-train the network based on a large amount of offline collected data to make it converge. Then, fine-tune the pre-trained neural network parameters with real-time collected data to adapt the neural network to the actual environment. Fine-tuning can be considered as a training process using pre-trained neural network parameters as initialization. In the fine-tuning stage, the parameters of some layers can be frozen, generally the layers close to the input end are frozen and the layers close to the output end are activated, so that the network can still converge. The less the data volume in the fine-tuning stage, the more layers are recommended to be frozen, only a small number of layers close to the output end are fine-tuned.

[0132] Optionally, the generalization of neural network refers to that the neural network can obtain reasonable output for data not encountered in the training (learning) process. To solve the generalization problem caused by the variable wireless transmission environment, there are two solutions for the neural network-based wireless communication system. The first solution is to train different neural networks under different transmission conditions to obtain multiple sets of neural network parameters, and switch the neural network parameters as the actual environment changes. The second solution is to train a common neural network based on mixed data, and the neural network parameters do not need to be switched with the change of the environment. These two modes have their own advantages and disadvantages: the first solution performs well under different transmission conditions, but it needs to store multiple network parameters and switch them as needed (which causes signaling overhead, frequent switching, etc.); the second solution only needs to store a set of neural network parameters and does not need to switch, but it cannot achieve optimal performance under each transmission condition. The construction method of mixed data set will affect the performance of the second solution.

[0133] Optionally, in machine learning and deep learning, label generally refers to the identification or annotation of the true class or target value of a data sample. The label is used to represent the information that the model should learn and predict, for example:

[0134] Labels in classification tasks: In classification tasks, labels represent which class a data sample belongs to. For example, in image classification, each image sample has a label indicating the class of object or scene contained in the image, such as "dog" or "cat".

[0135] Labels in object detection: In object detection tasks, labels usually include both location information (bounding boxes) and class information of objects. Each label identifies a target object in an image, including its location and class. Labels in regression tasks:

[0136] In regression tasks, labels usually represent continuous or real-valued targets to be predicted. For example, the label in a house price prediction task can be the actual sale price of a house.

[0137] Labels in sequence labeling: In natural language processing, labels in sequence labeling tasks are usually used in tasks such as part-of-speech tagging and named entity recognition, where labels are used to represent the properties or categories of each word or character in a text sequence.

[0138] Labels are a key component in supervised learning tasks, used to train machine learning models. Models learn patterns and rules by comparing with real labels in order to make predictions or classifications on unseen data. The quality and accuracy of labels are crucial for the performance of the model.

[0139] Six, life cycle management (LCM) of AI.

[0140] The life cycle management of AI models includes multiple AI function modules: model training module, model management module, model inference module, model monitoring module, model updating module.

[0141] The model training module is used to perform AI model training, validation and testing, and can generate model performance indicators that can be used as part of the model testing process. If necessary, this function is also responsible for data preparation (such as data preprocessing and cleaning, formatting and conversion) based on the training data provided by the data collection function.

[0142] The model management module is used to supervise the operation of AI models or AI functions (such as model selection, (de)activation, switching or fallback), and feedback model monitoring performance. This module is also responsible for making decisions based on data received from the data collection module and the model inference module to ensure correct inference operations.

[0143] Optionally, the following instructions or requests can be included:

[0144] Management instructions: information input by the model management module to the model inference module. Relevant information can include AI model or AI-based function to select, (de)activate or switch models, fallback to non-AI operation (i.e. not dependent on inference process), etc.

[0145] Model transmission request: used to request a model from the model storage function;

[0146] Performance feedback or retraining request: information required by the model training module, e.g. for model (re)training or updating purposes.

[0147] Model inference module, used to provide output applying AI model using data provided by the data collection function as input (i.e. inference data). If needed, the model inference module is also responsible for data preparation (e.g. data pre-processing and cleaning, formatting and conversion) based on inference data provided by the data collection function.

[0148] Optionally, inference output: data used by the model management module to monitor AI model or AI function performance.

[0149] In this application, the AI model can be referred to as AI unit, machine learning (ML) model, ML unit, AI structure, AI function, AI feature, neural network, neural network function, neural network function, etc., or the AI model can refer to a processing unit capable of implementing specific algorithms, formulas, processing flows, capabilities, etc. related to AI, or the AI model can be a processing method, algorithm, function, module or unit for a specific data set, or the AI model can be a processing method, algorithm, function, module or unit running on AI or ML related hardware such as Graphics Processing Unit (GPU), Neural Processing Unit (NPU), Tensor Processing Unit (TPU), Application Specific Integrated Circuit (ASIC), etc. No further limitation is made here.

[0150] It should be noted that after the terminal is powered on, the terminal usually reads the SIM card information first, and then searches for a suitable cell for camping according to the prior information (such as previously stored cell and frequency point information) stored in the SIM card. However, in some cases, such as when you switch the terminal to the flight mode and then fly to another country, and then switch back to the normal mode in the other country, the prior information stored in the terminal may be outdated. After the terminal is powered on, the terminal cannot find a suitable cell to access using the previously stored prior information, and the terminal will perform initial cell selection by scanning the frequency bands supported by the SIM card. This process takes a long time and consumes a lot of energy. In addition, the network deployed by the operator in different geographical locations may have different GSCNs. The operator may also temporarily deploy a new network in special places or during festivals, such as in places where large sports meetings or concerts are held, or in places where people gather during the New Year. These temporarily deployed networks may have different GSCNs. How to quickly perform initial cell search and selection when the terminal is powered on at any time and in any place, reduce the initial search time, and save terminal energy. Therefore, the present application provides a cell camping processing method.

[0151] The cell camping processing method provided by the embodiments of the present application will be described in detail in combination with the accompanying drawings and some embodiments and application scenarios.

[0152] Referring to FIG. 4, the present application provides a cell camping processing method, as shown in FIG. 4. The cell camping processing method provided by the embodiments of the present application includes:

[0153] Step 401, a first device obtains a target result based on a first artificial intelligence (AI) model;

[0154] The first device is a terminal, a network side device or a server, the target result is used for cell camping, and the target result includes at least one of the following: a frequency domain position of a synchronization signal transmission; a time domain position of the synchronization signal transmission; a beam transmission direction of the synchronization signal transmission; information of a first cell, the first cell being a cell that can be camped.

[0155] In the embodiments of the present application, the target result can be understood or replaced as an inference result of the first AI model, or the target result is determined based on the inference result of the first AI model, for example, the output result of the first AI model includes whether to camp on a certain cell, so that the information of the first cell is determined based on the output result. Since the target result is obtained by the first AI model, and then the search and selection of the cell are performed based on the first AI result to realize the cell camping of the terminal, the full frequency band supported by the SIM card can be avoided for cell search, and therefore the time delay of the terminal for cell camping is reduced.

[0156] Optionally, the information of the first cell can comprise a PCI. The first cell can be understood as a candidate cell.

[0157] Optionally, in some embodiments, when the target result comprises at least one of a frequency domain position of a synchronization signal transmission, a time domain position of the synchronization signal transmission, and a beam transmission direction of the synchronization signal transmission, the cell search can be performed based on the target result, so that the cell search does not need to be performed in the full frequency band supported by the SIM card.

[0158] Optionally, in some embodiments, when the target result comprises information of a first cell, the terminal can directly select the first cell for camping or only perform the cell search in the first cell, so as to save the time for the cell search.

[0159] Optionally, the beam transmission direction of the synchronization signal transmission can be understood or replaced by the strongest beam transmission direction of the synchronization signal transmission.

[0160] Embodiments of the present application obtain a target result by a first device based on a first artificial intelligence (AI) model. The first device is a terminal, a network side device or a server. The target result is used for cell camping, and the target result comprises at least one of a frequency domain position of a synchronization signal transmission, a time domain position of the synchronization signal transmission, a beam transmission direction of the synchronization signal transmission, and information of a first cell. The first cell is a cell that can be camped. In this way, the terminal can perform initial cell search and selection based on the time-frequency domain position, the beam transmission direction and the information of the first cell in the target result, so as to avoid frequency sweeping and network searching in the full frequency band supported by the terminal. Therefore, embodiments of the present application shorten the time for initial cell search and selection, thereby reducing the time delay of the terminal for cell camping, and at the same time, reducing the energy consumption of initial cell search and selection.

[0161] Optionally, in some embodiments, the first device obtains the target result based on the first AI model comprises:

[0162] The first device inputs first information into the first AI model to obtain the target result.

[0163] The first information comprises at least one of:

[0164] time information;

[0165] state information of the terminal, the state information comprising at least one of position information, moving direction, moving speed, energy consumption status, power status, environment information, perception information, network scenario information, operator information and network type;

[0166] a number of times of synchronization signal detection failure in a first preset time period;

[0167] a burst event;

[0168] mode information of the synchronization signal;

[0169] frequency domain feature of the synchronization signal;

[0170] time domain feature of the synchronization signal;

[0171] spatial domain feature of the synchronization signal.

[0172] In the embodiments of the present application, the time information can be specific to a certain time point, for example, 13:25:38. It can also be a time range, such as 13:00-14:00, morning or afternoon, day or night.

[0173] Optionally, the time information can be obtained through other radio access technologies (RATs), which can be Bluetooth, Wi-Fi, 3G, 4G, or LTE, etc.

[0174] Optionally, the location information can be specific location coordinates, such as GPS coordinates; or general range information of the terminal, such as range information of which street, which country, etc.; or location information of the terminal relative to the camping cell or the access cell, such as the east direction of the camping cell.

[0175] The moving direction of the terminal can be an absolute direction, such as 40 degrees east-south; or a relative direction, such as relative to the camping cell or the access cell.

[0176] The environment information can include weather information, etc.

[0177] Optionally, the network scenario information can include indoor hotspots (inH), urban macrocells (Uma), rural macrocells (RMa), etc., or include homogeneous networks or heterogeneous networks, i.e., with or without overlapping coverage.

[0178] Optionally, the frequency domain feature can include at least one of the following:

[0179] sync raster or GSCN frequency point positions where the synchronization signal can potentially exist, such as frequency domain positions defined in the protocol where the synchronization signal can potentially exist;

[0180] frequency domain resource blocks (RBs) or the number of subcarriers of the synchronization signal.

[0181] Optionally, the time domain feature can include a number of time domain symbols of the synchronization signal, or can include a time window length of time domain correlation detection of the synchronization signal.

[0182] Optionally, the network type can include a terrestrial network (TN), a non-terrestrial network (NTN), a cell-free network, and the like.

[0183] Optionally, the emergency event includes, but is not limited to, a concert and an earthquake, and the like.

[0184] Optionally, the inference of the first AI model can be performed at a network side device, or can be performed at a terminal, or can be performed at a server. For example, in some embodiments, when the first device is a network side device or a server, the method further includes:

[0185] The first device sends the target result to the terminal.

[0186] In the embodiments of the present application, when the terminal does not have the AI model inference function, the model inference can be performed by the network side device or the server, so that the requirements on the terminal can be reduced, and the application range of AI-based cell search and selection using the AI model can be improved.

[0187] Optionally, in some embodiments, the method further includes:

[0188] When the first device is a terminal, the first device activates the first AI model based on a first activation condition, and the first activation condition includes at least one of the following: the terminal is powered on; an initial cell search operation is performed; an initial cell selection operation is performed; an initial search is performed in a full frequency band supported by the terminal for a first preset time length; the terminal does not camp on a second cell within a second preset time period; a cell reselection operation is performed; a cell handover operation is performed; a timer for activating the first AI model is timed out; a number of synchronization signal block (SSB) detection failures is greater than or equal to a first threshold; and it is determined that the first AI model needs to be activated based on at least one of second information, the second information being at least part of the input information of the first AI model.

[0189] Alternatively, when the first device is a network side device or a server, the first device activates the first AI model based on a second activation condition, and the second activation condition includes at least one of the following:

[0190] receive target indication information from the terminal, the target indication information being used to indicate at least one of the following: the terminal is powered on; an initial cell search operation is performed; an initial cell selection operation is performed; an initial search is performed in a manner of performing cell search in a full frequency band supported by the terminal for a first preset time length; the terminal does not camp on a second cell within a second preset time period; a cell reselection operation is performed; a cell handover operation is performed; a number of synchronization signal block (SSB) detection failures is greater than or equal to a first threshold; and it is determined, based on at least one of second information, that the first AI model needs to be activated, the second information being at least part of input information of the first AI model;

[0191] the timer for activating the first AI model expires;

[0192] it is determined, based on at least one of third information, that the first AI model needs to be activated, the third information being at least part of input information of the first AI model.

[0193] In the embodiments of the present application, triggering the activation of the first AI model can be understood or replaced as using the first AI model to perform AI-based cell search and selection. For example, the activation of the first AI model can be triggered when the terminal is powered on, that is, the first AI model is used to perform AI-based cell search and selection when the terminal is powered on. For another example, the activation of the first AI model can be triggered when an initial cell search operation is performed, that is, the first AI model is used to perform AI-based cell search and selection when the initial cell search operation is performed.

[0194] It should be understood that when the terminal is an inference device of the first AI model, the terminal can activate the first AI model when the first activation condition is met, and when the terminal is not an inference device of the first AI model, the terminal can send the above target indication information to a network side device or a server to indicate the network side device or the server to activate the first AI model when the first activation condition is met.

[0195] Optionally, the activation of the first AI model can be triggered when an initial cell selection operation is performed.

[0196] Optionally, the activation of the first AI model can be triggered when an initial search is performed in a manner of performing cell search in a full frequency band supported by the terminal for a first preset time length.

[0197] Optionally, the activation of the first AI model can be triggered after the terminal does not camp on a second cell within a second preset time period. The second cell can be understood or replaced as a new cell or a newly camped cell, that is, a cell other than the last camped cell. That is, the activation of the first AI model is triggered when the terminal fails to successfully camp on a new cell for more than the second preset time period.

[0198] Optionally, the first AI model activation can be triggered when a cell reselection operation is performed.

[0199] Optionally, the first AI model activation can be triggered when a cell switching operation is performed.

[0200] Optionally, the first AI model activation can be triggered when the SSB detection fails more than a certain number of times.

[0201] Optionally, at least one of the second information and the third information can be the first information or a subset of the first information. Wherein, determining that the first AI model needs to be activated based on at least one of the second information can be understood as that at least one of the second information indicates that the first AI model needs to be activated. For example, the eighth information includes the number of synchronization signal detection failures within a certain time, and when the number exceeds a certain threshold, it indicates that the range of synchronization signal detection may be too large, at which time the possible synchronization signal resource position needs to be predicted, and the first AI model is activated to use the first AI model for AI-based cell search and selection.

[0202] Optionally, in some embodiments, when the first device is a terminal, the method further comprises at least one of:

[0203] The first device updates the first AI model based on fourth information, or the first device sends fourth information to a second device, the fourth information being used to update the first AI model, wherein the fourth information includes at least one of the target result and the state information of the terminal;

[0204] The first device performs a first operation;

[0205] Wherein, the first operation includes at least one of the following: fallback to a way of performing cell search in a full frequency band supported by the terminal; trigger AI model switching; trigger retraining of the first AI model; trigger supervision of the first AI model.

[0206] In the embodiments of the present application, when the first device supports updating the first AI model (for example, the first device is a node trained by the first AI model), the first device can update the first AI model based on the fourth information. Updating the first AI model can be understood or replaced as fine-tuning the first AI model. When the first device does not support updating the first AI model, the first device can send the fourth information to the second device, and the second device updates the first AI model, and then the first device obtains the updated first AI model from the second device.

[0207] Optionally, AI model switching can include changing input information or changing AI algorithms.

[0208] Optionally, in some embodiments, the first device performing the first operation can be triggered periodically, or conditionally, or autonomously by the first device. For example, in some embodiments, the first device performing the first operation comprises:

[0209] performing the first operation by the first device in a case where the first condition is met;

[0210] wherein the first condition comprises at least one of:

[0211] a time length for inference using the first AI model exceeds a second preset time length;

[0212] a suitable cell for camping is not found using the first AI model;

[0213] inference using the first AI model is not successfully completed.

[0214] Optionally, in some embodiments, the first AI model satisfies at least one of:

[0215] a complexity of the AI model is less than or equal to a second threshold;

[0216] an inference time delay of the AI model is less than or equal to a third preset time length;

[0217] an inference success rate of the AI model is greater than or equal to a third threshold;

[0218] a reliability of an inference result of the AI model is greater than or equal to a fourth threshold.

[0219] In embodiments of the present application, different AI model complexity index requirements can be defined for different types or different capabilities of base stations or terminals, such as for ordinary terminals, the complexity of the AI model used cannot exceed a specific value.

[0220] Optionally, the inference time delay of the AI model being less than or equal to the third preset time length can be understood as the time length for inferring the time-frequency position or beam direction of the synchronization signal transmission, or inferring the first cell that can be camped, using the first AI model cannot exceed the third preset time length.

[0221] Optionally, the inference success rate of the AI model being greater than or equal to the third threshold can be understood as the success rate for inferring the time-frequency position or beam direction of the synchronization signal transmission, or inferring the first cell that can be camped, using the first AI model cannot exceed the third preset time length.

[0222] Optionally, the reliability of the inference result of the AI model is greater than or equal to a fourth threshold value, where the reliability can be understood as signal strength information such as RSRP, RSRQ or RSSI of a successfully camped cell, where the requirements of RSRP and the like here are different from the RSRP index requirements in the S criterion. For example, the measured signal strength information is greater than or equal to or less than or equal to a certain value.

[0223] Optionally, in some embodiments, the first AI model is obtained by independent training of the terminal, a network side device or a server, or the first AI model is obtained by joint training of at least two of the terminal, the network side device and the server. Wherein, the network side device can include at least one of a base station and a core network device (such as a core network device specially used for model training). Optionally, the network side device can be a base station or a network side device associated with the cell where the terminal last camped or accessed. Or the network side device is the base station or network side device associated with the cell that sends the RRC release message.

[0224] Optionally, the scenario in which the first AI model is obtained by joint training of at least two of the terminal, the network side device and the server can include at least one of the following:

[0225] The terminal reports the output of model training to the network side device or the server, and the network side device or the server takes the terminal reported information (i.e. the output of the terminal model training) as one of the input contents of its own model training, and performs model training.

[0226] The network side device sends the output of model training to the terminal or the server, and the terminal or the server takes the information sent by the network side device (i.e. the output of the network side device model training) as one of the input contents of its own model training, and performs model training.

[0227] At least one of the terminal, the network side device and the server performs offline model training, and then the terminal, the network side device and the server fine-tune in the actual network.

[0228] Optionally, when the terminal performs at least part of the model training, at least part of the input information of the model training is sent by the network side device to the terminal, and the signal or signaling of the at least part of the input information includes at least one of the following: MAC CE; RRC message; NAS message; user plane data; DCI information; system information block SIB; Layer 1 signaling of physical downlink control channel PDCCH; information of physical downlink shared channel PDSCH; MSG 2 information; MSG 4 information; MSG B information.

[0229] Optionally, the at least part of the input information for the model training is sent by the terminal to the network-side device, and the signal or signaling for sending the at least part of the input information includes at least one of the following: a MAC CE; an RRC message; a NAS message; user plane data; MSG 1 information; MSG A information; MSG 3 information; information of a physical uplink control channel (PUCCH); information of a physical uplink shared channel (PUSCH); information of a physical random access channel (PRACH); an SRS or other uplink reference signal such as a WUS.

[0230] Optionally, the at least part of the input information for the model training is sent by the terminal or the network-side device to the server, and the at least part of the input information can be indicated by an over the top (OTT) message. The OTT message can be a message provided by a third-party service provider or a third-party server or the Internet, etc.

[0231] Optionally, in some embodiments, the input information for the model training can be obtained in the following manner: the input information for the model training is reported (e.g., sent by the terminal to the network-side device) or delivered (e.g., sent by the network-side device to the terminal) at least once after the terminal camps on a cell, or initially selects a cell, or reselects a cell, or performs RRC connected state or enters an inactive state for a period of time.

[0232] Optionally, the reporting or delivery of the input information for the model training at least once can be periodic or semi-static. The period of time can be a fixed time length configured by the network-side device.

[0233] Optionally, if the first AI model is finally trained at the network-side device or the server, after the training of the first AI model is completed, the network-side device or the server can send the trained first AI model to the terminal, so that the terminal completes the inference of the AI model, thereby reducing the subsequent signaling interaction and reducing the latency of cell search and selection of the terminal. Alternatively, the model inference is performed at the network-side device or the server, and the target result obtained by the inference is sent to the terminal, which can reduce the demand for terminal capability.

[0234] Optionally, in some embodiments, before the first device receives the first AI model from the second device, the method further includes:

[0235] The first device sends fifth information to the second device, and the fifth information is used for the second device to train the first AI model;

[0236] The fifth information includes at least one of the following:

[0237] time information;

[0238] state information of the terminal, the state information comprising at least one of the following: location information, moving direction, moving speed, energy consumption status, power status, environment information, perception information, network scenario information, operator information, and network type;

[0239] a number of times of synchronization signal detection failures within a first preset time period;

[0240] an event;

[0241] mode information of the synchronization signal;

[0242] a frequency domain feature of the synchronization signal;

[0243] a time domain feature of the synchronization signal;

[0244] a space domain feature of the synchronization signal.

[0245] In the embodiments of the present application, the first device can be a terminal or a network side device, the fifth information is sent by the terminal to the network side device or a server, or the fifth information is sent by the network side device to the terminal or the server, so as to train the first AI model, and after the second device completes the training of the first AI model, the trained first AI model is sent to the first device, and the first device performs inference based on the first AI model to obtain a target result.

[0246] Optionally, in some embodiments, the trigger condition for the first device to send the fifth information to the second device can comprise at least one of the following:

[0247] the terminal camping on a cell;

[0248] the terminal initially selecting a cell;

[0249] the terminal reselecting a cell;

[0250] the terminal entering an RRC connected state;

[0251] a duration of the terminal entering an inactive state reaching a preset duration.

[0252] Optionally, in some embodiments, the method further comprises:

[0253] the first device receiving the first AI model from the second device;

[0254] The second device is a terminal, a network side device, or a server.

[0255] In the embodiments of the present application, the first device can be only an inference device of the first AI model, and further can be a device for joint training of the first AI model.

[0256] Optionally, in some embodiments, before the first device receives the first AI model from the second device, the method further includes:

[0257] The first device inputs the sixth information into the second AI model to obtain a first training result, and the first training result is used for the second device to train the first AI model.

[0258] The first device sends the first training result to the second device.

[0259] The sixth information includes at least one of the following:

[0260] Time information;

[0261] State information of the terminal, the state information including at least one of the following: position information, moving direction, moving speed, energy consumption condition, power condition, environment information, perception information, network scenario information, operator information and network type;

[0262] Number of times of synchronization signal detection failure in a first preset time period;

[0263] Sudden event;

[0264] Mode information of the synchronization signal;

[0265] Frequency domain feature of the synchronization signal;

[0266] Time domain feature of the synchronization signal;

[0267] Space domain feature of the synchronization signal.

[0268] In the embodiments of the present application, the first device and the second device perform joint training of the first AI model, and finally complete training of the first AI model at the second device. After the second device completes training of the first AI model, the second device can send the trained first AI model to the first device, and the first device performs inference based on the first AI model to obtain a target result.

[0269] Optionally, in some embodiments, the trigger condition for obtaining the sixth information can include at least one of the following:

[0270] The terminal camps on a cell;

[0271] The terminal initially selects a cell;

[0272] The terminal reselects a cell;

[0273] The terminal enters an RRC connected state;

[0274] The terminal enters an inactive state for a duration reaching a preset duration.

[0275] Optionally, in some embodiments, the method further comprises:

[0276] In a case where the first device is the server, the first device acquires the sixth information from at least one of the terminal and a network-side device;

[0277] Or, in a case where the first device is the network-side device, the first device acquires at least part of the sixth information from the terminal;

[0278] Or, in a case where the first device is the terminal, the first device acquires at least part of the sixth information from the network-side device.

[0279] Optionally, in some embodiments, the method further comprises any one of the following:

[0280] The first device trains the first AI model based on seventh information to obtain the first AI model;

[0281] The first device inputs a second training result received from a second device into a third AI model for AI training to obtain the first AI model;

[0282] The seventh information comprises at least one of the following:

[0283] Time information;

[0284] State information of the terminal, the state information comprising at least one of the following: position information, moving direction, moving speed, energy consumption condition, power condition, environment information, perception information, network scenario information, operator information and network type;

[0285] Number of times of synchronization signal detection failure within a first preset time period;

[0286] Sudden event;

[0287] Mode information of the synchronization signal;

[0288] Frequency domain feature of the synchronization signal;

[0289] Time domain feature of the synchronization signal;

[0290] Space domain feature of the synchronization signal.

[0291] In the embodiments of the present application, the first device can be an inference device of the first AI model or a training device of the first AI model. Specifically, when the first AI model is independently trained by the first device, the seventh information can be input to the AI model to be trained for training, and the first AI model is obtained. When the first AI model is jointly trained by the first device and the second device, the first device can receive the second training result from the second device, and the second training result is used as one of the inputs of the third AI model for model training, and the first AI model is obtained.

[0292] It should be noted that the input information for training the first AI model (such as the fifth information, the sixth information or the seventh information described above) can be the input information corresponding to the last N times of successful cell camping of the terminal, or the input information corresponding to the last N times of detecting a synchronization signal (such as CD-SSB).

[0293] Further, the input information for inference of the first AI model (such as the first information or the second information) can be the input information for training of the first AI model, or a subset of the input information for training of the first AI model.

[0294] Optionally, in some embodiments, the input of the training of the first AI model further includes a target label, and the target label includes at least one of the following:

[0295] Whether the terminal detects a synchronization signal;

[0296] A time length during which the terminal detects a synchronization signal;

[0297] A frequency domain position of the synchronization signal detected by the terminal;

[0298] A time domain position of the synchronization signal detected by the terminal;

[0299] A beam direction of the synchronization signal detected by the terminal;

[0300] The terminal detects a synchronization signal at a preset frequency domain position;

[0301] The terminal detects a synchronization signal at a preset time domain position;

[0302] The terminal detects a synchronization signal at a preset beam direction;

[0303] A signal quality of a camped cell measured by the terminal;

[0304] An identity of a cell successfully camped by the terminal;

[0305] A tracking area in which a cell successfully camped by the terminal is located;

[0306] The terminal successfully camps;

[0307] The terminal successfully camps on the preset cell;

[0308] A time length from a first time to a second time, the first time being a time of initiating a cell search or a time of activating the first AI model, and the second time being a time of successful camping of the terminal.

[0309] Optionally, the signal quality can include at least one of the following: RSSI, PSS or SSS detection signal strength, channel estimation SNR, SSB-RSRP, L1 RSRP and L3 RSRP.

[0310] Optionally, the signal quality of the camped cell measured by the terminal can include at least one of the following:

[0311] The terminal measures the signal quality of the camped cell at a preset frequency domain position;

[0312] The terminal measures the signal quality of the camped cell at a preset time domain position;

[0313] The terminal measures the signal quality of the camped cell at a preset beam direction.

[0314] Optionally, in some embodiments, before the first device obtains the target result based on the first artificial intelligence (AI) model, the method further includes:

[0315] The first device triggers training of the first AI model based on first configuration information periodically;

[0316] The first configuration information includes at least one of the following: a starting point of periodic model training; an interval of periodic model training; a number of model training in a period; a model training time length in a period.

[0317] Optionally, in some embodiments, before the first device obtains the target result based on the first artificial intelligence (AI) model, the method further includes:

[0318] The first device triggers training of the first AI model based on a semi-static triggering manner;

[0319] The semi-static triggering manner includes at least one of the following:

[0320] Semi-static triggering based on second configuration information;

[0321] Activation or deactivation of semi-static training of the model through physical control information;

[0322] The second configuration information satisfies at least one of the following: at least one of transmission and activation of the second configuration information is triggered based on a target event; the second configuration information is configured through radio resource control (RRC).

[0323] Optionally, in some embodiments, before the first device obtains the target result based on a first artificial intelligence (AI) model, the method further includes:

[0324] The first device triggers training of the first AI model based on a target event;

[0325] The target event includes at least one of:

[0326] A transmission frequency point of a last cell-defined synchronization signal block (CD-SSB) changes;

[0327] A transmission frequency point of a last non-cell-defined synchronization signal block (NCD-SSB) changes;

[0328] The terminal moves to a cell edge or a preset location;

[0329] The terminal moves at a speed higher than or equal to a first threshold;

[0330] The terminal moves at a speed lower than or equal to a second threshold;

[0331] A number of terminals currently accessing or camping on the cell is higher than or equal to a third threshold;

[0332] A number of terminals currently accessing or camping on the cell is lower than or equal to a fourth threshold;

[0333] Inference using the first AI model fails;

[0334] A number of consecutive inference failures using the first AI model reaches a fifth threshold;

[0335] A number of inference failures using the first AI model reaches a sixth threshold;

[0336] Inference is performed using the first AI model;

[0337] The terminal reselects to a second cell;

[0338] A tracking area of the terminal changes;

[0339] An external environment of the terminal changes;

[0340] The terminal moves to a second cell;

[0341] The terminal moves to a new tracking area;

[0342] The terminal moves to a new geographic location;

[0343] A change in the speed of the terminal is greater than or equal to a seventh threshold;

[0344] a RSRP measurement value of the terminal changes;

[0345] a time since a last training reaches a fourth preset duration;

[0346] a timer for triggering retraining expires;

[0347] M consecutive model supervisions occur, M being an integer greater than 1;

[0348] L model supervisions occur, L being a positive integer;

[0349] a number of detection failures of a synchronization signal block reaches an eighth threshold.

[0350] In the embodiments of the application, the training of the first AI model can be understood as initial training or retraining of the first AI model. The target event can be understood or replaced as a target condition.

[0351] Optionally, the change in the external environment can be understood as an environment determined by obtaining change information of the environment through a sensor of the terminal. For example, it can include but is not limited to the following environmental changes: being in a city or a rural area, being indoors or outdoors, being in a high-speed motion environment or a low-speed motion environment, etc.

[0352] Optionally, the terminal moving to a second cell can be understood or replaced as: the terminal moving to a new cell, or the terminal moving to a cell other than the last accessed serving cell.

[0353] Optionally, the terminal moving to a new tracking area can be understood as: the terminal moving to a tracking area other than the last accessed serving cell.

[0354] Optionally, the terminal moving to a new geographic location can be understood as: the terminal moving to a geographic location other than the last accessed serving cell. For example, the terminal is powered off in A, and then powered on in B. At this time, it can be considered that the terminal moves to a new geographic location, B is a new geographic location, and A and B can be different cities, or different provinces, or different countries.

[0355] Optionally, the change in the moving speed of the terminal being greater than or equal to a seventh threshold can be understood as: the terminal moving speed changes significantly in a short time, for example, from 250 kM / h to 3 km / H, or from 3 km / H to 250 kM / h.

[0356] Optionally, in some embodiments, the method further comprises:

[0357] The first device determines that the training of the first AI model is completed based on the eighth information.

[0358] The eighth information includes at least one of the following: a received signal strength indication of the synchronization signal; a signal strength of the detected primary synchronization signal or secondary synchronization signal; a channel estimation signal-to-noise ratio of the synchronization signal; a reference signal received power (RSRP) of the synchronization signal block; a layer 1 RSRP; a layer 3 RSRP; a probability of successful detection of the synchronization signal by the terminal; a time length of detection of the synchronization signal by the terminal; a probability of successful camping by the terminal; and a probability of successful synchronization by the terminal.

[0359] In the embodiments of the present application, the first AI model training can be determined to be completed when part of the eighth information is greater than or equal to a corresponding preset threshold, and the first AI model training can also be determined to be completed when part of the eighth information is less than or equal to a corresponding preset threshold.

[0360] For example, the first AI model training is determined to be completed when the probability of successful detection of the synchronization signal by the terminal is greater than or equal to X%, X being a specific threshold value. Further, the probability of successful detection of the synchronization signal by the terminal being greater than or equal to X% can be understood or replaced as the probability of successful detection of the synchronization signal by the terminal in at least one of a specific frequency domain position, a specific time domain position, and a specific beam direction being greater than or equal to X%.

[0361] For another example, the first AI model training is determined to be completed when the time length of detection of the synchronization signal by the terminal is less than or equal to M, M being a specific threshold value. Further, the time length of detection of the synchronization signal by the terminal being less than or equal to M can be understood or replaced as the time length of detection of the synchronization signal by the terminal in at least one of a specific frequency domain position, a specific time domain position, and a specific beam direction being less than or equal to M.

[0362] Optionally, in some embodiments, the eighth information described above further includes at least one of the following:

[0363] a loss function;

[0364] a number of iterations of model training;

[0365] a number of iterations of model training fine-tuning.

[0366] In the embodiments of the present application, the first AI model training is determined to be completed when the loss function meets a predefined requirement index or value, for example, the error of training is less than a predefined threshold value. The loss function can include at least one of the following:

[0367] a mean squared error or normalized mean squared error of a predicted value and an actual value;

[0368] a mean absolute error of a predicted value and an actual value.

[0369] Optionally, if the terminal performs model training, the type of the terminal needs to be considered, and different types of terminals can have different AI model training capabilities.

[0370] For different types of terminals, the input or label information for model training is different. For example, the input information for model training of a terminal device with weak capability should be less.

[0371] For different types of terminals, the execution mode of model training is different. For example, for a terminal device with weak capability, model training can be performed only on the network side, or the terminal side only performs a small part of joint model training (for example, model training involving user privacy data can be performed on the terminal side)

[0372] For different types of terminals, the artificial intelligence model used for model training is different. For example, a terminal device with weak capability may not be able to apply a too complex artificial intelligence model.

[0373] Optionally, in some embodiments, the method further comprises:

[0374] The first device supervises the first AI model based on third configuration information;

[0375] The third configuration information comprises at least one of the following:

[0376] AI model identification that needs to be supervised;

[0377] Model supervision period;

[0378] Model supervision duration;

[0379] Model supervision detection window related information;

[0380] Model supervision trigger condition;

[0381] Model supervision index;

[0382] The model supervision index comprises at least one of the following: error type information or accuracy information between predicted value and true value; communication system performance; model related information of the first AI model.

[0383] In the embodiments of the present application, when the inference environment and the training environment differ greatly, the performance of AI-based cell search will become very poor, that is, mismatch will occur. Therefore, the actual inference performance of the AI-based cell search needs to be supervised, and the corresponding adjustment operation is triggered according to the supervision result.

[0384] Optionally, the AI model identification can be understood or replaced by at least one of the following:

[0385] AI structure identification;

[0386] an AI algorithm identifier;

[0387] an AI model associated specific dataset identifier;

[0388] an AI related specific scenario, environment, channel characteristic, device identifier;

[0389] an AI related function, feature, capability or module identifier,

[0390] Optionally, the detection window related information comprises at least one of: a time length of the detection window and a number of samples for detection.

[0391] Optionally, the error related information can comprise but is not limited to at least one of: mean error, mean square error, normalized mean square error, mean absolute error, Cross-entropy loss, and Root Mean Square Error.

[0392] Optionally, the accuracy information can comprise but is not limited to at least one of: similarity, cosine similarity, correlation, correlation coefficient, and Area Under Curve (AUC) score.

[0393] Optionally, the communication system performance can comprise but is not limited to at least one of: cell search latency, cell camping success rate, and timing error. The statistics of the cell search latency, cell camping success rate, and timing error are obtained within a monitoring window.

[0394] Optionally, the model related information of the first AI model can comprise but is not limited to at least one of: a running time of the first AI model, a CPU occupation of the first AI model, and a memory space occupation of the first AI model.

[0395] Optionally, in some embodiments, the triggering condition of the model supervision is determined based on at least one of: a model supervision indicator, an inference result of the first AI model, and a model inference indicator.

[0396] For example, in some embodiments, the supervision of the first AI model can be triggered when the model supervision indicator does not meet the requirement, or after the model supervision indicator does not meet the requirement for a period of time.

[0397] For example, in some embodiments, supervision of the first AI model can be triggered when the inference result of the first AI model does not meet the requirement, or when the inference result of the first AI model does not meet the requirement for a period of time. Optionally, the inference result of the first AI model can be considered to not meet the requirement when at least one of the following conditions is met:

[0398] The terminal has not found a suitable cell to camp on after using the first AI model to infer for more than M time lengths (i.e., a fifth preset time length);

[0399] The terminal has not successfully completed AI inference using the first AI model.

[0400] For example, in some embodiments, supervision of the first AI model can be triggered when at least one of the indicators of the model inference of the first AI model does not meet the requirement, or when at least one of the indicators of the model inference of the first AI model does not meet the requirement for a period of time. For example, supervision of the first AI model can be triggered when the RSRP at which the terminal successfully camps on a cell does not meet the requirement.

[0401] Optionally, in some embodiments, the method further comprises:

[0402] Transmitting target capability information between the first device and the second device, the target capability information comprising at least one of:

[0403] Whether the terminal supports the capability of training the first AI model;

[0404] Whether the terminal supports the capability of performing AI inference based on the first AI model;

[0405] Whether the terminal supports the capability of reporting assistance information for training the first AI model;

[0406] Whether the terminal supports the capability of reporting assistance information for performing AI inference based on the first AI model;

[0407] Whether the network side device supports the capability of training the first AI model;

[0408] Whether the network side device supports the capability of performing AI inference based on the first AI model;

[0409] Whether the network side device supports the capability of indicating assistance information for training the first AI model;

[0410] Whether the network side device supports the capability of indicating assistance information for performing AI inference based on the first AI model;

[0411] Whether the server supports the capability of training the first AI model;

[0412] whether the server supports the capability of AI inference based on the first AI model.

[0413] Optionally, in some embodiments, the method further comprises:

[0414] The first device determines the target capability information corresponding to the second device based on at least one of the following:

[0415] The device type of the second device;

[0416] The network type of the second device;

[0417] The reference signal sent by the second device;

[0418] The control information sent by the second device;

[0419] The RRC signaling sent by the second device;

[0420] The interface message between the first device and the second device.

[0421] Optionally, the determination of the target capability information can depend on the device type. For example, the second device is a terminal, and different terminal types introduce different target capability information. At this time, the relevant capability of the terminal can be implicitly indicated by reporting the type of the terminal.

[0422] Optionally, the determination of the target capability information can depend on the network type. For example, different network types (NTN or TN) introduce different target capability information, and at this time the relevant capability of the second device (such as a network side device or a server) can be implicitly indicated by transmitting the network type.

[0423] Optionally, one or more reference signals can be used to indicate the target capability information, for example, the PRACH resource can be used to indicate the target capability information of the second device.

[0424] Optionally, when the second device is a terminal, the terminal can use uplink control information (UCI) to indicate the target capability information, such as physical layer control information, for example, the UCI reported by the terminal to the network side device.

[0425] The interface message between the first device and the second device can include at least one of the following:

[0426] The interface message between the terminal and the server, specifically, it can be a specific interface message between the terminal and the server, which can be a message related to a specific AI model or a message related to all AI models;

[0427] The interface message between the terminal and the network side device can be a specific interface message between the terminal and the network side device, which can be a message related to a specific AI model or a message related to all AI models.

[0428] The interface message between the server and the network side device can be a specific interface message between the server and the network side device, which can be a message related to a specific AI model or a message related to all AI models.

[0429] Referring to FIG. 5, the application further provides a cell camping processing method, as shown in FIG. 5, the cell camping processing method comprises:

[0430] The second device performs at least one of the following:

[0431] sending at least part of the first information to the first device, the first information being used for inference of the first AI model;

[0432] a second operation;

[0433] The second operation comprises at least one of the following:

[0434] training the first AI model to obtain the first AI model and sending the first AI model to the first device;

[0435] training the first AI model to obtain a second training result and sending the second training result to the first device, the second training result being used for training the first AI model by the first device;

[0436] The first device is a terminal, a network side device or a server, the second device is a terminal, a network side device or a server, the first AI model is used for determining a target result, the target result is used for cell camping, and the target result comprises at least one of the following: a frequency domain position of synchronization signal transmission; a time domain position of synchronization signal transmission; a beam transmission direction of synchronization signal transmission; information of a first cell, the first cell being a cell that can be camped.

[0437] Optionally, the second device training the first AI model to obtain the first AI model comprises:

[0438] The second device trains the first AI model based on fifth information to obtain the first AI model;

[0439] The fifth information comprises at least one of the following:

[0440] time information;

[0441] State information of the terminal, the state information comprising at least one of the following: location information, moving direction, moving speed, energy consumption status, power status, environment information, perception information, network scenario information, operator information, and network type;

[0442] A number of times of synchronization signal detection failures within a first preset time period;

[0443] An event;

[0444] Mode information of the synchronization signal;

[0445] Frequency domain characteristics of the synchronization signal;

[0446] Time domain characteristics of the synchronization signal;

[0447] Space domain characteristics of the synchronization signal.

[0448] Optionally, before the second device obtains the first AI model based on the training of the fifth information first AI model, the method further comprises:

[0449] In a case where the second device is the server, the second device obtains the fifth information from at least one of the terminal and the network side device;

[0450] Or, in a case where the second device is the network side device, the second device obtains at least part of the fifth information from the terminal;

[0451] Or, in a case where the second device is the terminal, the second device obtains at least part of the fifth information from the network side device.

[0452] Optionally, the method further comprises:

[0453] The second device receives fourth information from the first device;

[0454] The second device updates the first AI model based on the fourth information;

[0455] The second device sends the updated first AI model to the first device.

[0456] Optionally, the second device trains the first AI model to obtain the first AI model, comprising:

[0457] The second device receives a first training result from the first device;

[0458] The second device inputs the first training result to a fourth AI model to train the first AI model and obtain the first AI model;

[0459] The second device sends the first AI model to the first device.

[0460] Optionally, the second device trains the first AI model, obtains a second training result, and sends the second training result to the first device, including:

[0461] The second device inputs the ninth information into the fifth AI model to obtain the second training result.

[0462] The second device sends the second training result to the first device.

[0463] The ninth information includes at least one of the following:

[0464] Time information;

[0465] State information of the terminal, including at least one of the following: position information, moving direction, moving speed, energy consumption status, power status, environment information, perception information, network scenario information, operator information and network type;

[0466] The number of synchronization signal detection failures within a first preset time period;

[0467] Sudden events;

[0468] Mode information of the synchronization signal;

[0469] Frequency domain characteristics of the synchronization signal;

[0470] Time domain characteristics of the synchronization signal;

[0471] Space domain characteristics of the synchronization signal.

[0472] Optionally, before the second device inputs the ninth information into the fifth AI model to obtain the second training result, the method further includes:

[0473] In the case that the second device is the server, the second device obtains the ninth information from at least one of the terminal and the network side device;

[0474] Or, in the case that the second device is the network side device, the second device obtains at least part of the ninth information from the terminal;

[0475] Or, in the case that the second device is the terminal, the second device obtains at least part of the ninth information from the network side device.

[0476] Optionally, in the case that the second device is the terminal, the method further includes:

[0477] The second device receives the target result from the first device.

[0478] Optionally, in a case where the second device is a terminal, the method further includes:

[0479] The second device sends target indication information to a network side device or a server, the target indication information being used to activate the first AI model, and the target indication information being used to indicate at least one of the following: the terminal is powered on; an initial cell search operation is performed; an initial cell selection operation is performed; an initial search is performed in a manner of performing cell search on a full frequency band supported by the terminal for a first preset time length; the terminal does not camp on a second cell within a second preset time period; a cell reselection operation is performed; a cell handover operation is performed; a number of synchronization signal block (SSB) detection failures is greater than or equal to a first threshold; and it is determined that the first AI model needs to be activated based on at least one of second information, the second information being at least part of input information of the first AI model.

[0480] Optionally, the method further includes:

[0481] The second device periodically triggers training of the first AI model based on first configuration information;

[0482] The first configuration information includes at least one of the following: a starting point of periodic model training; an interval of periodic model training; a number of model training in a period; and a model training time length in a period.

[0483] Optionally, the method further includes:

[0484] The second device triggers training of the first AI model based on a semi-static triggering manner;

[0485] The semi-static triggering manner includes at least one of the following:

[0486] Semi-static triggering based on second configuration information;

[0487] Semi-static training of the model is activated or deactivated through physical control information;

[0488] The second configuration information satisfies at least one of the following: at least one of sending and activating of the second configuration information is triggered based on a target event; and the second configuration information is configured through radio resource control (RRC).

[0489] Optionally, before the first device obtains the target result based on the first artificial intelligence (AI) model, the method further includes:

[0490] The first device triggers training of the first AI model based on a target event;

[0491] wherein the target event comprises at least one of:

[0492] a transmission frequency point of a last cell-defined synchronization signal block (CD-SSB) changes;

[0493] a transmission frequency point of a last non-cell-defined synchronization signal block (NCD-SSB) changes;

[0494] the terminal moves to a cell edge or a preset location;

[0495] a moving speed of the terminal is higher than or equal to a first threshold;

[0496] a moving speed of the terminal is lower than or equal to a second threshold;

[0497] a number of terminals currently accessing or camping on the cell is higher than or equal to a third threshold;

[0498] a number of terminals currently accessing or camping on the cell is lower than or equal to a fourth threshold;

[0499] inference using the first AI model fails;

[0500] a number of consecutive inference failures using the first AI model reaches a fifth threshold;

[0501] a number of inference failures using the first AI model reaches a sixth threshold;

[0502] inference using the first AI model is performed;

[0503] the terminal reselects to a second cell;

[0504] a tracking area of the terminal changes;

[0505] an external environment of the terminal changes;

[0506] the terminal moves to a second cell;

[0507] the terminal moves to a new tracking area;

[0508] the terminal moves to a new geographic location;

[0509] a moving speed variation of the terminal is greater than or equal to a seventh threshold;

[0510] an RSRP measurement value of the terminal changes;

[0511] a time since last training reaches a fourth preset duration;

[0512] a timer for triggering retraining expires;

[0513] M consecutive model supervision occurs, M being an integer greater than 1;

[0514] L model supervision occurs, L being a positive integer;

[0515] The number of detection failures of the synchronization signal block reaches an eighth threshold.

[0516] Optionally, the method further comprises:

[0517] The first device determines that the first AI model training is completed based on eighth information;

[0518] The eighth information includes at least one of the following: a received signal strength indication of the synchronization signal; a signal strength of the detected primary synchronization signal or secondary synchronization signal; a channel estimation signal-to-noise ratio of the synchronization signal; a reference signal received power RSRP of the synchronization signal block; a layer 1 RSRP; a layer 3 RSRP; a probability of successful detection of the synchronization signal by the terminal; a time length of detection of the synchronization signal by the terminal; a probability of successful camping by the terminal; and a probability of successful synchronization by the terminal.

[0519] Optionally, the method further comprises:

[0520] The second device and the first device transmit target capability information, and the target capability information includes at least one of the following:

[0521] Whether the terminal supports the capability of the first AI model training;

[0522] Whether the terminal supports the capability of AI inference based on the first AI model;

[0523] Whether the terminal supports the capability of reporting assistance information for the first AI model training;

[0524] Whether the terminal supports the capability of reporting assistance information for AI inference based on the first AI model;

[0525] Whether the network side device supports the capability of the first AI model training;

[0526] Whether the network side device supports the capability of AI inference based on the first AI model;

[0527] Whether the network side device supports the capability of indicating assistance information for the first AI model training;

[0528] Whether the network side device supports the capability of indicating assistance information for AI inference based on the first AI model;

[0529] Whether the server supports the capability of the first AI model training;

[0530] whether the server supports the capability of AI inference based on the first AI model.

[0531] Optionally, the method further includes:

[0532] The second device determines the target capability information corresponding to the first device based on at least one of the following:

[0533] a device type of the first device;

[0534] a network type of the first device;

[0535] a reference signal sent by the second device;

[0536] control information sent by the first device;

[0537] RRC signaling sent by the first device;

[0538] an interface message between the first device and the second device.

[0539] The cell camping processing method provided in the embodiments of the present application can be executed by a cell camping processing apparatus. The cell camping processing method executed by the cell camping processing apparatus is taken as an example in the embodiments of the present application, and the cell camping processing apparatus provided in the embodiments of the present application is described.

[0540] The cell camping processing apparatus provided in the embodiments of the present application can be a communication device or a component in a communication device, for example, a chip. The communication device can be a terminal, a network side device, a server, or the like. Exemplarily, the terminal can include, but is not limited to, the types of the terminal 11 listed above, the network side device can include, but is not limited to, the types of the network side device 12 listed above, and the embodiments of the present application do not make specific limitations.

[0541] The cell camping processing apparatus includes a receiving module, a sending module and a processing module. The receiving module, the sending module and the processing module can be implemented by software or by hardware. When implemented by hardware, the processing module can be implemented by a processor. The processor can include a general-purpose processor, a special-purpose processor, a central processing unit (CPU), a microprocessor, a digital signal processor (DSP), an artificial intelligent (AI) processor, a graphics processing unit (GPU), an application specific integrated circuit (ASIC), a network processor (NP), a field programmable gate array (FPGA) or other programmable logic devices, a gate circuit, a transistor, a discrete hardware component, etc. The receiving module and the sending module can be implemented by a communication interface, which can include a transceiver, a pin, a circuit, a bus, a radio frequency unit, etc.

[0542] Specifically, referring to FIG. 6, the cell camping processing apparatus 600 is applied to a first device, and the cell camping processing apparatus 600 includes:

[0543] A first processing module 601 is configured to obtain a target result based on a first artificial intelligent (AI) model.

[0544] The first device can be a terminal, a network-side device or a server. The target result is used for cell camping. The target result includes at least one of the following: a frequency domain position of a synchronization signal transmission; a time domain position of the synchronization signal transmission; a beam transmission direction of the synchronization signal transmission; and information of a first cell, which is a cell that can be camped.

[0545] The first device obtains the target result based on the first AI model, including:

[0546] The first device inputs first information into the first AI model to obtain the target result.

[0547] The first information includes at least one of the following:

[0548] Time information;

[0549] State information of the terminal, the state information comprising at least one of the following: location information, moving direction, moving speed, energy consumption status, power status, environment information, perception information, network scenario information, operator information, and network type;

[0550] A number of times of synchronization signal detection failures within a first preset time period;

[0551] An event;

[0552] Mode information of the synchronization signal;

[0553] Frequency domain characteristics of the synchronization signal;

[0554] Time domain characteristics of the synchronization signal;

[0555] Space domain characteristics of the synchronization signal.

[0556] Optionally, the cell camping processing apparatus 600 further comprises a first sending module configured to send the target result to the terminal when the first device is a network side device or a server.

[0557] Optionally, when the first device is a terminal, the first processing module 601 is further configured to activate the first AI model based on a first activation condition, the first activation condition comprising at least one of the following: terminal power-on; performing an initial cell search operation; performing an initial cell selection operation; performing an initial search by searching for a cell in a full frequency band supported by the terminal for a first preset time length; not camping on a second cell within a second preset time period; performing a cell reselection operation; performing a cell handover operation; a timer for activating the first AI model being timed out; a number of times of synchronization signal block (SSB) detection failures being greater than or equal to a first threshold; and determining, based on at least one of second information, that the first AI model needs to be activated, the second information being at least part of input information of the first AI model.

[0558] Alternatively, when the first device is a network side device or a server, the first processing module 601 is further configured to activate the first AI model based on a second activation condition, the second activation condition comprising at least one of the following:

[0559] receive target indication information from a terminal, the target indication information being used to indicate at least one of the following: the terminal is powered on; an initial cell search operation is performed; an initial cell selection operation is performed; an initial search is performed by searching for a cell in a full frequency band supported by the terminal for a first preset time length; the terminal does not camp on a second cell within a second preset time period; a cell reselection operation is performed; a cell handover operation is performed; a number of synchronization signal block (SSB) detection failures is greater than or equal to a first threshold value; and determining, based on at least one of the second information, that the first AI model needs to be activated, the second information being at least part of input information of the first AI model;

[0560] a timer for activating the first AI model expires;

[0561] determining, based on at least one of the third information, that the first AI model needs to be activated, the third information being at least part of input information of the first AI model.

[0562] Optionally, in the case of the first device being a terminal, the first processing module 601 is further configured to perform at least one of the following:

[0563] updating the first AI model based on fourth information, or sending, by the first device, fourth information to a second device, the fourth information being used to update the first AI model, wherein the fourth information includes at least one of the target result and state information of the terminal;

[0564] performing a first operation;

[0565] The first operation includes at least one of the following: falling back to searching for a cell in a full frequency band supported by the terminal; triggering switching of an AI model; triggering retraining of the first AI model; and triggering supervision of the first AI model.

[0566] Optionally, the first processing module 601 is specifically configured to perform a first operation when a first condition is met;

[0567] The first condition includes at least one of the following:

[0568] a time length of using the first AI model for inference exceeds a second preset time length;

[0569] a suitable cell is not found for camping by using the first AI model;

[0570] inference is not successfully completed by using the first AI model.

[0571] Optionally, the first AI model meets at least one of the following:

[0572] a complexity of the AI model is less than or equal to a second threshold value;

[0573] an inference latency of the AI model is less than or equal to a third preset time length;

[0574] an inference success rate of the AI model is greater than or equal to a third threshold value;

[0575] a reliability of an inference result of the AI model is greater than or equal to a fourth threshold value.

[0576] Optionally, the first AI model is obtained by independent training of the terminal, a network side device or a server, or the first AI model is obtained by joint training of at least two of the terminal, the network side device and the server.

[0577] Optionally, the cell camping processing apparatus 600 further includes a first receiving module configured to receive the first AI model from a second device.

[0578] The second device is a terminal, a network side device or a server.

[0579] Optionally, the cell camping processing apparatus 600 further includes a first sending module configured to send fifth information to the second device, the fifth information being used for the second device to train the first AI model.

[0580] The fifth information includes at least one of the following:

[0581] time information;

[0582] state information of the terminal, the state information including at least one of the following: location information, moving direction, moving speed, energy consumption condition, power condition, environment information, perception information, network scene information, operator information and network type;

[0583] a number of times of synchronization signal detection failure within a first preset time period;

[0584] a sudden event;

[0585] mode information of the synchronization signal;

[0586] frequency domain characteristics of the synchronization signal;

[0587] time domain characteristics of the synchronization signal;

[0588] spatial domain characteristics of the synchronization signal.

[0589] Optionally, the cell camping processing apparatus 600 further includes a first sending module, wherein,

[0590] The first processing module 601 is configured to input sixth information into a second AI model to obtain a first training result, and the first training result is used for the second device to train the first AI model.

[0591] The first sending module is configured to send the first training result to a second device.

[0592] The sixth information includes at least one of the following:

[0593] Time information;

[0594] State information of the terminal, and the state information includes at least one of the following: position information, moving direction, moving speed, energy consumption condition, power condition, environment information, perception information, network scene information, operator information and network type;

[0595] The number of times of synchronization signal detection failure in a first preset time period;

[0596] Sudden event;

[0597] Mode information of the synchronization signal;

[0598] Frequency domain feature of the synchronization signal;

[0599] Time domain feature of the synchronization signal;

[0600] Space domain feature of the synchronization signal.

[0601] Optionally, the cell camping processing apparatus 600 further includes a first receiving module configured to perform at least one of the following:

[0602] In a case where the first device is the server, the sixth information is obtained from at least one of the terminal and a network side device;

[0603] Or, in a case where the first device is the network side device, at least part of the sixth information is obtained from the terminal;

[0604] Or, in a case where the first device is the terminal, at least part of the sixth information is obtained from the network side device.

[0605] Optionally, the first processing module 601 is further configured to perform at least one of the following:

[0606] Training the first AI model based on seventh information to obtain the first AI model;

[0607] Inputting a second training result received from a second device into a third AI model for AI training to obtain the first AI model;

[0608] The seventh information includes at least one of the following:

[0609] Time information;

[0610] State information of the terminal, the state information including at least one of the following: position information, moving direction, moving speed, energy consumption condition, power condition, environment information, perception information, network scenario information, operator information, and network type;

[0611] Number of times of synchronization signal detection failure in a first preset time period;

[0612] Sudden event;

[0613] Mode information of the synchronization signal;

[0614] Frequency domain feature of the synchronization signal;

[0615] Time domain feature of the synchronization signal;

[0616] Space domain feature of the synchronization signal.

[0617] Optionally, the input of the training of the first AI model further includes a target label, and the target label includes at least one of the following:

[0618] Whether the terminal detects the synchronization signal;

[0619] Duration that the terminal detects the synchronization signal;

[0620] Frequency domain position of the synchronization signal detected by the terminal;

[0621] Time domain position of the synchronization signal detected by the terminal;

[0622] Beam direction of the synchronization signal detected by the terminal;

[0623] The terminal detects the synchronization signal at a preset frequency domain position;

[0624] The terminal detects the synchronization signal at a preset time domain position;

[0625] The terminal detects the synchronization signal at a preset beam direction;

[0626] Signal quality of a camped cell measured by the terminal;

[0627] Identity of a cell successfully camped by the terminal;

[0628] Tracking area where the cell successfully camped by the terminal is located;

[0629] The terminal successfully camps;

[0630] The terminal successfully camps to a preset cell;

[0631] A time length from a first time to a second time, the first time being a time of initiating a cell search or a time of activating the first AI model, and the second time being a time of successful camping of the terminal.

[0632] Optionally, the first processing module 601 is further configured to:

[0633] periodically trigger training of the first AI model based on first configuration information;

[0634] The first configuration information includes at least one of the following: a starting point of periodic model training; an interval of periodic model training; a number of model training in a period; and a model training time length in a period.

[0635] Optionally, the first processing module 601 is further configured to trigger training of the first AI model based on a semi-static triggering manner.

[0636] The semi-static triggering manner includes at least one of the following:

[0637] Semi-static triggering based on second configuration information;

[0638] Semi-static training of the model is activated or deactivated by physical control information.

[0639] The second configuration information satisfies at least one of the following: at least one of transmission and activation of the second configuration information is triggered based on a target event; and the second configuration information is configured by radio resource control (RRC).

[0640] Optionally, the first processing module 601 is further configured to trigger training of the first AI model based on a target event.

[0641] The target event includes at least one of the following:

[0642] A transmission frequency point of a last cell-defined synchronization signal block (CD-SSB) changes;

[0643] A transmission frequency point of a last non-cell-defined synchronization signal block (NCD-SSB) changes;

[0644] The terminal moves to a cell edge or a preset position;

[0645] A moving speed of the terminal is higher than or equal to a first threshold;

[0646] The moving speed of the terminal is lower than or equal to a second threshold;

[0647] A number of terminals currently accessing or camping in the cell is higher than or equal to a third threshold;

[0648] a quantity of terminals currently accessing or camping on the cell is less than or equal to a fourth threshold;

[0649] a number of consecutive inference failures using the first AI model reaches a fifth threshold;

[0650] a number of consecutive inference failures using the first AI model reaches a fifth threshold;

[0651] a number of inference failures using the first AI model reaches a sixth threshold;

[0652] inference using the first AI model is performed;

[0653] the terminal reselects to a second cell;

[0654] a tracking area of the terminal changes;

[0655] an external environment of the terminal changes;

[0656] the terminal moves to a second cell;

[0657] the terminal moves to a new tracking area;

[0658] the terminal moves to a new geographic location;

[0659] a change in a moving speed of the terminal is greater than or equal to a seventh threshold;

[0660] an RSRP measurement value of the terminal changes;

[0661] a time since last training reaches a fourth preset time length;

[0662] a timer for triggering retraining times out;

[0663] M consecutive model supervisions occur, M being an integer greater than 1;

[0664] L model supervisions occur, L being a positive integer;

[0665] a number of detection failures of synchronization signal blocks reaches an eighth threshold.

[0666] Optionally, the first processing module 601 is further configured to determine, based on eighth information, that the first AI model training is completed;

[0667] The eighth information includes at least one of a received signal strength indication of a synchronization signal, a signal strength of a detected primary synchronization signal or secondary synchronization signal, a channel estimation signal-to-noise ratio of the synchronization signal, a reference signal received power RSRP of a synchronization signal block, a layer 1 RSRP, a layer 3 RSRP, a probability of successful detection of the synchronization signal by the terminal, a time length of detection of the synchronization signal by the terminal, a probability of successful camping by the terminal, and a probability of successful synchronization by the terminal.

[0668] Optionally, the first processing module 601 is further configured to supervise the first AI model based on third configuration information.

[0669] The third configuration information includes at least one of the following:

[0670] An AI model that needs to be supervised;

[0671] A period of model supervision;

[0672] A duration of model supervision;

[0673] Detection window related information of model supervision;

[0674] Trigger conditions of model supervision;

[0675] Indicators of model supervision;

[0676] The indicators of model supervision include at least one of the following: error type information or accuracy information between predicted values and true values; communication system performance; model related information of the first AI model.

[0677] Optionally, the trigger conditions of model supervision are determined based on at least one of the following: indicators of model supervision; inference results of the first AI model; indicators of model inference.

[0678] Optionally, the cell camping processing apparatus 600 further includes a transmission module configured to transmit target capability information between the second device, the target capability information including at least one of the following:

[0679] Whether the terminal supports the capability of training the first AI model;

[0680] Whether the terminal supports the capability of performing AI inference based on the first AI model;

[0681] Whether the terminal supports the capability of reporting assistance information for training the first AI model;

[0682] Whether the terminal supports the capability of reporting assistance information for performing AI inference based on the first AI model;

[0683] Whether the network side device supports the capability of training the first AI model;

[0684] Whether the network side device supports the capability of performing AI inference based on the first AI model;

[0685] Whether the network side device supports the capability of indicating assistance information for training the first AI model;

[0686] whether the network-side device supports the capability of indicating the assistance information for AI inference based on the first AI model;

[0687] whether the server supports the capability of training the first AI model;

[0688] whether the server supports the capability of AI inference based on the first AI model.

[0689] Optionally, the first processing module 601 is further configured to determine the target capability information corresponding to the second device based on at least one of the following:

[0690] a device type of the second device;

[0691] a network type of the second device;

[0692] a reference signal sent by the second device;

[0693] control information sent by the second device;

[0694] RRC signaling sent by the second device;

[0695] an interface message between the first device and the second device.

[0696] Specifically, referring to FIG. 7, the cell camping processing apparatus 700 is applied to the second device, and the cell camping processing apparatus 700 includes:

[0697] an execution module 701, configured to perform at least one of the following:

[0698] send at least part of the first information to the first device, the first information being used for inference of the first AI model;

[0699] a second operation;

[0700] The second operation includes at least one of the following:

[0701] perform training of the first AI model, obtain the first AI model, and send the first AI model to the first device;

[0702] perform training of the first AI model, obtain a second training result, and send the second training result to the first device, the second training result being used for training of the first AI model by the first device;

[0703] Wherein, the first device is a terminal, a network-side device, or a server, the second device is a terminal, a network-side device, or a server, the first AI model is used to determine the target result, the target result is used for cell camping, and the target result includes at least one of the following: the frequency domain location of the synchronization signal transmission; the time domain location of the synchronization signal transmission; the beam transmission direction of the synchronization signal transmission; and information of the first cell, wherein the first cell is a cell that can be camped.

[0704] Optionally, the execution module 701 is specifically used to: train the first AI model based on the fifth information to obtain the first AI model;

[0705] The fifth piece of information includes at least one of the following:

[0706] Time information;

[0707] The terminal's status information includes at least one of the following: location information, direction of movement, speed of movement, energy consumption status, battery status, environmental information, sensing information, network scene information, operator information, and network type;

[0708] The number of times the synchronization signal detection failed within the first preset time period;

[0709] Unexpected events;

[0710] Synchronization signal mode information;

[0711] Frequency domain characteristics of synchronization signals;

[0712] Time-domain characteristics of synchronization signals;

[0713] Spatial characteristics of synchronization signals.

[0714] Optionally, the execution module 701 includes: a second receiving module, configured to perform at least one of the following:

[0715] When the second device is the server, the fifth information is obtained from at least one of the terminal and the network-side device;

[0716] Alternatively, if the second device is the network-side device, at least a portion of the fifth information is obtained from the terminal;

[0717] Alternatively, if the second device is the terminal, at least a portion of the fifth information may be obtained from the network-side device.

[0718] Optionally, the execution module 701 includes:

[0719] The second receiving module is used to receive fourth information from the first device;

[0720] a second processing module, configured to update the first AI model based on the fourth information;

[0721] a second sending module, configured to send the updated first AI model to the first device.

[0722] Optionally, the execution module 701 comprises:

[0723] a second receiving module, configured to receive a first training result from the first device;

[0724] a second processing module, configured to input the first training result into a fourth AI model for training of the first AI model, to obtain the first AI model;

[0725] a second sending module, configured to send the first AI model to the first device.

[0726] Optionally, the execution module 701 comprises:

[0727] a second processing module, configured to input ninth information into a fifth AI model, to obtain a second training result;

[0728] a second sending module, configured to send the second training result to the first device;

[0729] The ninth information comprises at least one of the following:

[0730] time information;

[0731] state information of the terminal, the state information comprising at least one of the following: position information, moving direction, moving speed, energy consumption status, power status, environment information, perception information, network scenario information, operator information and network type;

[0732] a number of times of synchronization signal detection failure within a first preset time period;

[0733] a sudden event;

[0734] mode information of the synchronization signal;

[0735] frequency domain feature of the synchronization signal;

[0736] time domain feature of the synchronization signal;

[0737] spatial domain feature of the synchronization signal.

[0738] Optionally, the execution module 701 comprises a second receiving module, configured to perform at least one of the following:

[0739] in a case where the second device is the server, the ninth information is acquired from at least one of the terminal and a network side device.

[0740] Alternatively, in a case where the second device is the network-side device, obtaining at least part of the ninth information from the terminal;

[0741] Alternatively, in a case where the second device is the terminal, obtaining at least part of the ninth information from the network-side device.

[0742] Optionally, the execution module 701 includes a second receiving module configured to, in a case where the second device is a terminal, receive the target result from the first device.

[0743] Optionally, the execution module 701 includes a second sending module configured to, in a case where the second device is a terminal, send target indication information to a network-side device or a server, the target indication information being used to activate the first AI model, and the target indication information being used to indicate at least one of the following: the terminal is powered on; an initial cell search operation is performed; an initial cell selection operation is performed; an initial search is performed by searching for a cell in a full frequency band supported by the terminal for a first preset time length; the terminal does not camp on a second cell within a second preset time period; a cell reselection operation is performed; a cell handover operation is performed; a number of synchronization signal block (SSB) detection failures is greater than or equal to a first threshold; and it is determined, based on at least one of second information, that the first AI model needs to be activated, the second information being at least part of input information of the first AI model.

[0744] Optionally, the execution module 701 is specifically configured to periodically trigger training of the first AI model based on first configuration information.

[0745] The first configuration information includes at least one of the following: a starting point of periodic model training; an interval of periodic model training; a number of model training times within a period; and a model training time length within a period.

[0746] Optionally, the execution module 701 is specifically configured to trigger training of the first AI model based on a semi-static triggering manner.

[0747] The semi-static triggering manner includes at least one of the following:

[0748] Semi-static triggering based on second configuration information;

[0749] Activating or deactivating semi-static training of a model through physical control information;

[0750] The second configuration information satisfies at least one of the following: at least one of transmission and activation of the second configuration information is triggered based on a target event; and the second configuration information is configured through radio resource control (RRC).

[0751] Optionally, the execution module 701 is specifically configured to trigger training of the first AI model based on a target event;

[0752] The target event includes at least one of the following:

[0753] The transmission frequency point of the last cell-defined synchronization signal block CD-SSB changes;

[0754] The transmission frequency point of the last non-cell-defined synchronization signal block NCD-SSB changes;

[0755] The terminal moves to a cell edge or a preset position;

[0756] The moving speed of the terminal is higher than or equal to a first threshold;

[0757] The moving speed of the terminal is lower than or equal to a second threshold;

[0758] The number of terminals currently accessing or camping on the cell is higher than or equal to a third threshold;

[0759] The number of terminals currently accessing or camping on the cell is lower than or equal to a fourth threshold;

[0760] The inference using the first AI model fails;

[0761] The number of consecutive inference failures using the first AI model reaches a fifth threshold;

[0762] The number of inference failures using the first AI model reaches a sixth threshold;

[0763] The inference using the first AI model is performed;

[0764] The terminal reselects to a second cell;

[0765] The tracking area of the terminal changes;

[0766] The external environment of the terminal changes;

[0767] The terminal moves to a second cell;

[0768] The terminal moves to a new tracking area;

[0769] The terminal moves to a new geographic location;

[0770] The moving speed variation of the terminal is greater than or equal to a seventh threshold;

[0771] The RSRP measurement value of the terminal changes;

[0772] The time since the last training reaches a fourth preset duration;

[0773] a timer expires for triggering retraining;

[0774] M consecutive model supervision occurs, M being an integer greater than 1;

[0775] L model supervision occurs, L being a positive integer;

[0776] The number of detection failures of the synchronization signal block reaches an eighth threshold.

[0777] Optionally, the execution module 701 is specifically configured to determine that the first AI model training is completed based on eighth information;

[0778] The eighth information includes at least one of the following: a received signal strength indication of the synchronization signal; a signal strength of the detected primary synchronization signal or secondary synchronization signal; a channel estimation signal-to-noise ratio of the synchronization signal; a reference signal received power RSRP of the synchronization signal block; a layer 1 RSRP; a layer 3 RSRP; a probability of successful detection of the synchronization signal by the terminal; a time length of detection of the synchronization signal by the terminal; a probability of successful camping by the terminal; and a probability of successful synchronization by the terminal.

[0779] Optionally, the execution module 701 is further configured to transmit target capability information to the first device, the target capability information including at least one of the following:

[0780] whether the terminal supports the capability of the first AI model training;

[0781] whether the terminal supports the capability of AI inference based on the first AI model;

[0782] whether the terminal supports the capability of reporting assistance information for the first AI model training;

[0783] whether the terminal supports the capability of reporting assistance information for AI inference based on the first AI model;

[0784] whether the network side device supports the capability of the first AI model training;

[0785] whether the network side device supports the capability of AI inference based on the first AI model;

[0786] whether the network side device supports the capability of indicating assistance information for the first AI model training;

[0787] whether the network side device supports the capability of indicating assistance information for AI inference based on the first AI model;

[0788] whether the server supports the capability of the first AI model training;

[0789] whether the server supports an ability of AI inference based on the first AI model.

[0790] Optionally, the execution module 701 further includes:

[0791] The second processing module is configured to determine the target capability information corresponding to the first device based on at least one of the following:

[0792] A device type of the first device;

[0793] A network type of the first device;

[0794] A reference signal sent by the second device;

[0795] Control information sent by the first device;

[0796] RRC signaling sent by the first device;

[0797] An interface message between the first device and the second device.

[0798] The cell camping processing apparatus provided by the embodiments of the present application can implement each process implemented by the method embodiments of FIG. 4 to FIG. 5, and achieve the same technical effects. To avoid repetition, details are not described herein.

[0799] As shown in FIG. 8, the embodiments of the present application further provide a communication device 800, which includes a processor 801 and a memory 802, and the memory 802 stores programs or instructions executable on the processor 801. When the programs or instructions are executed by the processor 801, each step of the above cell camping processing method embodiments is implemented, and the same technical effects can be achieved. To avoid repetition, details are not described herein.

[0800] The embodiments of the present application further provide a terminal, which includes a processor and a communication interface, the communication interface is coupled to the processor, and the processor is configured to run programs or instructions to implement the steps in the method embodiments shown in FIG. 4 or FIG. 5. The terminal embodiment corresponds to the above first device side or second device side method embodiments. Each implementation process and implementation manner of the above method embodiments can be applied to the terminal embodiment, and the same technical effects can be achieved. The terminal can be the cell camping processing apparatus shown in FIG. 6 or FIG. 7. Specifically, FIG. 9 is a schematic diagram of a hardware structure of a terminal for implementing the embodiments of the present application.

[0801] The terminal 900 includes, but is not limited to, at least part of the following components: a radio frequency unit 901, a network module 902, an audio output unit 903, an input unit 904, a sensor 905, a display unit 906, a user input unit 907, an interface unit 908, a memory 909, and a processor 910, etc.

[0802] Those skilled in the art can understand that the terminal 900 can also include a power supply (such as a battery) for supplying power to each component, and the power supply can be logically connected to the processor 910 through a power management system, so that the power management system can realize the functions of managing charging, discharging and power consumption management. The terminal structure shown in FIG. 9 does not constitute a limitation on the terminal, and the terminal can include more or fewer components than those shown, or combine certain components, or different component arrangements, which are not described here.

[0803] It should be understood that in the embodiments of the present application, the input unit 904 can include a graphics processor 9041 and a microphone 9042, and the graphics processor 9041 processes image data of a still picture or a video obtained by an image capture device (such as a camera) in a video capture mode or an image capture mode. The display unit 906 can include a display panel 9061, which can be configured in the form of a liquid crystal display, an organic light-emitting diode, etc. The user input unit 907 includes at least one of a touch panel 9071 and other input devices 9072. The touch panel 9071 is also called a touch screen. The touch panel 9071 can include two parts of a touch detection device and a touch controller. The other input devices 9072 can include, but are not limited to, a physical keyboard, function keys (such as volume control keys, on-off keys, etc.), trackballs, mice, joysticks, which are not described here.

[0804] In the embodiments of the present application, after the radio frequency unit 901 receives the downlink data from the network side device, it can be transmitted to the processor 910 for processing. In addition, the radio frequency unit 901 can send uplink data to the network side device. Generally, the radio frequency unit 901 includes, but is not limited to, an antenna, an amplifier, a transceiver, a coupler, a low noise amplifier, a duplexer, etc.

[0805] The memory 909 can be used to store software programs or instructions and various data. The memory 909 can mainly include a first storage area storing programs or instructions and a second storage area storing data, wherein the first storage area can store an operating system, application programs or instructions required by at least one function (such as a sound playing function, an image playing function, etc.), and the like. In addition, the memory 909 can include a volatile memory or a non-volatile memory. The non-volatile memory can be a Read-Only Memory (ROM), a Programmable ROM (PROM), an Erasable PROM (EPROM), an Electrically EPROM (EEPROM), or a flash memory. The volatile memory can be a Random Access Memory (RAM), a Static RAM (SRAM), a Dynamic RAM (DRAM), a Synchronous DRAM (SDRAM), a Double Data Rate SDRAM (DDR SDRAM), an Enhanced SDRAM (ESDRAM), a Synch link DRAM (SLDRAM), and a Direct Rambus RAM (DRRAM). The memory 909 in the embodiments of the present application includes but is not limited to these and any other suitable types of memory.

[0806] The processor 910 can include one or more processing units; optionally, the processor 910 integrates an application processor and a modem processor, wherein the application processor mainly processes operations related to an operating system, a user interface, and an application program, and the modem processor mainly processes wireless communication signals, such as a baseband processor. It can be understood that the above-mentioned modem processor can also not be integrated into the processor 910.

[0807] When the terminal is the first device, the processor 910 is configured to obtain a target result based on a first artificial intelligence (AI) model.

[0808] The target result is used for cell camping, and the target result includes at least one of the following: a frequency domain position of a synchronization signal transmission; a time domain position of the synchronization signal transmission; a beam transmission direction of the synchronization signal transmission; and information of a first cell, the first cell being a cell that can be camped.

[0809] When the terminal is the second device, the radio frequency unit 901 is configured to perform at least one of the following:

[0810] send at least part of the information in the first information to the first device, the first information being used for inference of the first AI model;

[0811] a second operation;

[0812] The second operation includes at least one of the following:

[0813] perform training of the first AI model, obtain the first AI model, and send the first AI model to the first device;

[0814] perform training of the first AI model, obtain a second training result, and send the second training result to the first device, the second training result being used for training of the first AI model by the first device;

[0815] The first device is a network side device or a server, the first AI model is used to determine a target result, the target result is used for cell camping, and the target result includes at least one of the following: a frequency domain position of synchronization signal transmission; a time domain position of synchronization signal transmission; a beam transmission direction of synchronization signal transmission; information of a first cell, the first cell being a cell that can be camped.

[0816] It can be understood that the implementation processes of the implementation manners mentioned in the embodiments can refer to the related descriptions of the above method embodiments, and achieve the same or corresponding technical effects. To avoid repetition, they will not be described here again.

[0817] The embodiments of the present application also provide a network side device including a processor and a communication interface, the communication interface and the processor are coupled, the processor is used to run programs or instructions to realize the steps of the method embodiments shown in FIG. 4 or FIG. 5. The network side device embodiments correspond to the above-mentioned first device side or second device side method embodiments. The various implementation processes and implementation manners of the above-mentioned method embodiments can be applied to the network side device embodiments, and can achieve the same technical effects.

[0818] Specifically, the embodiment of the present application further provides a network side device, which can be the cell camping processing apparatus shown in FIG. 6 or FIG. 7. As shown in FIG. 10, the network side device 1000 includes an antenna 1001, a radio frequency device 1002, a baseband device 1003, a processor 1004 and a memory 1005. The antenna 1001 is connected with the radio frequency device 1002. In the uplink direction, the radio frequency device 1002 receives information through the antenna 1001 and sends the received information to the baseband device 1003 for processing. In the downlink direction, the baseband device 1003 processes the information to be sent and sends it to the radio frequency device 1002, and the radio frequency device 1002 processes the received information and sends it out through the antenna 1001.

[0819] The method performed by the network side device in the above embodiment can be implemented in the baseband device 1003, which includes a baseband processor.

[0820] The baseband device 1003 may, for example, include at least one baseband board on which a plurality of chips are arranged, as shown in FIG. 10, one of which is, for example, a baseband processor connected with the memory 1005 through a bus interface to call the program in the memory 1005 and perform the operations of the network side device shown in the above method embodiment.

[0821] The network side device can further include a network interface 1006, which is, for example, a Common Public Radio Interface (CPRI).

[0822] Specifically, the network side device 1000 of the embodiment of the present application further includes instructions or programs stored in the memory 1005 and executable on the processor 1004, and the processor 1004 calls the instructions or programs in the memory 1005 to perform the method performed by each module shown in FIG. 6 or FIG. 7 and achieve the same technical effect. To avoid repetition, details are not described here.

[0823] The embodiment of the present application further provides a readable storage medium, which stores programs or instructions, and the programs or instructions are executed by a processor to implement each process of the above cell camping processing method embodiment and achieve the same technical effect. To avoid repetition, details are not described here.

[0824] The processor is the processor in the terminal in the above embodiment. The readable storage medium includes a computer readable storage medium, such as a computer readable memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc. In some examples, the readable storage medium can be a non-transitory readable storage medium.

[0825] The embodiment of the present application further provides a chip, which comprises a processor and a communication interface, the communication interface is coupled with the processor, the processor is used for running programs or instructions, realizes each process of the cell camping method and can achieve the same technical effects, to avoid repetition, which will not be described here.

[0826] It should be understood that the chip mentioned in the embodiment of the present application can also be referred to as a system chip, a system chip, a chip system or a system on chip, etc.

[0827] The embodiment of the present application further provides a computer program / program product, which comprises computer instructions, the computer program / program product is executed by at least one processor to realize each process of the cell camping method and can achieve the same technical effects, to avoid repetition, which will not be described here.

[0828] The embodiment of the present application further provides a wireless communication system, which comprises a first device and a second device, the first device can be used to execute the steps of the cell camping method on the first device side, and the second device can be used to execute the steps of the cell camping method on the second device side.

[0829] It should be noted that in this paper, the term "comprise", "include" or any other variant thereof is intended to cover non-exclusive inclusion, so that the process, method, article or device including a series of elements not only includes those elements, but also includes other elements not explicitly listed or inherent to such process, method, article or device. Without more limitations, the element defined by the statement "comprises a" does not exclude the presence of another identical element in the process, method, article or device including the element. In addition, it should be pointed out that the scope of the method and device in the present application is not limited to the order of the functions shown or discussed, but also includes the functions performed in a substantially simultaneous manner or in the opposite order, for example, the described method can be performed in a different order from the described order, and various steps can also be added, omitted or combined. In addition, the features described with reference to some examples can be combined in other examples.

[0830] Through the description of the above embodiments, those skilled in the art can clearly understand that the above-mentioned embodiment method can be realized by means of computer software product and general hardware platform, of course, it can also be realized by hardware. The computer software product is stored in a storage medium (such as ROM, RAM, magnetic disk, optical disk, etc.), which includes a plurality of instructions for making the terminal or network side device execute the method described in each embodiment of the present application.

[0831] The embodiments of the present application are described above with reference to the accompanying drawings, but the present application is not limited to the above-described specific embodiments, and the above-described specific embodiments are merely illustrative, but not restrictive, and a person of ordinary skill in the art can make many forms of embodiments under the inspiration of the present application without departing from the purpose of the present application and the scope protected by the claims, and these embodiments all belong to the protection of the present application.

Claims

1. A cell camping method comprising: obtaining, by a first device, a target result based on a first artificial intelligence (AI) model; wherein the first device is a terminal, a network-side device, or a server, the target result is used for cell camping, and the target result comprises at least one of: a frequency domain location of synchronization signal transmission; a time domain location of synchronization signal transmission; a beam transmission direction of synchronization signal transmission; and information of a first cell, the first cell being a cell that can be camped.

2. The method of claim 1, wherein, obtaining, by the first device, the target result based on the first AI model comprises: inputting, by the first device, first information into the first AI model to obtain the target result; wherein the first information comprises at least one of: time information; state information of the terminal, the state information comprising at least one of: location information, moving direction, moving speed, energy consumption status, power status, environment information, perception information, network scenario information, operator information, and network type; a number of synchronization signal detection failures within a first preset time period; a sudden event; mode information of the synchronization signal; frequency domain characteristics of the synchronization signal; time domain characteristics of the synchronization signal; and spatial domain characteristics of the synchronization signal.

3. The method of claim 1, wherein, in a case where the first device is the network-side device or the server, the method further comprises: sending, by the first device, the target result to the terminal.

4. The method of claim 1, wherein, the method further comprises: in a case where the first device is the terminal, activating, by the first device, the first AI model based on a first activation condition, the first activation condition comprising at least one of: terminal power-on; performing an initial cell search operation; performing an initial cell selection operation; performing initial search in a manner of performing cell search on a full frequency band supported by the terminal for a first preset time length; not camping to a second cell within a second preset time period; performing a cell reselection operation; performing a cell handover operation; a timer for activating the first AI model expiring; a number of synchronization signal block (SSB) detection failures being greater than or equal to a first threshold; and determining, based on at least one of second information, that the first AI model needs to be activated, the second information being at least part of input information of the first AI model; or, in a case where the first device is the network-side device or the server, activating, by the first device, the first AI model based on a second activation condition, the second activation condition comprising at least one of: receiving, by the first device, target indication information from the terminal, the target indication information indicating at least one of: terminal power-on; performing an initial cell search operation; performing an initial cell selection operation; performing initial search in a manner of performing cell search on a full frequency band supported by the terminal for a first preset time length; not camping to a second cell within a second preset time period; performing a cell reselection operation; performing a cell handover operation; a number of synchronization signal block (SSB) detection failures being greater than or equal to a first threshold; and determining, based on at least one of second information, that the first AI model needs to be activated, the second information being at least part of input information of the first AI model; a timer for activating the first AI model expiring; and determine that the first AI model needs to be activated based on at least one of the third information, the third information being at least part of input information of the first AI model.

5. The method of claim 1, wherein, In a case where the first device is a terminal, the method further includes at least one of: the first device updates the first AI model based on fourth information, or the first device sends fourth information to a second device, the fourth information being used for updating the first AI model, wherein the fourth information includes at least one of the target result and state information of the terminal; the first device performs a first operation; wherein the first operation includes at least one of the following: fallback to a way of performing cell search in a full frequency band supported by the terminal; triggering switching of an AI model; triggering retraining of the first AI model; triggering supervision of the first AI model.

6. The method of claim 5, wherein, the first device performing the first operation includes: in a case where a first condition is met, the first device performs the first operation; wherein the first condition includes at least one of the following: a time length of using the first AI model for inference exceeds a second preset time length; no suitable cell is found for camping by using the first AI model; inference is not successfully completed by using the first AI model.

7. The method of claim 1, wherein, the method further includes: the first device receives the first AI model from a second device; wherein the second device is a terminal, a network side device or a server.

8. The method of claim 7, wherein, before the first device receives the first AI model from the second device, the method further includes: the first device sends fifth information to the second device, the fifth information being used for the second device to train the first AI model; wherein the fifth information includes at least one of the following: time information; state information of the terminal, the state information including at least one of the following: location information, moving direction, moving speed, energy consumption status, power status, environment information, perception information, network scenario information, operator information and network type; a number of times of synchronization signal detection failure within a first preset time period; a sudden event; mode information of the synchronization signal; frequency domain characteristics of the synchronization signal; time domain characteristics of the synchronization signal; spatial domain characteristics of the synchronization signal.

9. The method of claim 7, wherein, before the first device receives the first AI model from the second device, the method further includes: the first device inputs sixth information into a second AI model to obtain a first training result, the first training result being used for the second device to train the first AI model; the first device sends the first training result to the second device; wherein the sixth information includes at least one of the following: time information; state information of the terminal, the state information including at least one of the following: location information, moving direction, moving speed, energy consumption status, power status, environment information, perception information, network scenario information, operator information and network type; a number of times of synchronization signal detection failure within a first preset time period; a sudden event; mode information of the synchronization signal; frequency domain characteristics of the synchronization signal; time domain characteristics of the synchronization signal; spatial domain characteristics of the synchronization signal.

10. The method of claim 9, wherein, the method further includes: In a case that the first device is the server, the first device acquires the sixth information from at least one of the terminal and the network-side device; Or, in a case that the first device is the network-side device, the first device acquires at least part of the sixth information from the terminal; Or, in a case that the first device is the terminal, the first device acquires at least part of the sixth information from the network-side device.

11. The method of claim 1, wherein, The method further includes any one of the following: The first device trains the first AI model based on seventh information to obtain the first AI model; The first device inputs second training results received from a second device into a third AI model to perform the first AI training, and obtains the first AI model; The seventh information includes at least one of the following: Time information; State information of the terminal, the state information including at least one of the following: position information, moving direction, moving speed, energy consumption status, power status, environment information, perception information, network scenario information, operator information, and network type; Number of times of synchronization signal detection failures within a first preset time period; Sudden event; Mode information of the synchronization signal; Frequency domain feature of the synchronization signal; Time domain feature of the synchronization signal; Space domain feature of the synchronization signal.

12. The method according to any one of claims 8 to 11, wherein, The training of the first AI model further includes a target label, and the target label includes at least one of the following: Whether the terminal detects the synchronization signal; Duration that the terminal detects the synchronization signal; Frequency domain position of the synchronization signal detected by the terminal; Time domain position of the synchronization signal detected by the terminal; Beam direction of the synchronization signal detected by the terminal; The terminal detects the synchronization signal at a preset frequency domain position; The terminal detects the synchronization signal at a preset time domain position; The terminal detects the synchronization signal at a preset beam direction; Signal quality of a camped cell measured by the terminal; Identity of a cell successfully camped by the terminal; Tracking area in which the cell successfully camped by the terminal is located; The terminal successfully camps; The terminal successfully camps to a preset cell; Duration from a first time point to a second time point, the first time point being a time point of initiating cell search or a time point of activating the first AI model, and the second time point being a time point of successful camping of the terminal.

13. The method according to any one of claims 1 to 12, wherein, Before the first device obtains a target result based on a first artificial intelligence (AI) model, the method further includes: The first device triggers training of the first AI model periodically based on first configuration information; The first configuration information includes at least one of the following: start point of periodic model training; interval of periodic model training; number of model training in a period; and duration of model training in a period.

14. The method according to any one of claims 1 to 12, wherein, Before the first device obtains a target result based on a first artificial intelligence (AI) model, the method further includes: The first device triggers training of the first AI model based on a semi-static triggering manner; The semi-static triggering manner includes at least one of the following: Semi-static triggering based on second configuration information; Semi-static training of the model activated or deactivated by physical control information; The second configuration information satisfies at least one of the following conditions: the second configuration information is triggered to be sent and activated based on a target event; and the second configuration information is configured by radio resource control (RRC).

15. The method according to any one of claims 1 to 12, wherein, Before the first device obtains a target result based on a first artificial intelligence (AI) model, the method further includes: The first device triggers training of the first AI model based on a target event; The target event includes at least one of the following conditions: A transmission frequency point of a last cell-defined synchronization signal block (CD-SSB) changes; A transmission frequency point of a last non-cell-defined synchronization signal block (NCD-SSB) changes; The terminal moves to a cell edge or a preset location; A moving speed of the terminal is higher than or equal to a first threshold; The moving speed of the terminal is lower than or equal to a second threshold; A number of terminals currently accessing or camping on the cell is higher than or equal to a third threshold; The number of terminals currently accessing or camping on the cell is lower than or equal to a fourth threshold; Inference using the first AI model fails; A number of consecutive inference failures using the first AI model reaches a fifth threshold; A number of inference failures using the first AI model reaches a sixth threshold; Inference using the first AI model is performed; The terminal reselects to a second cell; A tracking area of the terminal changes; An external environment of the terminal changes; The terminal moves to a second cell; The terminal moves to a new tracking area; The terminal moves to a new geographic location; A moving speed variation of the terminal is greater than or equal to a seventh threshold; An RSRP measurement value of the terminal changes; A time since last training reaches a fourth preset time length; A timer for triggering retraining times out; M consecutive model supervisions occur, where M is an integer greater than 1; L model supervisions occur, where L is a positive integer; A number of detection failures of a synchronization signal block reaches an eighth threshold.

16. The method according to any one of claims 8 to 15, wherein, The method further includes: The first device determines, based on eighth information, that training of the first AI model is complete; The eighth information includes at least one of the following: a received signal strength indication of a synchronization signal; a signal strength of a detected primary synchronization signal or secondary synchronization signal; a channel estimation signal-to-noise ratio of the synchronization signal; a reference signal received power (RSRP) of a synchronization signal block; a layer 1 RSRP; a layer 3 RSRP; a probability that the terminal successfully detects the synchronization signal; a time length for which the terminal detects the synchronization signal; a probability that the terminal successfully camps; and a probability that the terminal successfully synchronizes.

17. The method of any one of claims 1 to 16, wherein, The method further includes: The first device supervises the first AI model based on third configuration information; The third configuration information includes at least one of the following: An AI model identifier that needs to be supervised; A period of model supervision; A time length of model supervision; Detection window related information of model supervision; Triggering conditions of model supervision; Indicators of model supervision; The indicators of model supervision include at least one of the following: error or accuracy information between a predicted value and an actual value; communication system performance; and model related information of the first AI model.

18. The method of claim 17, wherein, The trigger condition of the model supervision is determined based on at least one of the following: an index of model supervision; an inference result of the first AI model; an index of model inference.

19. The method of any one of claims 1 to 18, wherein, The method further includes: The target capability information transmitted between the first device and the second device includes at least one of the following: Whether the terminal supports the capability of training the first AI model; Whether the terminal supports the capability of performing AI inference based on the first AI model; Whether the terminal supports the capability of reporting auxiliary information for training the first AI model; Whether the terminal supports the capability of reporting auxiliary information for performing AI inference based on the first AI model; Whether the network side device supports the capability of training the first AI model; Whether the network side device supports the capability of performing AI inference based on the first AI model; Whether the network side device supports the capability of indicating auxiliary information for training the first AI model; Whether the network side device supports the capability of indicating auxiliary information for performing AI inference based on the first AI model; Whether the server supports the capability of training the first AI model; Whether the server supports the capability of performing AI inference based on the first AI model.

20. The method of claim 19, wherein, The method further includes: The first device determines the target capability information corresponding to the second device based on at least one of the following: The device type of the second device; The network type of the second device; The reference signal sent by the second device; The control information sent by the second device; The RRC signaling sent by the second device; The interface message between the first device and the second device.

21. A cell camping processing method, comprising: The second device performs at least one of the following: The second device sends at least part of the first information to the first device, the first information being used for inference of the first AI model; A second operation; The second operation includes at least one of the following: The second device performs training of the first AI model, obtains the first AI model, and sends the first AI model to the first device; The second device performs training of the first AI model, obtains a second training result, and sends the second training result to the first device, the second training result being used for training of the first AI model by the first device; The first device is a terminal, a network side device or a server, the second device is a terminal, a network side device or a server, the first AI model is used for determining a target result, the target result is used for cell camping, and the target result includes at least one of the following: frequency domain position of synchronization signal transmission; time domain position of synchronization signal transmission; beam transmission direction of synchronization signal transmission; information of a first cell, the first cell being a cell that can be camped.

22. The method of claim 21, wherein, The second device performs training of the first AI model, obtains the first AI model, and includes: The second device performs training of the first AI model based on the fifth information, obtains the first AI model; The fifth information includes at least one of the following: Time information; State information of the terminal, the state information comprising at least one of the following: location information, moving direction, moving speed, energy consumption status, power status, environment information, sensing information, network scenario information, operator information, and network type; A number of times of synchronization signal detection failures within a first preset time period; A sudden event; Pattern information of the synchronization signal; Frequency domain characteristics of the synchronization signal; Time domain characteristics of the synchronization signal; Space domain characteristics of the synchronization signal.

23. The method of claim 22, wherein, Before the second device obtains the first AI model based on the training of the fifth information first AI model, the method further comprises: In a case where the second device is the server, the second device obtains the fifth information from at least one of the terminal and the network side device; Or, in a case where the second device is the network side device, the second device obtains at least part of the fifth information from the terminal; Or, in a case where the second device is the terminal, the second device obtains at least part of the fifth information from the network side device.

24. The method of claim 23, wherein, The method further comprises: The second device receives fourth information from the first device; The second device updates the first AI model based on the fourth information; The second device sends the updated first AI model to the first device.

25. The method of claim 21, wherein, The second device trains the first AI model to obtain the first AI model, comprising: The second device receives a first training result from the first device; The second device inputs the first training result to a fourth AI model to train the first AI model to obtain the first AI model; The second device sends the first AI model to the first device.

26. The method of claim 21, wherein, The second device trains the first AI model to obtain a second training result, and sends the second training result to the first device, comprising: The second device inputs ninth information to a fifth AI model to obtain the second training result; The second device sends the second training result to the first device; The ninth information comprises at least one of the following: Time information; State information of the terminal, the state information comprising at least one of the following: location information, moving direction, moving speed, energy consumption status, power status, environment information, sensing information, network scenario information, operator information, and network type; A number of times of synchronization signal detection failures within a first preset time period; A sudden event; Pattern information of the synchronization signal; Frequency domain characteristics of the synchronization signal; Time domain characteristics of the synchronization signal; Space domain characteristics of the synchronization signal.

27. The method of claim 26, wherein, Before the second device inputs the ninth information to the fifth AI model to obtain the second training result, the method further comprises: In a case where the second device is the server, the second device obtains the ninth information from at least one of the terminal and the network side device; Or, in a case where the second device is the network side device, the second device obtains at least part of the ninth information from the terminal; Or, in a case where the second device is the terminal, the second device obtains at least part of the ninth information from the network side device.

28. The method of claim 21, wherein, In a case where the second device is a terminal, the method further includes: The second device receives the target result from the first device.

29. The method of any one of claims 21 to 28, wherein, The method further includes: The second device periodically triggers training of the first AI model based on first configuration information; The first configuration information includes at least one of the following: a starting point of periodic model training; an interval of periodic model training; a number of model training times within a period; a model training duration within a period.

30. The method of any one of claims 21 to 28, wherein, The method further includes: The second device triggers training of the first AI model based on a semi-static triggering manner; The semi-static triggering manner includes at least one of the following: Semi-static triggering based on second configuration information; Semi-static training of the model is activated or deactivated through physical control information; The second configuration information satisfies at least one of the following: at least one of transmission and activation of the second configuration information is triggered based on a target event; the second configuration information is configured through radio resource control (RRC).

31. The method of any one of claims 21 to 28, wherein, Before the first device obtains a target result based on a first artificial intelligence (AI) model, the method further includes: The first device triggers training of the first AI model based on a target event; The target event includes at least one of the following: A transmission frequency point of a last cell-defined synchronization signal block (CD-SSB) changes; A transmission frequency point of a last non-cell-defined synchronization signal block (NCD-SSB) changes; The terminal moves to a cell edge or a preset location; A moving speed of the terminal is higher than or equal to a first threshold; A moving speed of the terminal is lower than or equal to a second threshold; A number of terminals currently accessing or camping on a cell is higher than or equal to a third threshold; A number of terminals currently accessing or camping on a cell is lower than or equal to a fourth threshold; Inference using the first AI model fails; A number of consecutive inference failures using the first AI model reaches a fifth threshold; A number of inference failures using the first AI model reaches a sixth threshold; Inference using the first AI model is performed; The terminal reselects to a second cell; A tracking area of the terminal changes; An external environment of the terminal changes; The terminal moves to a second cell; The terminal moves to a new tracking area; The terminal moves to a new geographic location; A moving speed variation of the terminal is greater than or equal to a seventh threshold; An RSRP measurement value of the terminal changes; A time since the last training reaches a fourth preset duration; A timer for triggering retraining times out; M consecutive model supervisions occur, where M is an integer greater than 1; L model supervisions occur, where L is a positive integer; A number of synchronization signal block detection failures reaches an eighth threshold.

32. The method of any one of claims 21 to 31, wherein, The method further includes: The first device determines that training of the first AI model is complete based on eighth information; The eighth information includes at least one of the following: a received signal strength indication of a synchronization signal; a signal strength of a detected primary synchronization signal or secondary synchronization signal; a channel estimation signal-to-noise ratio of the synchronization signal; a reference signal received power (RSRP) of a synchronization signal block; a layer 1 RSRP; a layer 3 RSRP; a probability of successful detection of the synchronization signal by the terminal; a time length of detection of the synchronization signal by the terminal; a probability of successful camping by the terminal; and a probability of successful synchronization by the terminal.

33. The method of any one of claims 21 to 32, wherein, The method further includes: The second device transmits target capability information with the first device, and the target capability information includes at least one of the following: Whether the terminal supports the capability of training the first AI model; Whether the terminal supports the capability of performing AI inference based on the first AI model; Whether the terminal supports the capability of reporting auxiliary information for training the first AI model; Whether the terminal supports the capability of reporting auxiliary information for performing AI inference based on the first AI model; Whether the network side device supports the capability of training the first AI model; Whether the network side device supports the capability of performing AI inference based on the first AI model; Whether the network side device supports the capability of indicating auxiliary information for training the first AI model; Whether the network side device supports the capability of indicating auxiliary information for performing AI inference based on the first AI model; Whether the server supports the capability of training the first AI model; Whether the server supports the capability of performing AI inference based on the first AI model.

34. The method of claim 33, wherein, The method further includes: The second device determines the target capability information corresponding to the first device based on at least one of the following: A device type of the first device; A network type of the first device; A reference signal sent by the second device; Control information sent by the first device; RRC signaling sent by the first device; An interface message between the first device and the second device.

35. A cell camping processing apparatus applied to a first device, comprising: A first processing module configured to obtain a target result based on a first artificial intelligence (AI) model; The first device is a terminal, a network side device, or a server, the target result is used for cell camping, and the target result includes at least one of the following: a frequency domain position of synchronization signal transmission; a time domain position of synchronization signal transmission; a beam transmission direction of synchronization signal transmission; and information of a first cell, which is a cell that can be camped.

36. The apparatus of claim 35, wherein, The first processing module is specifically configured to input first information into the first AI model to obtain the target result. The first information includes at least one of the following: Time information; State information of the terminal, including at least one of the following: position information, moving direction, moving speed, energy consumption status, power status, environment information, perception information, network scenario information, operator information, and network type; A number of times of synchronization signal detection failure within a first preset time period; An event of burst; Mode information of the synchronization signal; Frequency domain characteristics of the synchronization signal; Time domain characteristics of the synchronization signal; Space domain characteristics of the synchronization signal.

37. A cell camping processing apparatus applied to a second device, wherein, The execution module is configured to perform at least one of the following: ​ sending at least part of the information in the first information to the first device, the first information being used for inference of the first AI model; a second operation; wherein the second operation comprises at least one of: performing training of the first AI model, obtaining the first AI model, and sending the first AI model to the first device; performing training of the first AI model, obtaining a second training result, and sending the second training result to the first device, the second training result being used by the first device to perform training of the first AI model; wherein the first device is a terminal, a network-side device, or a server, the second device is a terminal, a network-side device, or a server, the first AI model is used to determine a target result, the target result is used to perform cell camping, and the target result comprises at least one of: a frequency domain location of synchronization signal transmission; a time domain location of synchronization signal transmission; a beam transmission direction of synchronization signal transmission; information of a first cell, the first cell being a cell that can be camped on.

38. The apparatus of claim 37, wherein, The execution module is specifically configured to perform training of the first AI model based on fifth information, and obtain the first AI model; wherein the fifth information comprises at least one of: time information; state information of the terminal, the state information comprising at least one of: location information, moving direction, moving speed, energy consumption status, power status, environment information, perception information, network scenario information, operator information, and network type; a number of times of synchronization signal detection failure within a first preset time period; a sudden event; mode information of the synchronization signal; frequency domain characteristics of the synchronization signal; time domain characteristics of the synchronization signal; spatial domain characteristics of the synchronization signal.

39. A terminal comprising a processor and a memory, the memory storing programs or instructions executable on the processor, the programs or instructions being executed by the processor to implement the steps of the cell camping processing method according to any one of claims 1 to 34.

40. A network-side device comprising a processor and a memory, the memory storing programs or instructions executable on the processor, the programs or instructions being executed by the processor to implement the steps of the cell camping processing method according to any one of claims 1 to 34.

41. A readable storage medium, the readable storage medium storing programs or instructions, the programs or instructions being executed by a processor to implement the steps of the cell camping processing method according to any one of claims 1 to 34.

42. A computer program product comprising computer instructions, the computer instructions being executed by a processor to implement the steps of the cell camping processing method according to any one of claims 1 to 34.

Images