Transmission control method and apparatus, and communication device

Abstract

The present application relates to the technical field of communications, and discloses a transmission control method and apparatus, and a communication device. The transmission control method of embodiments of the present application comprises: a first device acquires target information, the target information being obtained on the basis of a first model; and the first device executes a first operation on the basis of the target information, wherein the target information comprises at least one of the following: information of a target cell set; time information corresponding to a first procedure; time information corresponding to the measurement of a first signal; time information corresponding to the transmission of a second signal; time domain information of a target synchronization signal set; frequency domain information of a target synchronization signal set; spatial domain information of a target synchronization signal set; index information of a target synchronization signal set; and transmission mode information of a target synchronization signal set; and wherein the first operation comprises at least one of the following: enabling or disabling at least one target cell; switching the state of at least one target cell; transmitting or receiving at least one target signal; executing a second procedure; and performing a first measurement, the first measurement comprising performing measurement on the basis of at least one target cell.

Description

Transmission control method, apparatus and communication device

[0001] Cross-reference to Related Applications

[0002] The present application claims priority to the Chinese patent application No. 202410717893.5, filed on June 04, 2024, the contents of which are 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 transmission control method, apparatus and communication device. BACKGROUND

[0004] In some cases (such as when the load is low or the traffic is small), the network side device can close the transmission of some cells. When the user equipment (User Equipment, UE, also known as terminal) moves to a neighboring cell or needs to access a cell with better performance, the network side device needs to start the corresponding transmission. However, for the network side device, it is not clear when or where the UE has transmission needs, and for the UE, it is not clear whether the transmission state of the cell is on or off. This leads to poor effectiveness of the network side device or UE in transmission control. SUMMARY

[0005] Embodiments of the present application provide a transmission control method, apparatus and communication device, which can solve the problem of poor effectiveness of the network side device or UE in transmission control.

[0006] In a first aspect, a transmission control method is provided, executed by a first device, and the method comprises:

[0007] The first device obtains target information, wherein the target information is obtained based on a first model;

[0008] The first device performs a first operation based on the target information;

[0009] The target information comprises at least one of the following:

[0010] Information of a target cell set;

[0011] Target time information, wherein the target time information is used to indicate at least one of the following: time information corresponding to a first flow; time information corresponding to measuring a first signal; time information corresponding to transmitting a second signal;

[0012] target transmission information, the target transmission information comprising at least one of: time domain information of a target synchronization signal set; frequency domain information of the target synchronization signal set; spatial domain information of the target synchronization signal set; index information of the target synchronization signal set; transmission mode information of the target synchronization signal set;

[0013] The first operation comprises at least one of: turning on or off at least one target cell; switching a state of at least one target cell; transmitting or receiving at least one target signal; executing a second procedure; performing a first measurement, the first measurement comprising measuring based on at least one target cell;

[0014] The first procedure comprises at least one of cell selection and cell reselection.

[0015] The first signal comprises at least one of a synchronization signal and a reference signal (RS).

[0016] The second signal comprises at least one of a wake-up signal, a positioning signal, a sounding signal and a random access message.

[0017] The second procedure comprises at least one of cell selection, cell reselection, reselecting or camping on a target cell, switching a target transmission / reception point (TRP), switching a target transmission configuration indication (TCI) configuration, and switching a target RS.

[0018] The target cell comprises at least one of a physical cell, a carrier and a TRP.

[0019] The target signal comprises at least one of a synchronization signal, a paging signal and a random access channel (RACH).

[0020] In a second aspect, a transmission control apparatus is provided, the apparatus comprising:

[0021] A first processing module configured to obtain target information, the target information being obtained based on a first model.

[0022] A second processing module configured to perform a first operation based on the target information.

[0023] The target information comprises at least one of:

[0024] Information of a target cell set.

[0025] Target time information, the target time information being used to indicate at least one of: time information corresponding to the first procedure; time information corresponding to measuring the first signal; time information corresponding to transmitting the second signal.

[0026] target transmission information, the target transmission information comprising at least one of: time domain information of a target synchronization signal set; frequency domain information of the target synchronization signal set; spatial domain information of the target synchronization signal set; index information of the target synchronization signal set; transmission mode information of the target synchronization signal set;

[0027] The first operation comprises at least one of: turning on or off at least one target cell; switching a state of at least one target cell; transmitting or receiving at least one target signal; executing a second procedure; performing a first measurement, the first measurement comprising measuring based on at least one target cell;

[0028] The first procedure comprises at least one of cell selection and cell reselection.

[0029] The first signal comprises at least one of a synchronization signal and a reference signal (RS).

[0030] The second signal comprises at least one of a wake-up signal, a positioning signal, a sounding signal, and a random access message.

[0031] The second procedure comprises at least one of cell selection, cell reselection, reselecting or camping on a target cell, switching a target transmission / reception point (TRP), switching a target transmission configuration indication (TCI) configuration, and switching a target RS.

[0032] The target cell comprises at least one of a physical cell, a carrier, and a TRP.

[0033] The target signal comprises at least one of a synchronization signal, a paging signal, and a random access channel (RACH).

[0034] In a third aspect, a transmission control apparatus is provided, the apparatus being configured to perform the steps of the method of the first aspect.

[0035] In a fourth aspect, a communication device is provided, the communication device comprising a processor and a memory, the memory storing programs or instructions executable on the processor, the programs or instructions being executed by the processor to implement the steps of the method of the first aspect.

[0036] In a fifth aspect, a communication device is provided, the communication device comprising a processor and a communication interface, wherein the processor is configured to: obtain target information, the target information being obtained based on a first model; and perform a first operation based on the target information.

[0037] The target information comprises at least one of:

[0038] Information of a target cell set.

[0039] target time information, the target time information being used for indicating at least one of: time information corresponding to the first procedure; time information corresponding to measuring the first signal; time information corresponding to transmitting the second signal;

[0040] target transmission information, the target transmission information including at least one of: time domain information of the target synchronization signal set; frequency domain information of the target synchronization signal set; spatial domain information of the target synchronization signal set; index information of the target synchronization signal set; transmission mode information of the target synchronization signal set;

[0041] the first operation including at least one of: turning on or off the at least one target cell; switching a state of the at least one target cell; transmitting or receiving the at least one target signal; performing the second procedure; performing a first measurement, the first measurement including measuring based on the at least one target cell;

[0042] wherein the first procedure includes at least one of: cell selection and cell reselection;

[0043] the first signal including at least one of: a synchronization signal and a reference signal, RS;

[0044] the second signal including at least one of: a wake-up signal, a positioning signal, a sounding signal and a random access message;

[0045] the second procedure including at least one of: cell selection, cell reselection, reselecting or camping on a target cell, switching a target transmission / reception point, TRP, switching a target transmission configuration indication, TCI, configuration, switching a target RS;

[0046] the target cell including at least one of: a physical cell, a carrier and a TRP;

[0047] the target signal including at least one of: a synchronization signal, a paging signal and a random access channel, RACH.

[0048] In a sixth aspect, a readable storage medium is provided, the readable storage medium storing a program or instructions, the program or instructions being executed by a processor to implement steps of the method according to the first aspect.

[0049] In a seventh aspect, a wireless communication system is provided, including: a terminal and a network side device, the terminal being configured to implement steps of the method according to the first aspect, and the network side device being configured to implement steps of the method according to the first aspect.

[0050] In an eighth aspect, a chip is provided, the chip including a processor and a communication interface, the communication interface being coupled to the processor, the processor being configured to run a program or instructions to implement steps of the method according to the first aspect.

[0051] In a ninth aspect, a computer program / program product is provided, which is stored in a storage medium, and is executed by at least one processor to implement the steps of the transmission control method according to the first aspect.

[0052] In the embodiments of the present application, the first device obtains target information, the target information being obtained based on a first model; the first device performs a first operation based on the target information; wherein the target information comprises at least one of the following: information of a target cell set; target time information, the target time information being used to indicate at least one of the following: time information corresponding to a first procedure; time information corresponding to measuring a first signal; time information corresponding to transmitting a second signal; target transmission information, the target transmission information comprising at least one of the following: time domain information of a target synchronization signal set; frequency domain information of the target synchronization signal set; spatial domain information of the target synchronization signal set; index information of the target synchronization signal set; transmission mode information of the target synchronization signal set; the first operation comprises at least one of the following: turning on or off at least one target cell; switching a state of at least one target cell; transmitting or receiving at least one target signal; performing a second procedure; performing a first measurement, the first measurement comprising measuring based on at least one target cell; wherein the first procedure comprises at least one of cell selection and cell reselection; the first signal comprises at least one of a synchronization signal and an RS; the second signal comprises at least one of a wake-up signal, a positioning signal, a sounding signal and a random access message; the second procedure comprises at least one of cell selection, cell reselection, reselecting or camping on a target cell, switching a target TRP, switching a target TCI configuration, switching a target RS; the target cell comprises at least one of a physical cell, a carrier and a TRP; the target signal comprises at least one of a synchronization signal, a paging signal and RACH. In this way, since the first device can obtain target information obtained based on a first model, the target information can provide a basis for the first device to perform transmission control related operations (i.e. the first operation), thereby improving the effect of the first device on transmission control. BRIEF DESCRIPTION OF DRAWINGS

[0053] FIG. 1 is a schematic diagram of a network structure to which embodiments of the present application can be applied;

[0054] FIG. 2a is a schematic diagram of a neural network;

[0055] FIG. 2b is a schematic diagram of a neuron;

[0056] FIG. 3 is a specific operation framework diagram of an AI / ML model;

[0057] FIG. 4a is a schematic diagram of multi-antenna panel transmission within the same TRP;

[0058] FIG. 4b is a schematic diagram of multi-TRP / panel transmission between multi-TRPs, ideal backhaul line;

[0059] FIG. 4c is a schematic diagram of multi-TRP / panel transmission between multi-TRPs, non-ideal backhaul line;

[0060] FIG. 5 is a flowchart of a transmission control method according to an embodiment of the present application;

[0061] FIG. 6 is a schematic diagram corresponding to embodiment 5 of the present application;

[0062] FIG. 7a is a schematic diagram corresponding to embodiment 6 of the present application;

[0063] FIG. 7b is a schematic diagram corresponding to embodiment 7 of the present application;

[0064] FIG. 7c is a schematic diagram corresponding to embodiment 8 of the present application;

[0065] FIG. 8 is a structural diagram of a transmission control apparatus according to an embodiment of the present application;

[0066] FIG. 9 is a structural diagram of a communication device according to an embodiment of the present application;

[0067] FIG. 10 is a structural diagram of a terminal according to an embodiment of the present application;

[0068] FIG. 11 is a structural diagram of a network-side device according to an embodiment of the present application;

[0069] FIG. 12 is a structural diagram of another network-side device according to an embodiment of the present application. DETAILED DESCRIPTION

[0070] The technical solutions in the embodiments of the present application will be described clearly below with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only some of the embodiments of the present application, rather than all the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art belong to the scope of protection of the present application.

[0071] The terms "first," "second," etc., used in this application are used to distinguish similar objects and not to describe a specific order or sequence. It should be understood that such terms can be used interchangeably where appropriate so that embodiments of this application can be implemented in orders other than those illustrated or described herein, and the objects distinguished by "first" and "second" are generally of the same class, not limited in number; for example, the first object can be one or more. Furthermore, "or" in this application indicates at least one of the connected objects. For example, the scope of protection for "A or B" covers at least three scenarios: Scenario 1: including A but not B; Scenario 2: including B but not A; Scenario 3: including both A and B. In addition, the terms "A and / or B," "at least one of A and B," and "at least one of A or B" also cover at least the above three scenarios. The character " / " generally indicates that the preceding and following objects are in an "or" relationship.

[0072] The term "instruction" in this application can be either a direct instruction (or explicit instruction) or an indirect instruction (or implicit instruction). A direct instruction can be understood as one in which the sender explicitly informs the receiver of specific information, the operation to be performed, or the requested result, etc., in the instruction sent. An indirect instruction can be understood as one in which the receiver determines the corresponding information based on the instruction sent by the sender, or makes a judgment and determines the operation to be performed or the requested result, etc., based on the judgment result.

[0073] It is worth noting that the technology described in the embodiments of the present application is not limited to Long Term Evolution (LTE) / LTE-Advanced (LTE-A) systems, but can also be used in other wireless communication systems, such as Code Division Multiple Access (CDMA), Time Division Multiple Access (TDMA), Frequency Division Multiple Access (FDMA), Orthogonal Frequency Division Multiple Access (OFDMA), Single-carrier Frequency-Division Multiple Access (SC-FDMA) or other systems. The terms "system" and "network" in the embodiments of the present application are often used interchangeably, and the described technology can be used in the above-mentioned systems and radio technologies, as well as in other systems and radio technologies. The following description describes a New Radio (NR) system for the purpose of example, and NR terminology is used in most of the following description, but these technologies can also be applied to systems other than NR systems, such as 6th Generation (6G) communication systems.

[0074] FIG. 1 shows a block diagram of a wireless communication system to which embodiments of the present application can be applied. The wireless communication system includes a terminal 11 and a network-side device 12. The terminal 11 can be a terminal-side device such as a mobile phone, a Tablet Personal Computer, a Laptop Computer, a notebook computer, a Personal Digital Assistant (PDA), a palmtop computer, a netbook, an Ultra-mobile Personal Computer (UMPC), a Mobile Internet Device (MID), an Augmented Reality (AR) device, a Virtual Reality (VR) device, a robot, a wearable device, a flight vehicle, a Vehicle User Equipment (VUE), a shipboard device, a Pedestrian User Equipment (PUE), a smart home (a home device with a wireless communication function such as a refrigerator, a television, a washing machine, or furniture), a game console, a Personal Computer (PC), a kiosk, or a self-service machine. The wearable device includes a smart watch, a smart bracelet, a smart earphone, smart glasses, smart jewelry (a smart bracelet, a smart necklace, a smart ring, a smart necklace, a smart anklet, a smart necklace, etc.), a smart wristband, smart clothes, etc. The vehicle-mounted device can also be referred to as a vehicle-mounted terminal, a vehicle-mounted controller, a vehicle-mounted module, a vehicle-mounted component, a vehicle-mounted chip, or a vehicle-mounted unit, etc. It should be noted that the specific type of the terminal 11 is not limited in the embodiments of the present application. The network-side device 12 can include an access network device or a core network device. The access network device can also be referred to as a Radio Access Network (RAN) device, a radio access network function, or a radio access network unit. The access network device can include a base station, a Wireless Local Area Network (WLAN) Access Point (AP), or a Wireless Fidelity (WiFi) node, etc.The base station can be referred to as a Node B (NB), an evolved Node B (eNB), a next generation Node B (gNB), a New Radio Node B (NR Node B), an access point, a relay station (RBS), a serving base station (SBS), a base transceiver station (BTS), a radio base station, a radio transceiver, a basic service set (BSS), an extended service set (ESS), a home Node B (HNB), a home evolved Node B, a transmit / receive point (TRP), or some other suitable terminology in the art, and is not limited to a particular technical terminology, provided that the same technical effect is achieved. It should be noted that in the embodiments of the present application, only the base station in the NR system is taken as an example for introduction, and the specific type of the base station is not limited.

[0075] The core network device can also be referred to as a core network node, a core network function, or a core network network element, etc., which includes but is not limited to at least one of the following: a mobility management entity (MME), an access and mobility management function (AMF), a session management function (SMF), a user plane function (UPF), a policy control function (PCF), a policy and charging rules function (PCRF), an edge application server discovery function (EASDF), a unified data management (UDM), a unified data repository (UDR), a home subscriber server (HSS), a centralized network configuration (CNC), a network repository function (NRF), a network exposure function (NEF), a local NEF (L-NEF), a binding support function (BSF), an application function (AF), a location management function (LMF), a gateway mobile location center (GMLC), a network data analytics function (NWDAF), etc. It should be noted that only the core network device in the NR system is taken as an example for introduction in the embodiments of the present application, and the specific type of the core network device is not limited. If the name of the core network device mentioned in the embodiments of the present application changes in the subsequent protocol version (for example, 6G), it is also within the protection scope of the present application.

[0076] Optionally, the core network device can be implemented by one or more function modules in one device, or can be implemented by multiple devices jointly, and the embodiments of the present application do not make a specific limitation hereon. It can be understood that the above function modules can be network elements in a hardware device, can be software function modules running on a dedicated hardware, or can be virtualized function modules instantiated on a platform (for example, a cloud platform).

[0077] Before the embodiments of the present application are described, the related art is briefly introduced as follows:

[0078] I. On cell selection and cell reselection

[0079] In the cell selection and reselection process, the cell can be divided into the following four categories:

[0080] Acceptable cell: a cell that can meet the minimum access requirements according to the cell selection criteria (i.e., S criteria).

[0081] Suitable cell: a cell that can provide normal service to the UE according to the S criteria, and the public land mobile network (PLMN) to which the cell belongs is consistent with the UE subscription data. The PLMN can uniquely identify a communication operator, which is composed of a mobile country code (MCC) and a mobile network code (MNC).

[0082] Reserved cell: a cell indicated as reserved in the system information.

[0083] Barred cell: a cell indicated as barred in the system information.

[0084] Cell selection criteria (S criteria) are as follows:

[0085] In the cell selection process, the terminal needs to measure the cell to be selected, so as to perform channel measurement, perform channel quality evaluation, and judge whether it meets the standard of camping. The measurement criteria of cell selection are referred to as S criteria. When the channel quality and signal strength of a certain cell meet the S criteria, it can be selected as a camping cell. The S criteria are met, i.e., Srxlev>0 and Squal>0. Wherein, the S criteria power standard is: the received power Srxlev>0, and the S criteria quality standard is: the accepted signal quality Squal>0 in cell search.

[0086] Srxlev=Qrxlevmeas-(Qrxlevmin+Qrxlevminoffset)-Pcompensation-Qoffsettemp

[0087] Srxlev: Cell selection received level value.

[0088] Qrxlevmeas: Measured cell's received level value / signal strength (e.g. Reference Signal Received Power (RSRP)).

[0089] Qrxlevmin (network side configuration): Cell minimum received level. Increasing this value for a cell makes it more difficult for the cell to meet the S criterion, makes it more difficult for the cell to become a suitable cell, and makes it more difficult for the UE to select the cell, and vice versa. The value of this parameter should be such that the selected cell can provide the signal quality requirement of basic class service.

[0090] Qrxlevminoffset (network side configuration): Cell minimum received level offset. This parameter is only used when the UE is camped on a VPLMN and cell selection is triggered due to periodic search for high priority PLMN. Increasing this value for a cell makes it more difficult for the cell to meet the S criterion, makes it more difficult for the cell to become a suitable cell, and makes it more difficult for the UE to select the cell, and vice versa.

[0091] Pcompensation (network side configuration): Used to penalize the UE that does not reach the cell maximum power. When the UE maximum allowed transmit power is less than or equal to the UE capability supported maximum transmit power, Pcompensation = 0. When the UE maximum allowed transmit power is greater than the UE capability supported maximum transmit power, Pcompensation = UE maximum allowed transmit power - UE capability supported maximum transmit power.

[0092] Qoffsettemp (network side configuration): Temporary offset applied to the current cell. This value is configured in RRC with the ConnEstFailOffset parameter and is used for connection failure control.

[0093] Squal = Qqualmeas - (Qqualmin + Qqualminoffset) - Qoffsettemp

[0094] Squal: Cell selection quality value.

[0095] Qqualmeas: Measured cell quality value (e.g. Reference Signal Received Quality (RSRQ)).

[0096] Qqualmin (network side configuration): minimum received signal quality. This parameter represents the minimum received signal quality required for reselection, and is used to control the difficulty of cell reselection. This parameter is issued in system message 5. Increasing the value of a certain cell makes it more difficult to meet the S criterion, making it more difficult to become a suitable cell, and increasing the difficulty of the UE selecting the cell, and vice versa.

[0097] Qqualminoffset (network side configuration): minimum received signal quality offset value. This parameter represents the minimum received signal quality offset of a cell, and is applied to the cell selection criterion (S criterion) formula. This parameter is only used when the UE is camped on a VPLMN and cell selection is triggered due to periodic search for high priority PLMNs. Increasing the value of a certain cell makes it more difficult to meet the S criterion, making it more difficult to become a suitable cell, and increasing the difficulty of the UE selecting the cell, and vice versa.

[0098] Qoffsettemp (network side configuration).

[0099] The cell reselection criterion (R criterion) is as follows:

[0100] When the UE is in the idle state / activated state, after cell selection, the UE needs to continuously monitor the signal quality of the neighboring cells and the current cell in order to camp on a cell with higher priority or better channel quality. When the signal quality of a neighboring cell meets the S criterion and certain reselection decision criteria are met, the UE will access the cell for camping.

[0101] Measurement criteria for cell reselection:

[0102] After the UE successfully camps, it will continue to perform measurements on the current cell. In order to reduce the UE energy consumption caused by measurements as much as possible, the radio resource control (RRC) layer calculates the S criterion based on the RSRP / RSRQ measurement results, and compares it with the intra-frequency measurement start threshold (Sintrasearch) and the inter-frequency measurement start threshold (Snonintrasearch) as a decision condition for whether to start neighboring cell measurements.

[0103] The UE measures the signal of the serving cell and detects the signal strength Srxlev or quality Squal of the serving cell.

[0104] Intra-frequency measurement start criterion: Srxlev <= Sintrasearch or Squal <= Snonintrasearch.

[0105] Inter-frequency measurement start criterion (for the same priority or lower priority frequency point): Srxlev <= Snonintrasearch or Squal <= Sintrasearch.

[0106] In the reselection process, the network can achieve the purpose of controlling the UE to camp by setting the priority of different frequency points; the UE will select the cell with the best channel quality on a certain frequency point to provide the best service. There are three ways for the UE to obtain the frequency point priority information it needs to use:

[0107] (1) System information: for a certain frequency point, the corresponding absolute priority is provided in the system information;

[0108] (2) RRC Release message: if the frequency point priority is provided by dedicated RRC signaling, the priority in the system information (SI) is ignored;

[0109] (3) Inherited from other radio access technologies (RAT).

[0110] The intra-frequency and inter-frequency cell reselection criteria (R-criteria) are as follows:

[0111] The cell ranking criteria are defined as follows, where Rs is for the serving cell and Rn is for the neighbor cell.

[0112] Rs = Qmeas,s + Qhyst - Qoffsettemp

[0113] Rn = Qmeas,n - Qoffset - Qoffsettemp

[0114] Qmeas: RSRP measurement.

[0115] Qoffset: bias between the target candidate cell and the currently camped cell. It is used to adjust the difficulty of reselection and reduce ping-pong effects. Under the condition that other parameters are constant, increasing the bias, i.e., increasing the difficulty of intra-frequency or inter-frequency and same priority cell reselection, or vice versa. For intra-frequency reselection, this parameter is equal to Qoffsets,n between cells (Qoffsets,n exists in system broadcast) or 0 (Qoffsets,n does not exist in system broadcast). For inter-frequency reselection, this parameter is equal to 'inter-frequency Qoffsetfrequency + Qoffsets,n between cells' (Qoffsets,n exists in system broadcast) or 'inter-frequency Qoffsetfrequency' (Qoffsets,n does not exist in system broadcast).

[0116] Qhyst: hysteresis value of the serving cell measurement quantity. This parameter is related to the slow fading characteristics of the environment where the cell is located. The larger the slow fading variance, the larger the hysteresis value should be. The larger the hysteresis value, the larger the border of the serving cell, and the more difficult it is to reselect to a neighbor cell. This value is used to adjust the difficulty of reselection and reduce ping-pong effects. If the value is configured too large, it can easily lead to a failure to reselect in time, and if the terminal initiates connection establishment at this time, it can cause the RRC connection establishment to fail.

[0117] II. Artificial Intelligence (AI)

[0118] AI can be represented as machine learning (ML). AI has been widely applied in various fields. Integrating artificial intelligence into wireless communication networks significantly improves technical indicators such as throughput, latency, and user capacity, which is an important task for future wireless communication networks. AI modules have various implementation methods, such as neural networks, decision trees, support vector machines, and Bayesian classifiers.

[0119] Neural Network:

[0120] Figure 2a is a schematic diagram of a neural network, which is composed of neurons. Figure 2b is a schematic diagram of a neuron, where a1, a2, … aK are inputs, w is a weight (multiplicative coefficient), b is a bias (additive coefficient), and σ(.) is an activation function. Common activation functions include Sigmoid, tanh, linear rectification functions (such as rectified linear units (ReLU)), and the like.

[0121] The parameters of the neural network are optimized by a gradient optimization algorithm. Gradient optimization algorithms are a class of algorithms that minimize or maximize an objective function (sometimes also called a loss function), which 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 and b to minimize the value of the loss function above. The smaller the loss value, the closer our model is to the true situation.

[0122] The common optimization algorithm is basically based on error back propagation (BP) algorithm. The basic idea of BP algorithm is that the learning process consists of two processes of forward propagation of signals and backward propagation of errors. When forward propagation, 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 error is entered. 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 weight of each unit. The weight adjustment process of each layer of the signal forward propagation and the error backward propagation is repeated. The process of continuously adjusting the weight 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 the learning time reaches the preset learning time.

[0123] The common optimization algorithm includes gradient descent, stochastic gradient descent (SGD), mini-batch gradient descent, momentum method, Nesterov (the name of the inventor, specifically stochastic gradient descent with momentum), adaptive gradient descent (Adagrad), Adadelta, root mean square prop (RMSprop), adaptive moment estimation (Adam), etc.

[0124] These optimization algorithms, when error back propagation, are based on the error / loss obtained from the loss function, and the derivative / partial derivative of the current neuron is added to the learning rate, the previous gradient / derivative / partial derivative, etc. to obtain the gradient, and the gradient is transmitted to the previous layer.

[0125] Generally speaking, according to the difference of solution types, the selected AI algorithm and the adopted AI model also have some differences. According to the 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 algorithm or processing module by means of neural network-based algorithm and AI model. In a specific scenario, neural network-based algorithm and AI model can achieve better performance than deterministic algorithm. Commonly used neural networks include deep neural network, convolutional neural network and recurrent neural network, etc. With the help of existing AI tools, the construction, training and verification of neural network can be realized.

[0126] Fine-tuning related background:

[0127] In practice, it is difficult to achieve convergence by directly training neural networks due to the insufficient size of real-time collected data sets. A common approach is to pre-train the network based on a large amount of offline collected data, so that it converges. Then use real-time collected data to fine-tune the pre-trained neural network parameters, so that the neural network adapts to the actual environment. Fine-tuning can be considered as a training process that uses the pre-trained neural network parameters as initialization. In the fine-tuning stage, the parameters of some layers can be frozen, usually 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, and only a small number of layers close to the output end are fine-tuned.

[0128] Generalization problem of neural network:

[0129] Generalization refers to the ability of a neural network to produce reasonable outputs for data that was not encountered during the training (learning) process. To address the generalization problem caused by the variability of wireless transmission environments, there are two solutions for neural network-based wireless communication systems. The first solution is to train different neural networks under different transmission conditions, 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 requires storing multiple network parameters and switching 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 cannot achieve optimal performance under each transmission condition. The way of constructing mixed data sets will affect the performance of the second solution.

[0130] Label:

[0131] In machine learning and deep learning, labels usually refer to the identification or annotation of the true class or target value of a data sample. Labels are used to represent the information that the model should learn and predict, such as:

[0132] Labels in classification tasks: In classification tasks, labels represent which category a data sample belongs to. For example, in image classification, each image sample has a label indicating the class of objects or scenes contained in the image, such as "dog" or "cat".

[0133] Labels in object detection: In object detection tasks, labels usually include object location information (bounding box) and class information. Each label identifies a target object in an image, including its location and class.

[0134] Labels in regression tasks: In regression tasks, labels typically represent continuous or real-valued targets to be predicted. For example, the label in a house price prediction task could be the actual sale price of a house.

[0135] Labels in sequence labeling: In natural language processing, labels in sequence labeling tasks are typically used for tasks such as part-of-speech tagging, named entity recognition, etc., where labels are used to represent the properties or categories of each word or character in a text sequence.

[0136] Labels are a key component in supervised learning tasks, used to train machine learning models. Models learn patterns and rules through comparison with true labels in order to make predictions or classifications on unseen data. The quality and accuracy of labels are crucial for the performance of models.

[0137] AI life cycle management (LCM):

[0138] The life cycle management of AI / ML models includes multiple AI functional modules: model training, model deployment, model inference, model monitoring, model updating. Figure 3 shows the specific operation framework of AI / ML models.

[0139] Model training

[0140] Performing AI model training, validation, and testing can generate model performance metrics that can be used as part of the model testing process. If needed, this function is also responsible for data preparation (e.g., data preprocessing and cleaning, formatting, and conversion) based on the training data provided by the data collection function.

[0141] Training / Updating models: If there is a model storage function, it is used to transfer the trained, validated, and tested AI models to the model storage function, or to transfer updated versions of the models to the model storage function.

[0142] Model management

[0143] Supervising AI models or issuing AI functions (such as model selection / (de)activation / switching / fallback), feeding back model monitoring performance. This module is also responsible for making decisions based on data received from the data collection module and the inference module to ensure correct inference operations.

[0144] Management instructions: Information input by the model management function to the model inference function. Relevant information may include AI models or AI / ML-based functions to select / (de)activate / switch models, fallback to non-AI / ML operations (i.e., not dependent on inference processes), etc.

[0145] Model transfer request: used to request models from the model storage function.

[0146] Performance feedback / re-training request: The model training function inputs information required, e.g., for model (re-)training or update purposes.

[0147] Model inference

[0148] The inference function provides the output of applying the AI model using the data provided by the data collection function as input. If needed, the inference function is also responsible for data preparation (e.g., data pre-processing and cleaning, formatting and conversion) based on the inference data provided by the data collection function.

[0149] Inference output: The management function uses data for monitoring the performance of the AI model or the AI / ML function.

[0150] III. About Cell Search

[0151] Cell search is the process by which a UE acquires time and frequency synchronization to a cell and decodes the cell ID of the cell. The main purposes of cell search include:

[0152] 1. Acquire frequency and symbol synchronization (downlink synchronization) with the cell.

[0153] 2. Acquire system frame timing, i.e., the starting position of the downlink frame.

[0154] 3. Determine the physical cell identity (PCI) of the cell.

[0155] NR cell search is based on the primary synchronization signal (PSS) and secondary synchronization signal (SSS) and the physical broadcast channel (PBCH) demodulation reference signal (DMRS) located on the synchronization raster. The overall process of NR cell search can be divided into the following steps:

[0156] 1. The UE tunes to a specific frequency and only measures the received signal strength indication (RSSI).

[0157] 2. The UE attempts to detect SSB and decode PSS, SSS. If the UE fails at this step, it goes to step 1, and if it passes at this step, it goes to the next step.

[0158] 3. Once the UE successfully detects PSS / SSS, the UE attempts to decode PBCH.

[0159] 4. Once the UE successfully detects PBCH, it decodes Master Information Block (MIB).

[0160] 5. Based on pdcch-ConfigSIB1 in MIB, find the location of Control Resource Set #0 (CORESET #0) (i.e. CORESET for Physical downlink control channel (PDCCH) / Downlink Control Information (DCI) for System Information Block 1 (SIB1) transmission) and Search Space information.

[0161] 6. Blind decode DCI 1_0 scrambled with System Information Radio Network Temporary Identifier (SI-RNTI) in Search Space.

[0162] 7. Based on the content of DCI 1_0, detect and decode Physical downlink shared channel (PDSCH) carrying SIB1.

[0163] 8. Decode SIB1 and other SIBs (if SIB1 carries information about other SIBs).

[0164] UE needs to perform cell search not only at power on, but also to support mobility, UE keeps searching neighbor cells, acquiring synchronization and estimating the received quality of the cell signal, so as to decide whether to handover (when UE is in RRC_CONNECTED state) or cell re-selection (when UE is in RRC_IDLE state).

[0165] The Synchronization Signal Block (SSB) subcarrier spacing is determined by the frequency range: 6GHz and below (i.e. Frequency Range 1 (FR1)) supports 15 or 30kHz subcarrier spacing (SCS), 6GHz and above (i.e. FR2) supports 120 or 240kHz SCS. UE knows N_ID_(2) from PSS and N_ID_(1) from SSS, then the cell ID (e.g. PCI) is: N_cell_ID = 3*N_ID_(1) + N_ID_(2). Where N_ID_(2) takes values in {0, 1, 2}, N_ID_(1) takes values in {0, 1, … 335}, NR has 336*3 = 1008 N_cell_IDs, taking values in {0, 1, …, 1007}. For most bands in FR1, only one SSB SCS is supported, UE determines the band, and at the same time knows the SSB SCS. But there are some bands such as n5 / n41 / n66 / n90 that support two SSB SCS (15kHz and 30kHz), UE needs to use two SCSs to perform blind detection respectively to determine the SSB SCS of the cell. FR2 n257 / 258 / 259 / 260 / 261 all support 120 / 240kHz, at this time only two SCSs can be tried respectively to determine the SCS.

[0166] Four, about Sync raster

[0167] Channel raster can be understood as the optional position of the center frequency point 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, the frequency domain range is 0-100GHz, which is mainly used to identify the frequency domain location of RF channels, SSBs or other resources.

[0168] NR Absolute Radio Frequency Channel Number (NR-ARFCN) encodes the frequency domain range of the RF reference frequency, 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: FREF = FREF-Offs + AFGlobal(NREF-NREF-Offs). The ARFCN frequency point number corresponds to the channel raster. The channel raster has different interval densities in different NR bands (bands).

[0169] Table 1 Parameters of the global frequency grid of NR-ARFCN

[0170] In NR, if the UE searches for synchronization signals according to the channel raster, it takes a long time and consumes a lot of power because the channel bandwidth can be very large. Therefore, NR introduces the concept of synchronization raster (Synchronization raster), and the synchronization signal is placed according to the synchronization raster.

[0171] The Global Synchronization Channel Number (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 UE can only blindly detect the SSB at the GSCN position. Similarly, as shown in Table 2, 0-100GHz corresponds to 0-26639 GSCNs.

[0172] Table 2 GSCN parameters of the global frequency grid for channel bandwidths greater than 3MHz

[0173] 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 is different for different bands. 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.

[0174] Five, about Synchronization Signal Block (SSB)

[0175] In NR, PSS / SSS and PBCH are always bundled, so it is also called SSB. One SSB occupies 4 symbols (time indices l=0~3) in time domain and 240 contiguous subcarriers (20 RBs) in frequency domain. The center frequency of the 121st subcarrier SC in frequency domain is the GSCN corresponding to the SSB REF In NR, the time domain and frequency domain positions of SSB are no longer fixed, but flexible and variable. In frequency domain, SSB is no longer fixed in the middle of the frequency band; in time domain, the position and number of SSB transmission can change. Therefore, in NR, only by demodulating the PSS / SSS signal, the complete synchronization of the frequency domain and 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.

[0176] Cell-defining SSB (CD-SSB) or non cell-defining SSB (NCD-SSB):

[0177] In the NR system, CD-SSB is defined as the SSB associated with SIB1 (also known as Remaining Minimum SI (RMSI)). SIB1 defines the scheduling information of other SIBs and contains information for terminal initial access. The frequency position of CD-SSB must be on the system synchronization raster sync raster.

[0178] NCD-SSB is correspondingly defined as SSB not associated with SIB1. NCD-SSB can be used for secondary cell synchronization or as a measurement signal configured for the terminal. NCD-SSB does not necessarily locate on the system synchronization raster. If NCD-SSB is located on the system synchronization raster, it can indicate the GSCN of CD-SSB through the information it carries.

[0179] When the UE detects an SSB during cell search, the UE first needs to determine whether the SSB is CD-SSB or NCD-SSB. The determination is made according to the subcarrier offset k SSB provided by the PBCH of the SSB, which represents the subcarrier offset between the SSB and the common resource block grid. The valid subcarrier offset value range includes 0-23 and 0-11 subcarriers, which are represented by 5 bits and 4 bits respectively, corresponding to frequency range FR1 and FR2 respectively. If the value of k SSB is within the valid subcarrier offset value range, the SSB is CD-SSB, otherwise it is NCD-SSB.

[0180] In FR1, if kSSB >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 CD-SSB quickly, these k SSB It can also be used as an index, in conjunction with the RMSIPDCCH Config (MIB's PDCCH Config SIB1), to (indirectly) indicate the GSCN of the next SSB.

[0181] When the value k SSB =31(FR1) or k SSB When 15 (FR2) is reached, the UE considers that CD-SSB does not exist within a certain GSCN range.

[0182] VI. About TRP

[0183] The 3rd Generation Partnership Project (3GPP) proposes multi-TRP / multi-panel scenarios. Multi-TRP transmission can increase transmission reliability and throughput performance; for example, a UE can receive the same or different data from multiple TRPs. The following multi-TRP transmission scenarios are preliminarily discussed:

[0184] 1) Multi-antenna panel transmission within the same TRP (as shown in Figure 4a);

[0185] 2) Multi-TRP / panel transmission between multiple TRPs, ideal backhaul (as shown in Figure 4b);

[0186] 3) Multi-TRP / panel transmission between multiple TRPs, non-ideal backhaul (as shown in Figure 4c).

[0187] 3GPP Release 16 (Rel-16) standardizes multi-TRP / multi-panel scenarios, which can increase the reliability and throughput performance of transmission, for example, a UE can receive the same data or different data from multiple TRPs. Multi-TRPs can be divided into ideal backhaul and non-ideal backhaul. When the backhaul is non-ideal, there is a large delay in the exchange of information between multi-TRPs, which is more suitable for independent scheduling, and the Acknowledgement (ACK) / Negative Acknowledgement (NACK) and Channel State Information (CSI) reports are fed back to each TRP respectively. It is usually applicable to multi-Downlink Control Information (DCI) scheduling, that is, each TRP sends its own PDCCH, and each PDCCH schedules its own PDSCH. Multiple CORESETs configured for a UE are associated with different RRC parameters (such as CORESETPoolIndex), corresponding to different TRPs. Multiple PDSCHs scheduled by multiple DCIs may not overlap, partially overlap, or completely overlap in time and frequency resources. On the overlapping time and frequency resources, each TRP independently precodes according to its own channel, and the UE receives multiple-layer data streams belonging to multiple PDSCHs in a non-coherent joint transmission (NCJT) manner.

[0188] In related technologies, in a multi-cell scenario, when the network is in an energy-saving state, the transmission of some cells or TRPs or SSBs can be turned off. When a UE moves to a neighboring cell or needs to access a better cell to receive better transmission, the network needs to turn on the transmission of the corresponding cell or TRP or SSB to enable the UE to access. At the same time, the UE also needs to perform measurement and cell selection according to the transmission of the corresponding cell or TRP or SSB that is turned on. This scenario has the following problems:

[0189] Problem 1: When the network is in a low-load or low-traffic state, it can turn off some cells or the transmission of the synchronization signals of some cells. When a UE needs to reselect to these cells, the UE needs to perform measurement and evaluation on these cells. If the measurement on the cells that have been turned off or the cells whose synchronization signals have been turned off is performed, the UE still performs the measurement according to the assumption that these cells are turned on and normally transmit synchronization signals, which will cause the UE to waste power consumption.

[0190] Problem 2: When the UE needs to perform cell selection or cell reselection, the neighbor cell needs to be measured, and if the condition of cell selection or cell reselection is met, the terminal will start the corresponding intra-frequency measurement or inter-frequency measurement of cell reselection. If the terminal needs to measure all cells of the neighbor cell, it will consume more terminal power consumption.

[0191] Problem 3: When the UE performs cell reselection, if there is a cell in energy saving mode in the surrounding cells, in principle, the network needs to avoid the terminal selecting the cell in energy saving mode as much as possible. In the related art, the cell in energy saving mode can be indicated by SSB or SIB1 carrying specific information in the payload. This needs the terminal to decode the payload of SSB or SIB1, which may cause an increase in terminal power consumption.

[0192] Problem 4: When the UE performs cell reselection, the network is not clear about when the terminal will perform cell reselection, and when the terminal is in idle state, the network does not even know where the terminal initiates cell reselection.

[0193] In general, the above problems will cause the network or UE and the like to have poor effect in transmission control.

[0194] In view of this, the embodiments of the present application provide a transmission control method, a transmission control device and a communication device to solve the problem of poor effect of devices in transmission control in the related art.

[0195] In order to facilitate understanding, some terms involved in the embodiments of the present application are first explained.

[0196] Synchronization signal: including SSB or SIB, wherein the SSB can include at least one of PSS, SSS, PBCH and MIB. SSB can be used interchangeably with SS / PBCH block, or other names. SSB can also be expressed as downlink reference signal, downlink synchronization signal, SSB burst, SS / PBCH block, etc. SSB can refer to any module containing at least part of the synchronization signal, broadcast signal or other downlink broadcast signal or its control channel, or other reference signals such as Channel State Information Reference Signal (CSI-RS) / Positioning Reference Signal (PRS) and the like.

[0197] AI model: also referred to as AI unit, AI structure, etc., or the AI model can also 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-related hardware such as Graphics Processing Unit (GPU), Neural-network Processing Unit (NPU), tensor processing unit (TPU), Application Specific Integrated Circuit (ASIC), etc. The embodiments of the present application do not make specific limitations.

[0198] The identification (i.e. ID) of the AI model can be the identification of the AI model, the identification of the AI structure, the identification of the AI algorithm, or the identification of a specific data set associated with the AI model, or the identification of a specific scene, environment, channel feature or device related to AI, or the identification of a function, feature, capability or module related to AI. The embodiments of the present application do not make specific limitations. The index of the AI unit can be described in various ways, such as functionality ID, model ID, model physical ID, model logical ID, model global ID or model local ID.

[0199] AI can also represent machine learning (ML), which has various implementation methods, such as neural network, decision tree, support vector machine, Bayesian classifier, etc. The embodiments of the present application do not make specific limitations.

[0200] Server: specifically refers to an entity for training or prediction or providing AI-related information, or can also refer to a service that skips the operator's business (or referred to as Over The Top (OTT), or cross-border operator or third-party service provider or third-party server or Internet, etc.).

[0201] Random Access Channel (RACH): includes Message 1 (Msg1), Physical Random Access Channel (PRACH) or preamble, and can also refer to other signals or channels for uplink access, such as Message A (MsgA), MsgA PRACH, MsgA Physical Uplink Shared Channel (PUSCH), Msg3 PUSCH, Configured Grant (CG) or Dedicated Grant (DG) PUSCH, and the like.

[0202] The transmission control method provided by the embodiments of the present application will be described in detail below in combination with the accompanying drawings, some embodiments and application scenarios.

[0203] FIG. 5 shows a flowchart of a transmission control method according to an embodiment of the present application. As shown in FIG. 5, the transmission control method includes the following steps:

[0204] Step 501: A first device acquires target information, wherein the target information is obtained based on a first model;

[0205] The target information includes at least one of the following:

[0206] Information of a target cell set;

[0207] Target time information, wherein the target time information is used to indicate at least one of the following: time information corresponding to a first procedure, wherein the first procedure includes at least one of cell selection and cell reselection; time information corresponding to measuring a first signal, wherein the first signal includes at least one of a synchronization signal and a reference signal (RS); and time information corresponding to transmitting a second signal, wherein the second signal includes at least one of a wake-up signal, a positioning signal, a sounding signal and a random access message;

[0208] Target transmission information, wherein the target transmission information includes at least one of the following: time domain information of a target synchronization signal set; frequency domain information of the target synchronization signal set; spatial domain information of the target synchronization signal set; index information of the target synchronization signal set; and transmission mode information of the target synchronization signal set;

[0209] Step 502: The first device performs a first operation based on the target information;

[0210] The first operation includes at least one of the following: turning on or off at least one target cell, the target cell including at least one of a physical cell, a carrier, and a TRP; switching a state of at least one target cell; transmitting or receiving at least one target signal, the target signal including at least one of a synchronization signal, a paging signal, and a RACH; performing a second procedure, the second procedure including at least one of cell selection, cell reselection, reselecting or camping on a target cell, switching a target TRP, switching a target TCI configuration, and switching a target RS; and performing a first measurement, the first measurement including a measurement based on at least one target cell.

[0211] The carrier in the embodiments of the present application can also be referred to as a carrier frequency, a frequency point, a frequency band, a frequency band, and the like.

[0212] The TRP in the embodiments of the present application can also be referred to as an antenna panel.

[0213] The first device in the embodiments of the present application can be any communication device, including a terminal or a network side device, that is, the first device can be a terminal (such as a non-connected terminal) or a network side device. The network side includes at least one of a base station device and a core network device (such as a core network device specially used for model training). The network side device can be a terminal current service cell, or a cell device / core network device that is last camped or accessed, or a cell device / core network device that sends RRC release information.

[0214] As an example, in the case where the first device is a terminal, the first operation includes at least one of the following:

[0215] Transmitting or receiving at least one target signal, the target signal including at least one of a synchronization signal, a paging signal, and a RACH;

[0216] Performing a second procedure, the second procedure including at least one of cell selection, cell reselection, reselecting or camping on a target cell, switching a target TRP, switching a target TCI configuration, and switching a target RS;

[0217] Performing a first measurement, the first measurement including a measurement based on at least one target cell.

[0218] As another example, in the case where the first device is a network side device, the first operation includes at least one of the following:

[0219] Turning on or off at least one target cell, the target cell including at least one of a physical cell, a carrier, and a TRP;

[0220] switching a state of at least one target cell;

[0221] transmitting or receiving at least one target signal, the target signal comprising at least one of a synchronization signal, a paging signal, and a RACH.

[0222] It should be noted that the cell reselection included in the second flow and the reselection to the target cell can be different in understanding, for example, the cell reselection can be understood as reselecting to a certain cell (which is an unknown, pending cell), and the reselection to the target cell can be understood as reselecting to a target cell that has been determined.

[0223] In the embodiments of the present application, the first model can be understood as an AI model. The target information can be understood as the result obtained by the first model prediction (or reasoning), therefore, the target information can also be called the prediction result, the reasoning result or the target result.

[0224] The target cell set can include one or more cells. The target information includes the information of the target cell set, which can be understood as that the first model can predict the target cell set, i.e., the first model has the ability to predict the target cell set.

[0225] The target information includes target time information, which can be understood as that the first model can predict the target time, i.e., the first model has the ability to predict the target time.

[0226] The target transmission information can be understood as information used to determine the transmission parameters and / or transmission modes of the target synchronization signal set, which can include one or more synchronization signals (such as one or more SSBs). The target information includes the target transmission information, which can be understood as that the first model can predict the transmission parameters and / or transmission modes of the target synchronization signal set, i.e., the first model has the ability to predict the transmission parameters and / or transmission modes of the target synchronization signal set.

[0227] The first operation can be understood as some operations related to transmission control, for example, starting or closing at least one target cell, which can be understood as starting or closing the transmission of at least one target cell; switching the state of at least one target cell, which can be understood as switching the transmission state of at least one target cell.

[0228] Exemplarily, the first operation includes at least one of the following:

[0229] Starting a target cell (frequency, frequency layer, TRP); (this operation can be applicable to a network side device)

[0230] Switching the state of a target cell, for example, from an energy saving state to a normal state; (this operation can be applicable to a network side device)

[0231] start SSB or SIB transmission of the target cell; (this operation can be applicable to network side device)

[0232] start SSB or SIB transmission of the target cell based on the SSB transmission mode inferred by the AI model; (this operation can be applicable to network side device)

[0233] perform RACH reception in the cell corresponding to the target cell; (this operation can be applicable to network side device)

[0234] perform paging transmission in the cell corresponding to the target cell; (this operation can be applicable to network side device)

[0235] perform measurement based on the target cell; (this operation can be applicable to terminal)

[0236] perform transmission or reception of SSB / SIB of the target cell based on the SSB transmission mode inferred by the first model; (this operation can be applicable to terminal)

[0237] reselect or camp to the target cell; (this operation can be applicable to terminal)

[0238] initiate random access procedure in the target cell and perform RACH transmission; (this operation can be applicable to terminal)

[0239] perform paging reception in the target cell; (this operation can be applicable to terminal)

[0240] trigger reselection procedure of the target cell; (this operation can be applicable to terminal)

[0241] trigger reselection measurement of the target cell; (this operation can be applicable to terminal)

[0242] switch to the target TRP; (this operation can be applicable to terminal)

[0243] switch to the target TCI / Reference RS. (this operation can be applicable to terminal)

[0244] The RACH transmission can include RACH: Msg1, PRACH, preamble, or other uplink access signals or channels such as MsgA, MsgA PRACH, MsgA PUSCH, Msg3 PUSCH, CG PUSCH, or DG PUSCH, etc.

[0245] The target cell in the embodiments of the present application can be a cell included in the target cell set, or can be a cell not included in the target cell set. That is, the first device is not limited to performing the above-mentioned first operation on the cell in the target cell set, and the first device can also perform the above-mentioned first operation on the cell outside the target cell set. For example, the target cell set includes a first cell, the at least one target cell includes a second cell, the first cell and the second cell are the same cell, or the first cell and the second cell are different cells.

[0246] The target cell, the target signal, the target TRP, the target TCI configuration, and the target RS in the embodiments of the present application can be obtained based on the first model prediction (or inference), or be determined based on the prediction result (or inference result) of the first model.

[0247] In the embodiments of the present application, the first device obtains target information, the target information is obtained based on the first model; the first device performs a first operation based on the target information; wherein the target information includes at least one of the following: information of a target cell set; target time information, the target time information is used to indicate at least one of the following: time information corresponding to a first process; time information corresponding to measuring a first signal; time information corresponding to transmitting a second signal; target transmission information, the target transmission information includes at least one of the following: time domain information of a target synchronization signal set; frequency domain information of the target synchronization signal set; spatial domain information of the target synchronization signal set; index information of the target synchronization signal set; transmission mode information of the target synchronization signal set; the first operation includes at least one of the following: turning on or off at least one target cell; switching the state of at least one target cell; transmitting or receiving at least one target signal; performing a second process; performing a first measurement, the first measurement includes measuring based on at least one target cell; wherein the first process includes at least one of cell selection and cell reselection; the first signal includes at least one of a synchronization signal and an RS; the second signal includes at least one of a wake-up signal, a positioning signal, a sounding signal, and a random access message; the second process includes at least one of cell selection, cell reselection, reselecting or camping on a target cell, switching a target TRP, switching a target TCI configuration, and switching a target RS; the target cell includes at least one of a physical cell, a carrier, and a TRP; the target signal includes at least one of a synchronization signal, a paging signal, and RACH. In this way, since the first device can obtain target information obtained based on the first model, these target information can provide a basis for the first device to perform transmission control related operations (i.e. the first operation), thereby improving the effect of the first device on transmission control.

[0248] In some embodiments, the information of the target cell set is used to indicate at least one of the following: at least one target reselection cell; at least one target camping cell; at least one target measurement cell.

[0249] For the convenience of distinction, the target cell set can be divided into three types as follows:

[0250] The first target cell set includes potential reselection cells (frequencies, frequency layers or TRPs) (i.e. target reselection cells).

[0251] The second target cell set includes potential measurement cells (i.e. target measurement cells), which can be understood as cells to be measured for corresponding synchronization signals. Optionally, the target measurement cell is a cell for synchronization signal transmission and / or RS transmission. Here, for synchronization signal transmission and / or RS transmission can be understood or replaced by containing synchronization signal transmission and / or RS transmission, or, there is synchronization signal transmission and / or RS transmission, or, has synchronization signal transmission and / or RS transmission, or, supports synchronization signal transmission and / or RS transmission.

[0252] The third target cell set includes cells that can be camped (i.e. target camping cells).

[0253] That is, the first model can predict the set of potential reselection cells, the set of potential measurement cells, and the set of potential camping cells.

[0254] The target cell can be any one or more of the first target cell set, the second target cell set or the third target cell set.

[0255] In this way, the first device can know through the first model which cells the terminal can reselect to, which cells the terminal can measure, and which cells the terminal can camp on, so that the first device can perform relevant transmission control operations based on the prediction results of the first model, thereby improving the effect of the first device in transmission control.

[0256] In some embodiments, the time domain information of the target synchronization signal set comprises at least one of: a system frame number (SFN) of the target synchronization signal set; a reference time position of the target synchronization signal set; a periodicity of the target synchronization signal set; an interval between synchronization signals of the target synchronization signal set; a starting time or an ending time of the target synchronization signal set; a number of the target synchronization signal set, e.g., a number of synchronization signals within one synchronization signal period, or a number of synchronization signal periods of multiple synchronization signal periods, etc.

[0257] In some embodiments, the frequency domain information of the target synchronization signal set comprises at least one of: a synchronization raster corresponding to the target synchronization signal set; a center frequency point of the target synchronization signal set; a frequency band corresponding to the target synchronization signal set.

[0258] The frequency domain information can be an absolute value, or a relative value. The reference frequency domain point of the relative value can be a frequency domain position of a preset cell or a preset synchronization signal. The preset cell can be a currently accessed cell, or a preconfigured given cell. The frequency domain position of the preset synchronization signal can be a frequency domain position (or frequency point) of a synchronization signal of a current cell.

[0259] In some embodiments, the spatial domain information of the target synchronization signal set comprises at least one of: a spatial characteristic of the target synchronization signal set; a beam direction of the target synchronization signal set; a TRP corresponding to the target synchronization signal set.

[0260] The spatial characteristic can comprise at least one of: an associated reference signal, a spatial relation, a TCI state, and quasi co-location (QCL). The TCI state refers to that a network indicates that a DMRS antenna port of a downlink channel PDCCH and PDSCH and a certain downlink RS (SSB / CSI-RS) are quasi co-located. The description of the quasi co-location of the PDCCH, the PDSCH and the SSB / CSI-RS has the same meaning as the description of the quasi co-location of the DMRS (antenna port) of the PDCCH, the PDSCH and the SSB / CSI-RS, or the quasi co-location attributes between the two are the same. The attributes of the quasi co-location include at least one of: Doppler shift, Doppler spread, average delay, delay spread, and spatial RX parameters.

[0261] In some embodiments, the transmission mode information is used to indicate at least one of: whether a SIB is included; whether a synchronization signal is transmitted on-demand; whether the cell is allowed to be accessed; whether the cell is allowed to be camped on.

[0262] In this way, the first device can learn the transmission parameters and / or transmission mode of the target synchronization signal set through the first model, so that the first device can perform relevant transmission control operations based on the transmission parameters and / or transmission mode of the target synchronization signal set predicted by the first model, thereby improving the effect of the first device on transmission control.

[0263] In some embodiments, the switching of the state of the at least one target cell includes at least one of:

[0264] switching the state of the at least one target cell from the energy saving state to the normal state or the non-energy saving state;

[0265] switching the state of the at least one target cell from the normal state or the non-energy saving state to the energy saving state.

[0266] The energy saving state can be understood as: only transmitting sparse synchronization signals, or transmitting synchronization signals in a periodic manner greater than or equal to P (P is greater than the period of synchronization signal transmission in the normal state), or transmitting simplified synchronization signals (such as only transmitting synchronization sequences without system information), or only transmitting SSBs (without SIBs), etc.

[0267] The normal state or the non-energy saving state can be understood as: transmitting synchronization signals in a periodic manner less than or equal to L (L is less than the synchronization signal transmission period in the energy saving state, or L is the default period, or L is the minimum period), or transmitting complete synchronization signals (including synchronization sequences and system information).

[0268] In some embodiments, the transmitting or receiving of the at least one target signal includes:

[0269] transmitting or receiving a target signal corresponding to the at least one target cell based on the target transmission information.

[0270] Here, the target signal can include a synchronization signal set or system information.

[0271] For example, transmitting or receiving SSBs / SIBs corresponding to the target cell based on the SSB transmission mode inferred by the first model.

[0272] In some embodiments, the first operation is performed at a target time, and the target time is determined based on at least one of: a predefined or preconfigured time window; a predefined or preconfigured time period; a predefined or preconfigured timer; a predefined or preconfigured time region.

[0273] That is, the first operation is performed in a time window / time period / timer / time area, which is predefined or preconfigured.

[0274] In some embodiments, the first operation is performed in at least one target area, which includes at least one of a target cell, a cell group to which the target cell belongs, a target TRP, a TRP group to which the target TRP belongs, a target frequency point, a target frequency layer, and a target tracking area (TA).

[0275] That is, the first operation is performed on at least one target cell / cell group / TRP / TRP group / frequency layer / frequency point / TA.

[0276] The above-mentioned target frequency point, target frequency layer, target TA, and the like, can be obtained based on the first model prediction (or inference), or determined based on the prediction result (or inference result) of the first model.

[0277] In some embodiments, the first device obtains target information, including:

[0278] The first device predicts target information based on the first model.

[0279] That is, the first device predicts based on the first model (or the first device performs inference of the AI model) to obtain the target information.

[0280] In addition, the first device can also not obtain the target information through the AI model inference, for example, the first device can obtain the target information from the second device, the second device (or other device) performs inference of the AI model to obtain the target information, and then sends the target information to the first device.

[0281] In some embodiments, the first model includes at least one of a first AI module, a second AI module, and a third AI module.

[0282] The first device predicts target information based on the first model, including at least one of:

[0283] Predicting information of the target cell set based on the first AI module;

[0284] Predicting the target time information based on the second AI module;

[0285] Predicting the target transmission information based on the third AI module.

[0286] The first AI module can also be referred to as a first AI function, the second AI module can also be referred to as a second AI function, and the third AI module can also be referred to as a third AI function.

[0287] For example, the first AI function can be used for at least one of the following:

[0288] Predicting a first target cell set, the first target cell set including potential reselection cells (frequencies, frequency layers, or TRPs);

[0289] Predicting a second target cell set, the second target cell set including potential reselection cells to be measured for corresponding synchronization signals;

[0290] Predicting a third target cell set, the third target cell set including cells that can be camped on.

[0291] For example, the second AI function can be used for at least one of the following:

[0292] Predicting a start time / end time of triggering reselection to a target cell;

[0293] Predicting a start time / end time of triggering measurement of corresponding synchronization signals of a target cell;

[0294] Predicting a start time / end time of a first uplink signal transmission, the first uplink signal including an uplink (UL) wake-up signal (WUS), a random access message (such as msg1, msgA, or msg3, etc.), an SRS, a CSI / RSRP report, etc., the first uplink signal being used for wake-up, positioning, measurement, random access, etc.

[0295] For example, the third AI function is used to predict a transmission mode of at least one target cell corresponding to a synchronization signal, including at least one of the following:

[0296] Predicting a time domain position (SFN, reference time, period, interval, start or end time, number, etc.) of a target synchronization signal set;

[0297] Predicting a frequency domain position (Sync raster, frequency, band, etc.) of a target synchronization signal set;

[0298] Predicting a spatial domain feature (spatial characteristic, beam direction, TRP, etc.) of a target synchronization signal set;

[0299] Predicting a related function (whether including SIB1, whether allowing access, whether allowing camping, etc.) of a target synchronization signal set.

[0300] In some embodiments, the method further comprises:

[0301] The first device obtains target configuration information, the target configuration information being used to determine a related parameter of the first model.

[0302] The first device can obtain the target configuration information from a network side device. When the first device is a terminal, the network side device can include a serving cell / TRP of the terminal, or a neighboring cell / TRP of the terminal, etc.

[0303] In some embodiments, the first device obtains the target configuration information, including at least one of the following:

[0304] The first device obtains first configuration information from a serving cell, and the target configuration information includes the first configuration information.

[0305] The first device obtains second configuration information from a neighboring cell, and the target configuration information includes the second configuration information.

[0306] The first configuration information can be carried by SIB or RRC signaling of the serving cell, for example, Cell-specific configuration, including SIB or Paging message, and for example, UE-specific configuration, including RRC release / setup message or Dedicated signaling, etc.

[0307] The second configuration information can be carried by SSB or MIB of the neighboring cell. The SSB of the neighboring cell can be divided into a first SSB set and a second SSB set. The first SSB set is a default SSB set, which can be used to identify the neighboring cell. The second SSB set is an SSB set based on AI model inference transmission, and the transmission behavior of the SSB set is obtained based on AI inference of the first configuration information. Alternatively, the second configuration information can be obtained through information carried by the default SSB set.

[0308] The first device can obtain the target configuration information through any of the above ways alone, or can obtain the target configuration information by combining the first configuration information of the serving cell and the second configuration information of the neighboring cell.

[0309] In this way, the first device can determine the first model based on the target configuration information by obtaining the target configuration information, and thus can perform prediction (or inference) based on the first model.

[0310] In some embodiments, the target configuration information is used to indicate at least one of the following:

[0311] At least one of a cell, a cell group, a TRP, and a TRP group corresponding to the first model;

[0312] at least one of a frequency layer and a frequency point corresponding to the first model;

[0313] TA corresponding to the first model;

[0314] requesting the first model; here, requesting the first model can be understood as requesting the first model to a second device, when the first device is a terminal, the second device may, for example, be a network side device;

[0315] a type of the first model;

[0316] an input parameter of the first model, for example, a measurement value of a serving cell, a measurement value of a neighbor cell, a UE distribution of a serving cell;

[0317] an output parameter of the first model.

[0318] Exemplarily, the target configuration information includes information or parameters such as: a cell (target cell) / cell group / TRP / TRP group / frequency layer / frequency point / TA to which the AI model can be applied; and whether the UE needs to request the AI model from the network. Exemplarily, the UE can request the AI model from the network through a random access message (msg1 or msg3, etc.), and also through uplink control information (Uplink Control Information, UCI), a medium access control control element (Medium Access Control Control Element, MAC CE) or an RRC message, etc.

[0319] The cell / cell group / TRP / TRP group / frequency layer / frequency point / TA to which the AI model can be applied can be determined according to at least one of the following manners:

[0320] According to the configuration of the AI model, if the AI model configuration contains a list (list) of applicable cells / cell groups / TRPs / TRP groups / frequency layers / frequency points / TAs, the list is determined according to the list;

[0321] According to the prediction result of the AI model, if the prediction result of the AI model includes a list of applied cells / cell groups / TRPs / TRP groups / frequency layers / frequency points / TAs, the list is determined according to the list;

[0322] According to the determination of the payload of the SSB or PBCH, the information bits can be predefined to indicate whether the AI model can be applied to the cell / cell group / TRP / TRP group / frequency layer / frequency point / TA corresponding to the reception of the SSB.

[0323] In addition, if there are multiple cells / cell groups / TRPs / TRP groups / frequency layers / frequency points / TAs that meet the conditions predicted by the AI model, the cell / cell group / TRP / TRP group / frequency layer / frequency point / TA that meets the condition predicted by the AI model can be selected according to the RSRP or the highest priority.

[0324] Exemplarily, the target configuration information further includes the configuration of the AI model, specifically including at least one of the following parameters or information:

[0325] The type of the AI model;

[0326] The input parameters of the AI model; for example, the measurement value of the serving cell, the measurement value of the neighbor cell, the UE distribution of the serving cell, the UE distribution of the neighbor cell, etc.

[0327] The output parameters of the AI model; for example, if the AI model is used to predict the transmission parameters of the SSB, the output of the AI model can include: the frequency point of the SSB, the frequency domain starting position, the band, the carrier, the bandwidth part (BWP), the synchronization raster, etc.; the time domain position period, the number, and the pattern (uniform or non-uniform) of the SSB; the SSB monitoring / detection window length (the UE detects the SSB within the monitoring window), the time length of SSB transmission, the number of transmission times or the number of transmission periods, and the position of the first SSB after prediction; the beam direction and the number of the SSB; the SSB transmission mode (if there are multiple modes such as normal mode, simplified mode, and aggregated mode). For another example, if the AI model is used to predict the SSB transmission mode of the target cell that needs to be measured or needs to be reselected, and the target cell is the cell to which the AI model is applied, the output of the AI model can include: which SSB transmission mode the cell is in, or which SSB transmission mode (if there are multiple modes such as normal mode, simplified mode, and aggregated mode) the cell supports; and whether the target cell is transmitting the SSB.

[0328] The frequency / cell / area range to which the AI model can be applied, for example, to a single or multiple frequency layers, to a single or multiple cells (or cell groups), or to the entire TA;

[0329] Whether the UE needs to request the AI model and AI model inference from the network, and the request signal can include a random access message (msg1, msg3, etc.), UCI, MAC CE or RRC message, etc.

[0330] Configuration information of the request signal, such as time domain resource, frequency domain resource, transmission time, period or format, etc.

[0331] In some embodiments, the first device predicts the target information based on the first model, including at least one of the following:

[0332] The first device predicts the target information based on the first model in the case of receiving a first indication, and the first indication is used to indicate that the first device triggers the prediction of the first model;

[0333] The first device predicts the target information based on the first model in the case of meeting a preset condition;

[0334] Among them, the preset condition includes at least one of the following:

[0335] The cell reselection related condition;

[0336] The state related condition of the first device.

[0337] In some embodiments, the cell reselection related condition includes at least one of the following:

[0338] The threshold corresponding to the S criterion power standard is lower than the first preset threshold, or the interval corresponding to the S criterion power standard exceeds the first preset interval;

[0339] The threshold corresponding to the S criterion quality standard is lower than the second preset threshold, or the interval corresponding to the S criterion quality standard exceeds the second preset interval;

[0340] The threshold corresponding to the measurement power value of layer 1 or layer 3 is lower than the third preset threshold, or the interval corresponding to the measurement power value of layer 1 or layer 3 exceeds the third preset interval;

[0341] The threshold corresponding to the measurement quality value of layer 1 or layer 3 is lower than the fourth preset threshold, or the interval corresponding to the measurement power value of layer 1 or layer 3 exceeds the fourth preset interval.

[0342] In some embodiments, the state related condition of the first device includes at least one of the following:

[0343] The first device obtains target configuration information, and the target configuration information is used to determine the related parameters of the first model;

[0344] The first device acquires the target configuration information and acquires transmission parameters of synchronization signals of one or more cells.

[0345] Exemplarily, when the UE performs AI model inference, the AI model triggering manner includes:

[0346] Method 1: The network instructs the UE to trigger AI model prediction, such as through broadcast signaling or dedicated signaling, or through paging DCI / SSB / SIB.

[0347] Method 2: Determine whether to trigger AI model prediction according to preset conditions, the preset conditions including cell reselection related conditions and / or UE current state related conditions, wherein the cell reselection related conditions include at least one of the following:

[0348] The threshold or interval corresponding to the S criterion quality standard is lower than the preset threshold or exceeds the preset interval;

[0349] The threshold or interval corresponding to the S criterion quality standard is lower than the preset threshold or exceeds the preset interval;

[0350] The threshold or interval corresponding to the layer 1 or layer 3 measurement power value (RSRP) is lower than the preset threshold or exceeds the preset interval, such as the RSRP of the serving cell or the RSRP of the reselection cell;

[0351] The threshold or interval corresponding to the layer 1 or layer 3 measurement quality value (RSRQ) is lower than the preset threshold or exceeds the preset interval, such as the RSRQ of the serving cell or the RSRQ of the reselection cell.

[0352] The UE current state related conditions include at least one of the following:

[0353] The UE acquires AI model configuration information (i.e., target configuration information) of the target cell;

[0354] The UE acquires AI model configuration information of the target cell, and acquires transmission parameters and / or transmission modes of synchronization signals of the target cell;

[0355] The UE acquires AI model configuration information of the target cell, and the serving cell where the UE is located does not satisfy the camping condition;

[0356] The UE acquires AI model configuration information of the target cell, the serving cell where the UE is located does not satisfy the camping condition, and the target cell satisfies the camping condition, such as the UE needs to perform cell reselection;

[0357] The UE acquires AI model configuration information of the target cell, and the UE needs to trigger a RACH procedure on the target cell;

[0358] The UE needs to send uplink WUS;

[0359] The UE needs to send RACH related signals, such as msg1, msgA, msg3, etc.

[0360] In some embodiments, the method further comprises:

[0361] The first device sends a third signal, which is used to indicate at least one of the following:

[0362] A target measurement value corresponding to triggering the first model to make a prediction;

[0363] A physical layer cell index or a physical layer cell group index predicted by the first model;

[0364] A serving cell index or a serving cell group index predicted by the first model;

[0365] A transmission parameter of the first signal predicted by the first model.

[0366] Exemplarily, when the first device is a terminal, the first device sends an uplink signal (i.e., a third signal) to a network side device. That is, after the UE triggers the AI model to make a prediction according to the above rules and conditions, the UE can indicate at least one of the following through the uplink signal:

[0367] Triggering to send the measurement value (i.e., the target measurement value) corresponding to the AI model prediction, including S criterion power standard, S criterion quality standard, layer 1 or layer 3 measurement power value (RSRP), layer 1 or layer 3 measurement quality value (RSRQ);

[0368] A physical layer cell index or a group index predicted by the AI model;

[0369] A serving cell index or a group index predicted by the AI model;

[0370] A transmission parameter of the SSB frequency point or group index predicted by the AI model;

[0371] An SSB transmission mode predicted by the AI model.

[0372] In some embodiments, the prediction manner of the first model comprises at least one of the following:

[0373] Making a prediction of the first model based on one or more preset or preconfigured beams;

[0374] Making a prediction of the first model based on one or more preset or preconfigured cells;

[0375] Making a prediction of the first model based on one or more preset or preconfigured frequency layers;

[0376] performing the prediction of the first model based on one or more cell groups being pre-set or pre-configured;

[0377] performing the prediction of the first model based on one or more TA being pre-set or pre-configured;

[0378] performing the prediction of the first model based on one or more time-domain resources being pre-set or pre-configured;

[0379] performing the prediction of the first model based on one or more devices (may include but not limited to terminals) being pre-set or pre-configured.

[0380] The implementation can be understood as the granularity of AI model prediction (or inference), which is also applicable to the training of AI model. That is, when the network node or terminal (such as a terminal in non-connected state) performs training or inference based on the target AI model, it can be performed according to any of the following ways (including combined or individual ways):

[0381] based on a specific (pre-set or pre-configured) one or more beams;

[0382] based on a specific (pre-set or pre-configured) one or more cells;

[0383] based on a specific (pre-set or pre-configured) one or more frequency layers;

[0384] based on a specific (pre-set or pre-configured) one or more cell groups;

[0385] based on a specific (pre-set or pre-configured) TA;

[0386] based on a specific (pre-set or pre-configured) one or more time regions (such as subframe, slot, symbol, time window, etc.);

[0387] based on a specific (pre-set or pre-configured, or UE-specific or group-specific) one or more terminals or terminal groups.

[0388] In some embodiments, the input parameters of the first model include at least one of the following:

[0389] measurement related information of one or more cells;

[0390] attribute information of one or more cells;

[0391] transmission related information of the first signal corresponding to one or more cells;

[0392] a detection-related feature of the first signal corresponding to one or more cells;

[0393] related information of one or more devices (including but not limited to terminals);

[0394] geographical environment information, such as cell radius, geographical location of the cell, environment, antenna configuration of the cell, coverage performance, scenario information, the scenario information can be network scenario information, which can include Indoor hotspots (inH), Urban Macrocell (Uma), Rural Macrocellular (RMa), etc., or include homogeneous network or heterogeneous network, i.e. with or without overlapping coverage;

[0395] time information, the time can be specific to a specific time point, such as 13:25:38. It can also be a time range, such as 13:00-14:00, AM / PM, day / night, the time information can be timing information obtained through other RATs, such as Bluetooth, Wi-Fi, 3G, 4G or LTE, etc.

[0396] Optionally, the measurement-related information includes at least one of the following:

[0397] S criterion power criterion;

[0398] S criterion quality criterion;

[0399] a measured power value at layer 1 or layer 3;

[0400] a measured quality value at layer 1 or layer 3.

[0401] Optionally, the attribute information includes at least one of the following:

[0402] a physical layer cell index or a physical layer cell group index;

[0403] a frequency band, frequency point or frequency layer where the cell is located;

[0404] whether the cell allows camping.

[0405] Optionally, the transmission-related information (including historical information and latest transmission parameter information) includes at least one of the following:

[0406] at least one (energy saving state or non-energy saving state) SSB index or SSB set index;

[0407] at least one of the following of at least one (energy saving state or non-energy saving state) SSB: frequency point, frequency domain start position, frequency band, carrier, BWP and synchronization raster;

[0408] at least one of a location, a period, a number, and a type of the at least one (energy-saving state or non-energy-saving state) SSB in a time domain;

[0409] at least one of a length of transmission time, a number of transmission times, and a transmission period of the at least one (energy-saving state or non-energy-saving state) SSB;

[0410] at least one of a start position of transmission and an end position of transmission of the at least one (energy-saving state or non-energy-saving state) SSB;

[0411] at least one of a beam direction and a number of beams of the at least one (energy-saving state or non-energy-saving state) SSB;

[0412] at least one of a transmission power and antenna configuration information of the at least one (energy-saving state or non-energy-saving state) SSB.

[0413] Optionally, the detection of the related features comprises at least one of:

[0414] RSSI of at least one frequency point, i.e., a frequency domain feature;

[0415] a detection signal strength of PSS or SSS of at least one frequency point, i.e., a frequency domain feature;

[0416] a channel estimation signal-to-noise ratio (SNR) of at least one frequency point, i.e., a frequency domain feature;

[0417] at least one of a synchronization success probability, an access success probability, a hypothetical block error rate (BLER), a physical downlink control channel (PDCCH) block error rate, a SIB1 block error rate, and a physical downlink shared channel (PDSCH) block error rate of at least one frequency point, i.e., a frequency domain feature;

[0418] RSRP of at least one frequency point, such as at least one of SSB-RSRP, layer 1 RSRP, and layer 3 RSRP, i.e., a frequency domain feature;

[0419] a number of time domain symbols of a synchronization signal, i.e., a time domain feature;

[0420] a length of a time window of time domain related detection, i.e., a time domain feature;

[0421] a PSS or SSS detection signal strength of at least one time domain position, i.e., a time domain feature;

[0422] SNR of at least one time domain location, i.e., time domain feature;

[0423] At least one of the following of at least one time domain location: synchronization success probability, access success probability, hypothetical BLER, PDCCH block error rate, SIB1 block error rate, and PDSCH block error rate, i.e., time domain feature;

[0424] RSRP of at least one time domain location, i.e., time domain feature;

[0425] Historical beam measurement results, i.e., spatial feature;

[0426] Current beam measurement results, i.e., spatial feature;

[0427] Link quality information, such as hypothetical BLER, PDCCH / PDSCH (MIB / SIB1) BLER, i.e., spatial feature.

[0428] Optionally, the related information of the at least one device includes at least one of the following:

[0429] At least one of the following of at least one device in connected state: number, location, traffic volume, beam direction, and channel quality;

[0430] At least one of the following of at least one device in idle state: number and location;

[0431] Location information of at least one device, which can be specific geographic location coordinates (such as GPS coordinates), or approximate location range information of the terminal (such as range information of which street, which country), or location information of the terminal relative to the camping cell or the access cell (such as in the east direction of the camping cell);

[0432] Moving direction and moving speed of at least one device, the moving direction can be an absolute direction, such as east by south 40 degrees; or a relative direction, such as relative to a certain base station.

[0433] Optionally, the synchronization signal corresponding to the one or more cells includes at least one of the following:

[0434] Synchronization signal being transmitted;

[0435] Synchronization signal not in transmission state;

[0436] Synchronization signal in normal mode (transmitted in a specific period and mode);

[0437] Synchronization signal in simplified mode (e.g., SSB with only minimum payload size);

[0438] Synchronization signals in an aggregated mode (e.g., multiple SSBs are transmitted consecutively in a period of time);

[0439] Synchronization signals to be transmitted (or in other words, synchronization signals about to start transmission).

[0440] In some embodiments, the method further comprises:

[0441] In the case where the first model fails to make a prediction, the first device performs a second operation, and the second operation comprises at least one of:

[0442] Making a prediction based on the first model again;

[0443] Making a prediction based on a second model, wherein the second model and the first model are different models, or the second model and the first model comprise different AI modules;

[0444] Transmitting a wake-up signal, wherein the wake-up signal is used to trigger transmission of synchronization signals of a cell;

[0445] Performing handover, cell selection or cell reselection based on a cell or frequency point other than the target cell;

[0446] Re-training the first model based on the first model again.

[0447] Illustratively, the behavior of the network node or terminal after the AI model inference trigger further comprises: if the prediction is unsuccessful, for example, no SSB is detected within the first window, the behavior of the network node or terminal comprises at least one of:

[0448] Triggering the AI model to make a prediction again;

[0449] Switching the AI model to make a prediction;

[0450] Sending a WUS to trigger SSB transmission;

[0451] Switching to another frequency point or cell for reselection;

[0452] If the number of failures exceeds a preset value, triggering the AI model to be trained; if the AI model is trained at the network side device, the UE needs to indicate to the network side device, for example, through a random access message (in idle state) or uplink transmission in connected state.

[0453] After the AI model prediction, the UE can listen to the feedback of the network, and the feedback comprises at least one of:

[0454] After the AI model prediction, the UE detects SSB / SIB within a time window;

[0455] If the SSB and the SIB are detected, the UE sends a Msg1, which can be a dedicated msg1, associated to a specific SSB.

[0456] After the network-side device receives the Msg1, it considers that the UE has successfully passed the prediction by the AI model and has completed the access.

[0457] In some embodiments, in a case where the first device is a terminal, the method further comprises at least one of:

[0458] The first device updates the first model based on the target information, or the first device sends a second indication to a third device, the second indication being used to indicate updating the first model, wherein the second indication comprises at least one of the target information and state information of the terminal;

[0459] The first device performs a third operation;

[0460] The third operation comprises at least one of the following: falling back to a traditional cell selection or cell reselection mode; triggering switching of the first model; triggering retraining of the first model; triggering supervision of the first model.

[0461] In the embodiments of the present application, when the first device supports updating the first model (for example, the first device is a node for training the first model), the first device can update the first model based on the target information. Updating the first model can be understood as or replaced by fine-tuning the first model. When the first device does not support updating the first model, the first device can send a second indication to a third device, and the third device updates the first model, and then the first device obtains the updated first model from the third device.

[0462] Optionally, the switching of the first model can include replacing input information or replacing an AI algorithm.

[0463] Optionally, the first device performing the third operation can be triggered periodically, conditionally, or autonomously by the first device.

[0464] Optionally, the first model is obtained by independent training of the terminal, a network-side device or a server, or the first model is obtained by joint training of at least two of the terminal, the network-side device and the server. 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 a cell where the terminal last camped or accessed. Or the network-side device is a base station or a network-side device associated with a cell that sends an RRC release message.

[0465] Optionally, the scenario jointly trained by at least two of the terminal, the network-side device and the server for the first model comprises at least one of the following:

[0466] The terminal reports the output of the model training to the network-side device or the server, and the network-side device or the server takes the terminal report information (i.e., the output of the terminal model training) as one of the input contents of the model training of itself, and performs the model training.

[0467] The network-side device sends the output of the 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 model training of the network-side device) as one of the input contents of the model training of itself, and performs the model training.

[0468] 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 perform fine-tuning in the actual network.

[0469] Optionally, at least part of the input information of the model training when the terminal performs at least part 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 comprises 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.

[0470] Optionally, at least part of the input information of the model training when the network-side device performs at least part of the model training is sent by the terminal to the network-side device, and the signal or signaling of the at least part of the input information comprises at least one of the following: MAC CE; RRC message; NAS message; user plane data; MSG 1 information; MSG A information; MSG 3 information; information of physical uplink control channel PUCCH; information of physical uplink shared channel PUSCH; information of physical random access channel PRACH; SRS or other uplink reference signal such as WUS.

[0471] Optionally, at least part of the input information of the model training when the server performs at least part of 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 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.

[0472] Optionally, the input information acquisition manner of the model training can comprise: triggering the reporting (such as sending by the terminal to the network side device) or the issuing (such as sending by the network side device to the terminal) of the input information of the model training at least once after the terminal camps on a cell, or initially selects a cell, or reselects a cell, or enters an RRC connected state or enters an idle state for a period of time.

[0473] Optionally, the reporting or the issuing of the input information of 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.

[0474] Optionally, if the first model is finally trained at the network side device or the server, after the training of the first model is completed, the network side device or the server can send the trained first model to the terminal, so that the inference of the first model is completed by the terminal, thereby reducing the subsequent signaling interaction, and at the same time, the latency of the terminal in performing cell search and selection can be reduced. 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, so that the demand for terminal capability can be reduced.

[0475] In order to better understand the embodiments of the present application, the following will be exemplarily described by combining specific target AI models through multiple embodiment groups. Each embodiment group can be implemented independently or used in combination. When different embodiments are combined, the AI model prediction (referred to as prediction for short) can be performed simultaneously or in stages. The prediction in different stages can have the same and partially same input parameters. If the prediction is performed in stages, the prediction in different stages can be associated with each other, for example, the X2th prediction can utilize the output of the X1th prediction (the step of the X2th prediction is after the X1th prediction). Which prediction method is used can be indicated by network higher layer signaling or DCI to activate or enable.

[0476] For ease of description, in each of the following embodiments, Cell A refers to the current serving cell, which can also be referred to as the current camped cell. Cell B refers to a neighbor cell, i.e., a non-current serving cell or a non-current camped cell. Cell B has AI capability and can provide a synchronization signal transmission function based on AI model inference.

[0477] Embodiment group 1: predicting a first cell set and a synchronization signal transmission mode of a cell corresponding to the first cell set based on a target AI model

[0478] The target AI model comprises a first AI function and a third AI function, wherein the third AI function is used to predict a transmission mode of a synchronization signal corresponding to at least one target cell.

[0479] The execution subject of the target AI model is a network side device or a UE.

[0480] Based on the target AI model, the output of the target AI model inference includes at least one of the following:

[0481] A first cell set, which is a cell to which at least one terminal corresponds and which is potentially reselected or camped;

[0482] The first cell set corresponds to a synchronization signal (SSB or SIB, hereinafter referred to as SSB) transmission mode of a cell.

[0483] Based on the target AI model, the result of predicting the first cell set includes at least one of the following:

[0484] At least one cell in an Intra-Frequency layer;

[0485] At least one cell in an Inter-frequency layer;

[0486] At least one cell with a power saving mode (may or may not be in a power saving state);

[0487] At least one cell in a power saving mode;

[0488] At least one cell with a cell signal quality or cell signal strength higher than a preset threshold;

[0489] At least one cell with a cell signal quality or cell signal strength within a preset range;

[0490] At least one cell that can be allowed to camp;

[0491] At least one cell that is transmitting SSB or SIB;

[0492] At least one cell that is transmitting SSB or SIB corresponding to a power saving state;

[0493] At least one cell in a power saving mode without transmitting SSB or SIB.

[0494] Based on the target AI model, the synchronization signal transmission mode of the cell corresponding to the first cell set is predicted, and at least one of the following is output:

[0495] At least one SSB index or SSB set index;

[0496] At least one frequency point, frequency domain starting position, band, carrier, BWP, synchronization raster, etc. of SSB;

[0497] Time domain location period, number, pattern (uniform or non-uniform) of at least one SSB;

[0498] Time length, number of transmission times or number of transmission periods of at least one SSB transmission;

[0499] Starting position or ending position of at least one SSB transmission;

[0500] Beam direction, number of at least one SSB transmission;

[0501] Transmission power, antenna configuration of at least one SSB.

[0502] The SSB includes at least one of the following:

[0503] SSB being transmitted;

[0504] SSB not in the state of being transmitted;

[0505] SSB in normal mode (transmitted in a specific period and mode);

[0506] SSB in simplified mode (such as SSB with only minimum payload size);

[0507] SSB in aggregated mode (such as multiple SSBs being continuously transmitted in a period of time);

[0508] SSB to be transmitted.

[0509] Based on the target AI model, the starting time / ending time of the synchronization signal corresponding to the measurement target cell set can also be inferred. Based on the starting time or ending time, the UE performs measurement on the target cell set within the time period.

[0510] Based on the target AI model, the model training input information includes at least one of the following:

[0511] Measurement related information corresponding to at least one cell, such as S criterion power standard, S criterion quality standard, layer 1 or layer 3 measurement power value (RSRP), layer 1 or layer 3 measurement quality value (RSRQ);

[0512] Attribute information of at least one cell, such as physical layer cell index or group index, frequency band / frequency point / frequency layer where the cell is located, whether the cell allows camping;

[0513] SSB transmission related information corresponding to at least one cell, such as at least one (energy saving state or non-energy saving state) SSB index or SSB set index, frequency point, frequency domain starting position, band, carrier, BWP, synchronization raster of at least one (energy saving state or non-energy saving state) SSB, time domain position period, number, pattern (uniform or non-uniform) of at least one (energy saving state or non-energy saving state) SSB, time length, number of transmission times or number of transmission periods of at least one (energy saving state or non-energy saving state) SSB transmission, starting position or ending position of at least one (energy saving state or non-energy saving state) SSB transmission, beam direction, number of at least one (energy saving state or non-energy saving state) SSB transmission, transmission power, antenna configuration of at least one (energy saving state or non-energy saving state) SSB. The SSB includes at least one of the following: an SSB being transmitted; an SSB not in a transmission state; an SSB in a normal mode (transmitted in a specific period and mode); an SSB in a simplified mode (such as an SSB with only a minimum payload size); an SSB in an aggregated mode (such as multiple SSBs being continuously transmitted in a period of time); an SSB to be transmitted;

[0514] Detection related characteristics of at least one SSB, such as frequency domain features: RSSI, PSS / SSS detection signal strength, channel estimation SNR, etc. of at least one frequency point (per cell, per frequency layer, per channel bandwidth, per SCS, per band, per frequency range, per PLMN, etc.), synchronization success probability, access success probability, hypothetical BLER, PDCCH / SIB1 PDSCH BLER of candidate frequency points, SSB-RSRP, L1 / L3 RSRP; such as time domain features: time domain symbol number of synchronization signals, time window length of time domain related detection, PSS / SSS detection signal strength, channel estimation SNR, etc. of at least one time domain position, synchronization success probability, access success probability, hypothetical BLER, PDCCH / SIB1 PDSCH BLER of at least one time domain position, SSB-RSRP, L1 / L3 RSRP of at least one time domain position; such as spatial features: historical beam measurement results, current beam measurement results, link quality information (such as hypothetical BLER, PDCCH / PDSCH (MIB / SIB1) BLER);

[0515] UE distribution, such as the number of Connected UEs, the location of Connected UEs, the traffic volume of Connected UEs, the beam direction of Connected UEs, the channel quality of Connected UEs, the number of Idle UEs, the location of Idle UEs, and the like, terminal location information, which can be specific geographic location coordinates (such as GPS coordinates), or approximate location range information of the terminal (such as range information of which street, which country), or location information of the terminal relative to the camping cell or access cell (such as in the northeast direction of the camping cell), the moving direction and speed of the terminal, which can be an absolute direction (such as east 40 degrees south) or a relative direction (such as relative to a certain base station);

[0516] Geographical environment, such as cell radius, geographical location of the cell, environment, antenna configuration of the cell, coverage performance, and scenario information (such as inH, Uma, RMa, and the like, or homogeneous / heterogeneous network (i.e., with or without overlapping coverage));

[0517] Time information, which can be a specific time point (such as 13:25:38) or a time range (such as 13:00-14:00, AM / PM, day / night), and which can be timing information obtained through other RATs, such as Bluetooth, Wi-Fi, 3G, 4G, or LTE.

[0518] The behavior after inference based on the target AI model includes at least one of the following:

[0519] The network-side device enables the cells corresponding to the first cell set;

[0520] Switches the state of the cells corresponding to the first cell set, such as from energy saving state to normal state;

[0521] Enables SSB or SIB transmission of the cells corresponding to the first cell set;

[0522] Performs SSB / SIB transmission of the cells corresponding to the first cell set based on the SSB transmission mode inferred by the AI model;

[0523] Performs RACH reception in the cells corresponding to the first cell set;

[0524] Performs paging transmission in the cells corresponding to the first cell set;

[0525] The UE performs measurement based on the target cell, which is one of the first cell set;

[0526] The UE performs SSB / SIB reception of the cells corresponding to the first cell set based on the SSB transmission mode inferred by the AI model;

[0527] UE reselects or camps to a target cell, the target cell is one of the first cell set;

[0528] UE performs RACH transmission in a target cell, the target cell is one of the first cell set;

[0529] UE performs paging reception in a target cell, the target cell is one of the first cell set.

[0530] Embodiment 1-1: Execution of AI model inference at network side device

[0531] Flow example: assume UE x camps in Cell A, the training of AI model is in Cell A. UE x can be one or multiple UEs.

[0532] When the trigger condition of AI model inference is met, Cell A performs inference based on the AI model, obtains a first cell set {Cell B}, and the SSB transmission mode (period, number, starting position, ending position, frequency domain position, beam direction, etc.) corresponding to {Cell B};

[0533] Cell A informs UE x of the result of AI model inference {Cell B} and the SSB transmission mode corresponding to {Cell B};

[0534] UE performs measurement based on {Cell B} and the SSB transmission mode corresponding to {Cell B}, reselects or camps to a target cell, the target cell is one of {Cell B}.

[0535] Embodiment 1-2: Execution of AI model inference at UE side

[0536] Flow example 1: assume UE camps in Cell A, UE obtains a target AI model from Cell A, the training of the target AI model is in Cell A.

[0537] UE performs inference based on the target AI model, obtains a first cell set Cell B list and the synchronization signal transmission mode (period, number, starting position, ending position, frequency domain position, beam direction, etc.) of the corresponding cells of Cell B list;

[0538] UE performs measurement based on the first cell set Cell B list and the corresponding synchronization signal transmission mode, measures the synchronization signals of the cells corresponding to Cell B list;

[0539] UE determines to reselect to one of the cells based on the measurement results of Cell B list.

[0540] Flow example 2: assuming UE camps in Cell A, UE obtains target AI model from Cell A, the training of target AI model is in Cell A.

[0541] UE performs inference based on the target AI model, and obtains a first cell set Cell B list, the Cell B list corresponds to the synchronization signal transmission mode (period, number, starting position, ending position, frequency domain position, beam direction, etc.) of the cell, and the starting time / ending time of triggering the measurement of the synchronization signal of the Cell B list;

[0542] UE measures the target cell set Cell B list and the corresponding synchronization signal transmission mode based on the starting time / ending time obtained by the AI model inference, and measures the synchronization signal of the cell corresponding to the Cell B list;

[0543] The UE determines to reselect to one of the cells based on the measurement result of the Cell B list.

[0544] The beneficial effects of embodiment group 1 are as follows:

[0545] The UE needs to measure each cell in the first cell set, and when measuring, the UE measures the synchronization signal set corresponding to the cell based on the AI model inference. Determine whether the conditions for reselection / camping are met

[0546] Further, the AI model inference result can also include whether the synchronization signal is a Cell defining synchronization signal, whether it contains SIB1, etc., to determine whether camping is allowed

[0547] Or, the system message of the corresponding cell can be obtained through the synchronization signal to determine whether camping is allowed

[0548] In this method, the UE needs to measure the reselection cell, and through the AI model inference, the first cell set and the synchronization signal transmission mode corresponding to the first cell set can be obtained, which can reduce the measurement of the UE's neighbor synchronization signal, and further save the power consumption of the UE's neighbor measurement. On the other hand, the network side device can start or switch the synchronization signal transmission of the cell corresponding to the first cell set to the normal mode based on the first cell set and the corresponding synchronization signal transmission mode obtained by the AI model inference, while not needing to perform starting or switching operation on other neighbor cells in power saving mode, further reducing unnecessary energy consumption of the network.

[0549] In the following two implementation modes, the synchronization signal transmission mode of the predicted target cell or potential target cell is not included.

[0550] Embodiment group 2: based on the target AI model, predict the target cell, the target cell is the reselection or camping cell of at least one terminal (in a non-measurement manner)

[0551] The target AI model comprises a first AI function.

[0552] The execution subject of the target AI model is a network side device or a UE.

[0553] Based on the target AI model, the output of the AI model inference includes at least one of the following:

[0554] At least one target cell, the target cell is a cell that at least one terminal can reselect or camp on;

[0555] The start time / end time of triggering reselection to the target cell.

[0556] Based on the target AI model, the predicted target cell includes:

[0557] One cell of the Intra-Frequency layer;

[0558] One cell of the Inter-frequency layer;

[0559] One cell with energy saving mode (may or may not be in energy saving state);

[0560] One cell that is in energy saving mode;

[0561] One cell with cell signal quality or cell signal strength higher than a preset threshold;

[0562] One cell with cell signal quality or cell signal strength within a preset range;

[0563] One cell that can be allowed to camp.

[0564] Based on the target AI model, the input information of the model training includes at least one of the following:

[0565] Measurement related information corresponding to at least one cell, such as S criterion power standard, S criterion quality standard, layer 1 or layer 3 measurement power value (RSRP), layer 1 or layer 3 measurement quality value (RSRQ);

[0566] Attribute information of at least one cell, such as physical layer cell index or group index, frequency band / frequency point / frequency layer where the cell is located, whether the cell allows camping;

[0567] UE distribution, such as the number of Connected UEs, location, traffic volume, beam direction, channel quality, the number of Idle UEs, location, and the like, terminal location information, which can be specific geographic location coordinates (such as GPS coordinates), or approximate location range information of the terminal (such as range information of which street, which country), or location information of the terminal relative to the camping cell or access cell (such as the positive east direction of the camping cell), the moving direction and speed of the terminal, which can be an absolute direction (such as east 40 degrees south) or a relative direction (such as the direction relative to a certain base station);

[0568] Geographical environment, such as cell radius, geographical location of the cell, environment, antenna configuration of the cell, coverage performance, and scenario information (such as inH, Uma, RMa, and the like, or homogeneous / heterogeneous network (i.e., with / without overlapping coverage));

[0569] Time information, which can be specific to a specific time point (such as 13:25:38) or a time range (such as 13:00-14:00, AM / PM, day / night), and the like. The time information can be timing information obtained through other RATs, such as Bluetooth, Wi-Fi, 3G, 4G, or LTE, and the like.

[0570] The behavior after AI model inference includes at least one of the following:

[0571] The network-side device starts the target cell;

[0572] Switching the state of the target cell, such as switching from the energy-saving state to the normal state;

[0573] Starting SSB or SIB transmission of the target cell;

[0574] Performing RACH reception in the target cell;

[0575] Performing paging transmission in the target cell;

[0576] UE reselects or camps to the target cell;

[0577] UE performs RACH transmission in the target cell;

[0578] UE performs paging reception in the target cell.

[0579] Embodiment 2-1: Execution of AI model inference at the network-side device

[0580] Flow example: Assume that UE x camps in Cell A, and the training of the AI model is in Cell A. UE x can be one or more UEs.

[0581] When the trigger condition of AI model inference is met, Cell A performs inference based on the AI model, and obtains a reselection target cell Cell B;

[0582] Cell A informs UE x of the result of AI model inference, i.e., Cell B;

[0583] Embodiment 2-2: Execution of AI model inference at the UE side

[0584] Flow example 1: Assuming that the UE is camped in Cell A, the UE obtains a target AI model from Cell A, and the training of the target AI model is performed in Cell A.

[0585] The UE performs inference based on the target AI model, and obtains a target cell Cell B;

[0586] The UE performs cell reselection based on the target cell Cell B.

[0587] Flow example 2: Assuming that the UE is camped in Cell A, the UE obtains a target AI model from Cell A, and the training of the target AI model is performed in Cell A.

[0588] The UE performs inference based on the target AI model, and obtains a target cell Cell B and a start time / end time of triggering reselection to Cell B; at this time, it is not necessary to meet the condition of reselection, such as the threshold of reselection triggering;

[0589] The UE performs cell reselection based on the target cell Cell B and the start time / end time of triggering reselection to Cell B.

[0590] The beneficial effects of embodiment group 2 are as follows:

[0591] The network side device does not need to switch or turn on the power saving mode of the target cell before the UE reselection flow is triggered, and the network side device turns on the target cell for UE reselection after the start time or before the end time of AI model inference, which can further save the energy consumption of the network side device. After the end time of AI model inference, if the UE completes reselection and camping, or the UE does not reselect to the target cell, the network side device can continue to turn on the energy saving mode of the target cell.

[0592] For the UE, the target cell inferred by the AI model is the cell where the UE finally reselects and camps. The UE does not need to reselect to the target cell based on the measurement results of the target cell. During the reselection process, the UE assumes that all conditions of the target cell are met. Since no measurement of the reselected cell is needed, the UE is more power saving. At the same time, if the network side device allows the target cell to adopt the power saving mode, it can determine whether to start based on whether the AI model inference needs to access the reselected UE, which can also bring power saving effect to the network side device.

[0593] It should be noted that since the signal strength of the target cell and whether the target cell allows camping are not obtained by measurement and reading system messages, but are obtained by AI model inference, the failure probability of the UE reselecting to the target cell can be relatively high, which depends on the inference ability of the AI model and has a higher requirement for the reliability of AI model training.

[0594] Embodiment group 3: based on the target AI model, predicting a second cell set, the second cell set containing at least one potential reselected or camped cell corresponding to the terminal

[0595] The execution subject of the target AI model is the network side device or the UE.

[0596] Based on the target AI model, the output of the target AI model inference includes at least one of the following:

[0597] The second cell set, the second cell set containing at least one potential reselected or camped cell corresponding to the terminal;

[0598] Triggering the start time / end time of measuring the cells corresponding to the second cell set.

[0599] Based on the target AI model, the predicted second cell set includes at least one of the following:

[0600] At least one cell of the Intra-Frequency layer;

[0601] At least one cell of the Inter-frequency layer;

[0602] At least one cell with a power saving mode (may or may not be in a power saving state);

[0603] At least one cell in a power saving mode;

[0604] At least one cell with a cell signal quality or cell signal strength higher than a preset threshold;

[0605] At least one cell with a cell signal quality or cell signal strength within a preset range;

[0606] At least one cell which is allowed to camp.

[0607] The target AI model is trained based on input information of model training, and the input information comprises at least one of the following:

[0608] Measurement-related information of at least one cell, such as S criterion power standard, S criterion quality standard, layer 1 or layer 3 measurement power value (RSRP), layer 1 or layer 3 measurement quality value (RSRQ);

[0609] Attribute information of at least one cell, such as physical layer cell index or group index, frequency band / frequency point / frequency layer of the cell, and whether the cell is allowed to camp;

[0610] UE distribution, such as number, location, traffic volume, beam direction, and channel quality of Connected UE, number and location of Idle UE, terminal location information, the location information can be specific geographic location coordinates (such as GPS coordinates), or approximate location range information of the terminal (such as range information of which street, which country), or location information of the terminal relative to the camping cell or the access cell (such as the east direction of the camping cell), moving direction and speed of the terminal, the moving direction can be an absolute direction (such as east 40 degrees south), or a relative direction (such as a direction relative to a certain base station);

[0611] Geographical environment, such as cell radius, geographical location of the cell, environment, antenna configuration of the cell, coverage performance, and scenario information (such as inH, Uma, RMa, or homogeneous / heterogeneous network (i.e., with or without overlapping coverage));

[0612] Time information, the time can be specific to a specific time point (such as 13:25:38), or a time range (such as 13:00 to 14:00, morning / afternoon, day / night), the time information can be timing information obtained through other RATs, and the RATs can be Bluetooth, Wi-Fi, and 3G, 4G, or LTE, etc.

[0613] Behaviors after inference based on the target AI model comprise at least one of the following:

[0614] The network-side device starts a cell corresponding to the second cell set;

[0615] Switch the state of the cell corresponding to the second cell set, for example, from energy saving state to normal state;

[0616] Start SSB or SIB transmission of the cell corresponding to the second cell set;

[0617] perform RACH reception in the cells corresponding to the second set of cells;

[0618] perform paging transmission in the cells corresponding to the second set of cells;

[0619] perform measurements based on the second set of cells;

[0620] reselect or camp to a target cell, the target cell being one of the second set of cells;

[0621] perform RACH transmission in the target cell, the target cell being one of the second set of cells;

[0622] perform paging reception in the target cell, the target cell being one of the second set of cells.

[0623] Embodiment 3-1: Execution of AI model inference at network side device

[0624] Flow example: Assume UE x camps in Cell A, the training of AI model is in Cell A. UE x can be one or multiple UEs. When the triggering condition of AI model inference is met, Cell A performs inference based on the AI model and obtains a second set of cells {Cell B};

[0625] Cell A notifies UE x of the result of AI model inference {Cell B};

[0626] UE performs measurements based on {Cell B}, and reselects or camps to a target cell, the target cell being one of the second set of cells.

[0627] Embodiment 3-2: Execution of AI model inference at UE side

[0628] Flow example 1: Assume UE camps in Cell A, the UE obtains a target AI model from Cell A, and the training of the target AI model is in Cell A.

[0629] UE performs inference based on the target AI model and obtains a second set of cells Cell B list;

[0630] UE performs measurements based on the second set of cells Cell B list, and measures synchronization signals of cells corresponding to Cell B list;

[0631] UE determines to reselect to one of the cells based on the measurement results of Cell B list.

[0632] Flow example 2: Assume UE camps in Cell A, the UE obtains a target AI model from Cell A, and the training of the target AI model is in Cell A.

[0633] The UE performs inference based on the target AI model to obtain a second cell set Cell B list and a start time / end time of triggering measurement of a synchronization signal of the Cell B list;

[0634] The UE performs measurement on the Cell B list based on the start time / end time obtained by the AI model inference, and measures the synchronization signal of the cell corresponding to the Cell B list;

[0635] The UE determines to reselect to one of the cells based on the measurement result of the Cell B list.

[0636] The beneficial effects of the embodiment group 3 are as follows:

[0637] The network side device can not need to switch the power saving mode of the target cell or turn on the target cell before the UE measures the synchronization signal of the second cell set. After the start time or before the end time of the AI model inference, the network side device turns on the target cell to allow the UE to perform measurement and reselection, which can save network energy consumption. After the end time of the AI model inference, if the UE completes the measurement and reselection or camping, or the UE does not reselect to the target cell, the network side device can continue to open the power saving mode of the target cell.

[0638] For the UE, the UE needs to measure each cell in the second cell set, i.e., measure the synchronization signal of each cell in the second cell set, to determine whether the condition for reselection / camping is met. Further, the UE needs to obtain the system message of the cell corresponding to the second cell set to determine whether camping is allowed. The second cell set obtained by the UE through AI model inference can reduce the neighbor cell measurement of the UE and save the power consumption of the UE. On the other hand, the network side device can open or switch the cells corresponding to the second cell set to normal mode based on the second cell set obtained by the AI model inference, so as to not need to open or switch other neighbor cells in the power saving mode, thereby avoiding unnecessary energy consumption of the network.

[0639] Embodiment group 4: transmitting a first signal / channel based on a first preset condition; predicting a third cell set and / or a synchronization signal transmission mode of a cell corresponding to the third cell set based on a second AI model and the first signal / channel

[0640] This embodiment group requires joint inference of the UE and the network side device.

[0641] The first preset condition can include at least one of condition 1 to condition 3, wherein,

[0642] Condition 1: preset conditions corresponding to the first cell (such as a serving cell), including at least one of the following:

[0643] the S-criterion power standard corresponding to the first cell is less than or equal to a first threshold value;

[0644] the S-criterion quality standard corresponding to the first cell is greater than or equal to a second threshold value;

[0645] the measured power value (RSRP) corresponding to the first cell is less than or equal to a third threshold value;

[0646] the measured quality value (RSRQ) corresponding to the first cell is greater than or equal to a fourth threshold value.

[0647] the S-criterion power standard corresponding to the first cell is less than or equal to a fifth threshold value;

[0648] the S-criterion quality standard corresponding to the first cell is greater than or equal to a sixth threshold value;

[0649] the measured power value (RSRP) corresponding to the first cell is less than or equal to a seventh threshold value;

[0650] the measured quality value (RSRQ) corresponding to the first cell is greater than or equal to an eighth threshold value.

[0651] Condition 2: preset conditions corresponding to the second cell (a neighboring cell), including at least one of the following:

[0652] the S-criterion power standard corresponding to the second cell is less than or equal to a ninth threshold value;

[0653] the S-criterion quality standard corresponding to the second cell is greater than or equal to a tenth threshold value;

[0654] the measured power value (RSRP) corresponding to the second cell is greater than or equal to an eleventh threshold value;

[0655] the measured quality value (RSRQ) corresponding to the second cell is greater than or equal to a twelfth threshold value.

[0656] the S-criterion power standard corresponding to the second cell is less than or equal to a thirteenth threshold value;

[0657] the S-criterion quality standard corresponding to the second cell is less than or equal to a fourteenth threshold value;

[0658] the measured power value (RSRP) corresponding to the second cell is less than or equal to a fifteenth threshold value;

[0659] the measured quality value (RSRQ) corresponding to the second cell is less than or equal to a sixteenth threshold value.

[0660] Condition 3: the first time based on the prediction of the first AI model is met, and the first signal / channel is transmitted based on the first time.

[0661] The first AI model includes a second AI function, and the second AI function is used to predict the start time / end time of the first uplink signal transmission. The first uplink signal includes UL WUS, random access message (msg1, msgA, msg3, etc.), SRS, CSI / RSRP reporting, etc. The first uplink signal can be used for wake-up, positioning, measurement, random access, etc.

[0662] The second AI model includes at least one of the following:

[0663] The first AI function is used to predict at least one target cell or a target cell set;

[0664] The third AI function is used to predict the transmission mode of the synchronization signal corresponding to at least one target cell.

[0665] The execution subject of the first AI model is a UE, and the execution subject of the second AI model is a network side device.

[0666] The output of the first AI model inference includes at least one of the following:

[0667] The first time, which can be the start time / end time of reselecting to a target cell, or the start time / end time of measuring the synchronization signal corresponding to the target cell;

[0668] The start time / end time of the first signal / channel transmission, and the first signal / channel is used to request the network, wake up the network, assist the network positioning, assist the network to measure, etc.

[0669] The output of the second AI model inference is similar to the output of the target AI model inference in Embodiment Group 1.

[0670] Based on the first AI model, the input information of the model training includes at least one of the following:

[0671] Measurement related information corresponding to at least one cell, such as S criterion power standard, S criterion quality standard, layer 1 or layer 3 measurement power value (RSRP), layer 1 or layer 3 measurement quality value (RSRP);

[0672] UE distribution, such as the number of Connected UEs, the location of Connected UEs, the traffic volume of Connected UEs, the beam direction of Connected UEs, the channel quality of Connected UEs, the number of Idle UEs, the location of Idle UEs, and the like, terminal location information, which can be specific geographic location coordinates (such as GPS coordinates), or approximate location range information of the terminal (such as range information of which street, which country), or location information of the terminal relative to the camping cell or access cell (such as the positive east direction of the camping cell), the moving direction and speed of the terminal, which can be an absolute direction (such as east 40 degrees south) or a relative direction (such as the direction relative to a certain base station);

[0673] Geographical environment, such as cell radius, geographical location of the cell, environment, antenna configuration of the cell, coverage performance, and scenario information (such as inH, Uma, RMa, and the like, or homogeneous / heterogeneous network (i.e., with or without overlapping coverage));

[0674] Time information, which can be a specific time point (such as 13:25:38) or a time range (such as 13:00-14:00, AM / PM, day / night), and can be timing information obtained through other RATs, such as Bluetooth, Wi-Fi, 3G, 4G, or LTE.

[0675] Training based on the second AI model, the input information of the model training includes the first signal / channel transmitted based on the preset condition or based on the inference of the first AI model, and can also include other input information (similar to Embodiment Group 1).

[0676] The behavior after the inference of the first AI model includes that the UE transmits the first signal / channel based on the first time.

[0677] The behavior after the inference of the second AI model includes at least one of the following:

[0678] The network-side device enables the cells corresponding to the third cell set;

[0679] Switching the state of the cells corresponding to the third cell set, such as switching from an energy-saving state to a normal state;

[0680] Enabling the SSB or SIB transmission of the cells corresponding to the third cell set;

[0681] Performing RACH reception in the cells corresponding to the third cell set;

[0682] Performing paging transmission in the cells corresponding to the third cell set;

[0683] The UE performs measurement based on the target cell, which is one of the third cell set.

[0684] UE reselects or camps to a target cell, the target cell is one of the third set of cells;

[0685] UE performs RACH transmission in a target cell, the target cell is one of the third set of cells;

[0686] UE performs paging reception in a target cell, the target cell is one of the third set of cells.

[0687] Embodiment 4-1:

[0688] Flow example: assuming that the UE camps in Cell A, the UE obtains a first AI model from Cell A.

[0689] The UE infers a first time based on the first AI model, and sends a first uplink signal (i.e., a first signal / channel) to a network side device; the first uplink signal can correspond to a current serving cell or other non-serving cell (i.e., a neighboring cell). The first uplink signal can also include beam information / TCI / QCL, etc.

[0690] After the network side device receives the first uplink signal, the network side device infers a third set of cells {Cell B} based on a second AI model;

[0691] The network side device notifies the UE of the result of AI model inference {Cell B};

[0692] The UE performs measurement based on synchronization signals of each cell in the third set of cells to determine whether the conditions for reselection / camping are met.

[0693] The beneficial effects of this embodiment are as follows:

[0694] In this embodiment, the UE needs to measure the reselected cell. The UE first sends a first uplink signal based on a first time inferred by an AI model, which helps the network side device to further infer a third set of cells based on the AI model, which can reduce the number of potential reselected cells and further reduce the power consumption of the UE for neighboring cell measurement. On the other hand, the network side device can monitor the first uplink signal based on the first time inferred by the AI model, and further infer the third set of cells based on the monitored first uplink signal. In this way, the network can turn on or switch to normal mode the cells corresponding to the third set of cells, without the need to turn on or switch other neighboring cells in power saving mode, further reducing unnecessary energy consumption of the network.

[0695] Embodiment 4-2:

[0696] Flow example: assume UE camps in Cell A, UE obtains the first AI model from Cell A.

[0697] UE infers the first time based on the first AI model, and sends the first uplink signal to the network side device; the first uplink signal can correspond to the current serving cell or other non-serving cells, that is, neighboring cells. The first uplink signal can also include beam information / TCI / QCL, etc.

[0698] After the network side device receives the first uplink signal, it infers the third cell set and the synchronization signal transmission mode corresponding to the third cell set based on the second AI model; the second AI model inference can be based on the spatial characteristics corresponding to the first uplink signal to obtain the third cell set and the time domain or spatial domain transmission characteristics of the corresponding synchronization signal, which can further reduce the number of third cell sets and corresponding synchronization signal transmissions. The serving cell and the neighboring cell can exchange the results of AI model inference or the input information of AI model inference.

[0699] The network side device informs the UE of the results of AI model inference {Cell B} and the SSB transmission mode corresponding to {Cell B};

[0700] The UE measures based on the SSB transmission mode corresponding to {Cell B} obtained by AI model inference to determine whether the conditions for reselection / camping are met.

[0701] The beneficial effects of this embodiment are as follows:

[0702] In this embodiment, the UE needs to measure the reselected cell. The UE first sends the first uplink signal based on the first time obtained by AI model inference, which helps the network side device to further infer the third cell set and the synchronization signal transmission mode corresponding to the third cell set based on the AI model, which can reduce the number of potential reselected cells and the number of synchronization signals that need to be measured, and further reduce the power consumption of the UE for neighboring cell measurement. On the other hand, the network side device can monitor the first uplink signal based on the first time of AI model inference, and further infer the third cell set and the corresponding synchronization signal transmission mode based on the monitored first uplink signal. In this way, the network side device can turn on or switch the synchronization signal transmission of the corresponding cell of the third cell set to the normal mode, while not needing to perform the turning on or switching operation on other neighboring cells in the power saving mode, further reducing unnecessary energy consumption of the network.

[0703] Other supplementary schemes are introduced as follows:

[0704] The UE reports or transmits the input information related to the above AI model in at least one of the following ways:

[0705] Measurement quantity reported by the connected-state UE, L1 SINR / RSRP, L3 measurement, CSI measurement reporting (CRI / RI / PMI / CQI), SRS, PRACH, or positioning information;

[0706] Information of the non-connected-state UE, L1 SINR / RSRP, L3 measurement, random access message, or positioning information, for example, training data can be exchanged through uplink transmission signals such as PRACH / WUS / SRS in the idle state, or training data can be exchanged through uplink data such as RRC message (msg3, Small Data Transmission (SDT)).

[0707] In some embodiments, the labels for the model training (i.e., the target of the model training) include at least one of the following:

[0708] The terminal detects a synchronization signal;

[0709] The duration for which the terminal detects a synchronization signal;

[0710] The frequency domain position / time domain position / beam direction of the detected synchronization signal;

[0711] The terminal detects a synchronization signal at a specific frequency domain position / time domain position / beam direction;

[0712] The measured RSSI of the camped cell, PSS / SSS detection signal strength, channel estimation SNR, SSB-RSRP, L1 / L3 RSRP, etc.

[0713] The measured RSSI of a specific candidate frequency point and / or specific candidate time domain position, PSS / SSS detection signal strength, channel estimation SNR, SSB-RSRP, L1 / L3 RSRP;

[0714] The cell ID (such as PCI) of successful camping;

[0715] The TA where the successfully camped cell is located;

[0716] The terminal successfully camps;

[0717] The terminal successfully camps on a specific cell;

[0718] The duration from initiation to successful camping.

[0719] In some embodiments, the execution subject of the AI model training (i.e., where the model training is performed) includes at least one of the following:

[0720] Only perform model training on the terminal side;

[0721] The model training is performed only at the network side, which includes at least one of a base station device, a core network device (such as a core network device dedicated for model training), and the base station device can be a base station device where the terminal currently resides or accesses.

[0722] In the case where the partial model training is performed at both the terminal side and the network side or the terminal side and the network side jointly train, the following at least one is included:

[0723] The terminal side reports the output of the model training to the network side, and the network side takes the information reported by the terminal side (i.e., the output of the terminal model training) as one of the input contents of the model training of the network side.

[0724] The network side sends the output of the model training to the terminal, and the terminal takes the information sent by the network side (i.e., the output of the model training of the network side) as one of the input contents of the model training of the terminal.

[0725] The terminal side or the network side performs offline model training, and the terminal side or the network side performs fine tuning in the actual network.

[0726] As a first sub-embodiment of the above embodiment, when the terminal performs the model training, at least part of the input information of the model training can be sent by the network side to the terminal, and the signal or signaling for sending the information includes at least one of the following: MAC CE, RRC message, NAS message, user plane data, DCI information, broadcast information or SIB, layer 1 signaling of physical downlink control channel (such as PDCCH), information of physical downlink shared channel (such as PDSCH), MSG 2 information, MSG 4 information, MSG B information.

[0727] As a second sub-embodiment of the above embodiment, when the network side performs the model training, at least part of the input information of the model training is reported by the terminal, and the signal or signaling for reporting the information by the terminal includes at least one of the following: MAC CE, RRC message, NAS message, user plane data, MSG 1 information, MSG A information, MSG 3 information, information of PUCCH, information of PUSCH, information of PRACH, SRS or other uplink reference signal (such as WUS).

[0728] The following provides more embodiments for exemplary illustration in combination with a specific scenario. The specific scenario is that the coverage range of Cell A is large, the coverage range of Cell B is located in the coverage range of Cell A, and the coverage range of Cell B is significantly smaller than the coverage range of Cell A.

[0729] Embodiment 5: General flow (see FIG. 6)

[0730] As shown in FIG. 6, the following steps are included:

[0731] Determine what AI model to use, for example, AI model determination by network (NW);

[0732] AI model training requires data collection, for example, NW and UE jointly participate in training data collection;

[0733] Based on the collected data, the selected AI model is trained, for example, the NW trains the AI model;

[0734] The device obtains the relevant configuration information of the AI model application, for example, the UE obtains the relevant configuration information of the AI model application from the NW;

[0735] After meeting the preset condition, trigger the AI model to make a prediction;

[0736] The NW transmits the SSB based on the AI model prediction result;

[0737] The NW transmits the SSB to the UE;

[0738] The UE receives the SSB based on the AI model prediction result, and performs measurement, synchronization, AGC, etc. Operation;

[0739] The UE determines whether to perform cell reselection or camping based on the measurement result.

[0740] In addition, after obtaining the AI model, the AI model can also be monitored or updated.

[0741] Embodiment 6: Model training (see FIG. 7a)

[0742] In some embodiments, AI model training occurs on the network side, and after AI model training is completed, the network side issues the trained AI model to the terminal.

[0743] In some embodiments, the triggering condition of the model training includes at least one of the following:

[0744] Condition / event triggered model training;

[0745] Periodic model training;

[0746] Semi-static triggered model training.

[0747] As a first sub-embodiment of the above embodiment, the AI model training is condition / event triggered, and the condition / event triggering the model training includes at least one of the following:

[0748] The recent SSB transmission mode of Cell B has changed, for example:

[0749] Frequency point, frequency domain starting position, band, carrier, BWP, synchronization raster, etc. of SSB;

[0750] Time domain position period, number, pattern (uniform or non-uniform) of SSB;

[0751] SSB monitoring / detection window length, UE detects SSB in the monitoring window;

[0752] Time length of SSB transmission, number of transmission times or number of transmission periods;

[0753] Predicted start position of the first SSB;

[0754] Beam direction, number of SSB;

[0755] SSB transmission mode (if there are multiple modes, such as normal mode, simplified mode, and aggregated mode);

[0756] Start and stop of SSB transmission;

[0757] Type of SSB, such as CD-SSB and NCD-SSB;

[0758] Change in distribution of UEs, such as at least one terminal moving to the cell edge or a specific location, at least one terminal moving at a speed higher or lower than a threshold value, more or fewer UEs accessing or camping in the current cell than a threshold value, more than a certain number (preset number) of new UEs accessing or camping, change in TA of at least one UE, change in surrounding physical environment (weather, natural environment);

[0759] Change in network deployment or configuration, such as at least one cell being turned on or off, at least one cell entering or switching to energy saving mode, at least one cell not transmitting synchronization signals, at least one cell not allowing access by specific UEs (barring), at least one frequency point being turned on or off;

[0760] Failure of AI model prediction, such as the AI model failing to predict N times in a row or the number of times the AI model fails to predict reaching a threshold value.

[0761] As a second sub-embodiment of the above embodiment, the AI model training is periodic, and the periodic configuration information includes at least one of the following:

[0762] Starting point of periodic model training, such as model training only after the terminal enters the connected state or after a period of time in the connected state;

[0763] Interval of periodic model training, such as triggering at least once model training every interval N time length;

[0764] The number of model training times or the model training duration in a cycle.

[0765] As a third sub-embodiment of the above embodiment, the AI model training is semi-statically triggered, and the semi-static triggering includes at least one of the following:

[0766] Triggering the issuance and activation of semi-static configuration information based on specific conditions / events;

[0767] The semi-static configuration information includes the starting point, cycle, and duration in the cycle of model training, etc.

[0768] The semi-static configuration information is configured by RRC, and the semi-static training of the model is activated / deactivated by DCI.

[0769] In some embodiments, the determination condition of the model training completion includes at least one of the following:

[0770] The loss function meets a predefined requirement index / value, such as the training error being less than a predefined threshold value. The loss function can be at least one of the following: mean square error or normalized mean square error of the predicted value and the true value, mean absolute error of the predicted value and the true value;

[0771] The measurement result of the terminal in the target cell reaches a preset threshold, and the measurement value includes: RSSI of the synchronization signal, signal strength detected by PSS / SSS, channel estimation SNR on the synchronization signal, SSB-RSRP, L1 / L3 RSRP;

[0772] The probability of the terminal successfully detecting the synchronization signal in the target cell, for example, the probability of the terminal successfully detecting the synchronization signal is more than X%, X being a specific threshold value; further, the probability of the terminal detecting the synchronization signal in a specific frequency domain position / time domain position / beam direction is more than X%;

[0773] The duration of the terminal detecting the synchronization signal in the target cell, for example, the duration of the terminal detecting the synchronization signal is less than M, M being a specific threshold value; further, the duration of the terminal detecting the synchronization signal in a specific frequency domain position / time domain position / beam direction is less than M;

[0774] The duration of the terminal measuring and the target cell is less than a certain preset value, and further, the measurement value of each target cell is higher than a threshold value;

[0775] The number of target reselection cells of the terminal is less than a certain preset value, and further, the successful access probability of each target reselection cell is higher than a threshold value;

[0776] The probability of the terminal successfully camping on the target cell;

[0777] Probability of terminal successfully synchronizing with target cell;

[0778] The number of model training times reaches a predefined value;

[0779] The number of iterations of fine tuning reaches a predetermined value.

[0780] Embodiment 7: UE side inference (see FIG. 7b)

[0781] Scenario description: UE infers the SSB transmission mode of the target cell (Cell B) based on the relevant configuration of the current serving cell (Cell A) and the AI model. This mode can reduce the measurement of Cell B and accelerate the reselection of the target cell.

[0782] The training of the AI model is in Cell A, and the AI model of Cell A is trained based on the relevant data of Cell A / Cell B. Further, Cell A and Cell B may need to interact with the training data.

[0783] Motivation: cell reselection, neighbor cell is in power saving mode, AI predicts the SSB transmission of the reselection cell, reduces the measurement of the neighbor cell. For example, some cells (Cell B) are in power saving mode, and the SSB transmission is based on the AI model, considering the UE that needs to reselect from Cell A; the UE has camped in Cell A, and the UE needs to perform cell reselection, based on AI to determine the SSB of the reselection cell for reception and measurement, and to reduce the measurement of the cell that may be reselected.

[0784] The UE obtains first configuration information from Cell A, and the first configuration information is used to determine the relevant parameters of the target AI model. The first configuration information can be carried by the SIB or other RRC signaling of the serving cell, for example, Cell-specific configuration (such as SIB, Paging message), UE-specific configuration (RRC release / setup message, Dedicated signaling).

[0785] The information or parameters included in the first configuration information are as follows:

[0786] The cell or cell group / frequency / TA to which the AI model needs to be applied;

[0787] Whether the UE needs to request the AI model from the network, for example, through random access messages (msg1, msg3, etc.), UCI, MAC CE, RRC message, etc. to request;

[0788] The type of AI model;

[0789] What are the input information of AI model?

[0790] What are the output results of AI model?

[0791] What is the applicable frequency / cell / area range of AI model inference, for example, applied to single or multiple frequency layers, to single or multiple cells (or cell groups), to the whole tracking area?

[0792] Further, the cells / cell groups / TRPs / TRP groups / frequency layers / frequencies / TAs to which AI model inference can be applied are determined in the following ways:

[0793] According to the configuration of the AI model, if the AI model configuration contains a list of applicable cells / cell groups / TRPs / TRP groups / frequency layers / frequencies / TAs, the list is determined according to the list.

[0794] According to the AI model prediction result, if the AI model prediction result includes a list of applied cells / cell groups / TRPs / TRP groups / frequency layers / frequencies / TAs;

[0795] According to the SSB or PBCH payload determination, the predefined information bits indicate whether the AI model can be applied to the cell / cell group / TRP / TRP group / frequency layer / frequency / TA corresponding to the received SSB.

[0796] If multiple cells / cell groups / TRPs / TRP groups / frequency layers / frequencies / TAs meet the AI model prediction conditions, how to determine which cell / cell group / TRP / TRP group / frequency layer / frequency / TA, for example, according to RSRP or priority, select the cell / cell group / TRP / TRP group / frequency layer / frequency / TA that meets the AI model prediction condition.

[0797] Whether the UE needs to request the AI model and AI model inference from the network, the request signal includes, for example, random access message (msg1, msg3, etc.), UCI, MAC CE, RRC message, etc.

[0798] Configuration information of the request signal, including time domain resource, frequency domain resource, sending time, period, format, etc.

[0799] Inference based on the AI model, the input information (i.e., the input parameters of the AI model) includes at least one of the following parameters or information: measurement value of Cell A, measurement value of Cell B, UE distribution of Cell A, UE distribution of Cell B, etc.

[0800] Inference based on the AI model, the output of the AI model includes at least one of the following:

[0801] Whether to measure Cell B (including one or more cells);

[0802] Whether to reselect to Cell B (including one or more cells);

[0803] Transmission mode of SSB of Cell B, such as frequency point of SSB, frequency domain starting position, band, carrier, BWP, synchronization raster, etc.; time domain position period, number, pattern (uniform or non-uniform) of SSB, further, SSB monitoring / detection window length (UE detects SSB in the monitoring window), time length of SSB transmission, number of transmission times or number of transmission periods, position of the first SSB after prediction starts to be transmitted;

[0804] Beam direction and number of SSB;

[0805] SSB transmission mode (if there are multiple modes, such as normal mode, simplified mode, and aggregation mode);

[0806] Whether Cell B is transmitting SSB.

[0807] When the UE performs AI model inference, the triggering mode of the AI model includes:

[0808] Method 1: The network instructs the UE to trigger AI model prediction, for example, through broadcast signaling or dedicated signaling indication, or through paging DCI / SSB / SIB indication.

[0809] Method 2: Determine whether to trigger AI model prediction according to preset conditions.

[0810] Trigger AI model prediction based on preset conditions, the preset conditions include at least one of the following:

[0811] S-criteria related conditions, e.g., the S-criteria power criterion corresponding to a threshold or interval is lower than a pre-set threshold or out of a pre-set interval; the S-criteria quality criterion corresponding to a threshold or interval is lower than a pre-set threshold or out of a pre-set interval; the layer 1 or layer 3 measurement power value (RSRP) corresponding to a threshold or interval is lower than a pre-set threshold or out of a pre-set interval; the layer 1 or layer 3 measurement quality value (RSRQ) corresponding to a threshold or interval is lower than a pre-set threshold or out of a pre-set interval; e.g., the RSRP or RSRQ of the serving cell, the RSRP or RSRQ of the reselection cell;

[0812] UE current state related conditions, e.g., the UE obtains the AI model configuration information of the target cell; the UE obtains the AI model configuration information of the target cell and knows that the target cell is in the SSB transmission mode of AI model inference; the UE obtains the AI model configuration information of the target cell and the UE does not satisfy the camping condition in the current serving cell; the UE obtains the AI model configuration information of the target cell and the UE does not satisfy the camping condition in the current serving cell, and the target cell is a suitable camping cell, that is, the UE needs to perform cell reselection; the UE obtains the AI model configuration information of the target cell and the UE triggers the RACH procedure on the target cell; the UE sends the uplink WUS; the UE sends the RACH related signal, such as msg1, msgA, msg3, etc.

[0813] After the UE triggers the AI model prediction according to the above rules and conditions, the UE can indicate at least one of the following through the uplink signal:

[0814] Triggering the sending of the measurement value corresponding to the AI model prediction, e.g., the S-criteria power criterion; the S-criteria quality criterion; the layer 1 or layer 3 measurement power value (RSRP); the layer 1 or layer 3 measurement quality value (RSRQ);

[0815] The physical layer cell index or group index predicted by the AI model;

[0816] The serving cell index or group index predicted by the AI model;

[0817] The SSB frequency point or group index predicted by the AI model;

[0818] The type information predicted by the AI model.

[0819] Embodiment 8: Network side inference (see FIG. 7c)

[0820] Scenario description: the network infers the SSB transmission mode of the target cell (Cell B) based on the related configuration and AI model of the current serving cell (Cell A). This mode can reduce unnecessary transmission to Cell B and reduce the energy consumption of Cell B.

[0821] The training of the AI model is performed at Cell A, and the AI model of Cell A is trained based on the relevant data of Cell A / Cell B. Further, the interaction training data of Cell A and Cell B can be required.

[0822] The network performs inference based on the AI model, and the input information includes at least one of the following parameters or information:

[0823] The measurement-related information reported by the terminal about Cell A, including historical measurement values and the latest measurement values, such as S criterion power standard; S criterion quality standard; layer 1 or layer 3 measurement power value (RSRP); layer 1 or layer 3 measurement quality value (RSRQ);

[0824] The measurement-related information reported by the terminal about Cell B, such as S criterion power standard; S criterion quality standard; layer 1 or layer 3 measurement power value (RSRP); layer 1 or layer 3 measurement quality value (RSRQ);

[0825] The attribute information of Cell B, such as physical layer cell index or group index; frequency band / frequency point / frequency layer of the cell; whether the cell allows camping;

[0826] The SSB transmission-related information of Cell B, such as at least one (energy-saving state or non-energy-saving state) SSB index or SSB set index; at least one (energy-saving state or non-energy-saving state) SSB frequency point, frequency domain starting position, band, carrier, BWP, synchronization raster, etc.; at least one (energy-saving state or non-energy-saving state) SSB time domain position period, number, pattern (uniform or non-uniform); at least one (energy-saving state or non-energy-saving state) SSB transmission time length, transmission number or transmission cycle number; at least one (energy-saving state or non-energy-saving state) SSB transmission starting position or ending position; at least one (energy-saving state or non-energy-saving state) SSB transmission beam direction, number; at least one (energy-saving state or non-energy-saving state) SSB transmission power, antenna configuration; the SSB includes at least one of the following: SSB being transmitted, SSB not in the transmission state, SSB in normal mode (transmitted in a specific period and mode), SSB in simplified mode (e.g., only SSB with minimum payload size), SSB in aggregation mode (e.g., multiple SSBs are continuously transmitted in a period of time), SSB about to start transmission;

[0827] The terminal receives detection-related characteristics of at least one SSB of Cell B, for example, frequency domain characteristics: RSSI, PSS / SSS detection signal strength, channel estimation SNR, etc. of at least one frequency point (per cell, per frequency layer, per channel bandwidth, per SCS, per band, per frequency range, per PLMN, etc.), synchronization success probability, access success probability, hypothetical BLER, PDCCH / SIB1 PDSCH BLER of at least one frequency point, SSB-RSRP, L1 / L3 RSRP; time domain characteristics: time domain symbol number of synchronization signals, time window length of time domain related detection, PSS / SSS detection signal strength, channel estimation SNR, etc. of at least one time domain position, synchronization success probability, access success probability, hypothetical BLER, PDCCH / SIB1 PDSCH BLER of at least one time domain position, SSB-RSRP, L1 / L3 RSRP of at least one time domain position; spatial characteristics: historical beam measurement results, current beam measurement results, link quality information (such as hypothetical BLER, PDCCH / PDSCH (MIB / SIB1) BLER);

[0828] UE distribution of Cell A and Cell B, for example, number, position, traffic volume, beam direction, channel quality of Connected UE; number, position, etc. of Idle UE; terminal position information, which can be specific geographic position coordinates (such as GPS coordinates), or approximate position range information of the terminal (such as range information of which street, which country), or position information of the terminal relative to the camping cell or the access cell (such as in the positive east direction of the camping cell); moving direction and moving speed of the terminal, which can be an absolute direction, such as east 40 degrees south; or a relative direction, such as a direction relative to a certain base station;

[0829] Geographical environment of Cell A and Cell B, for example, cell radius, geographical position, environment of the cell, antenna configuration, coverage performance of the cell; scenario information (such as inH, Uma, RMa, etc., or homogeneous / heterogeneous network (i.e. with or without overlapping coverage));

[0830] Time information, which can be specific to a particular time point, such as 13:25:38. It can also be a time range, such as 13:00-14:00, AM / PM, day / night. The time information can be timing information obtained over other RATs. The RATs can be, for example, Bluetooth, Wi-Fi, and 3G, 4G, or LTE, etc.

[0831] Inference based on the AI model, the output of the AI model including at least one of:

[0832] Whether to measure Cell B (including one or more Cells);

[0833] Whether to reselect to Cell B (including one or more Cells);

[0834] Transmission mode of SSB of Cell B, for example, frequency point of SSB, frequency domain starting position, band, carrier, BWP, synchronization raster, etc. of which SSB is located; time domain position period, number, pattern (uniform or non-uniform) of SSB, for example, SSB monitoring / detection window length (UE detects SSB within the monitoring window), time length of SSB transmission, number of transmission times or number of transmission periods, position of the first SSB after prediction starts to be transmitted; beam direction, number of SSB; SSB transmission mode (if there are multiple modes, for example, normal mode, simplified mode, aggregation mode); whether Cell B is transmitting SSB.

[0835] Cell A transmits second information for indicating the result of AI model inference. The second information can be carried by SIB or other RRC signaling of Cell A, specifically, for example, Cell-specific configuration (such as SIB, Paging message), UE-specific configuration (such as RRC release / setup message, Dedicated signaling).

[0836] The second information can also include the following information or parameters:

[0837] Cell or cell group / frequency / TA to which the result of AI model inference needs to be applied, for example, frequency / cell / area range to which the AI model inference is applicable, such as applied to a single or multiple frequency layers, applied to a single or multiple cells (or cell group), applied to the entire tracking area.

[0838] Further, the cells / cell groups / TRPs / TRP groups / frequency layers / frequency points / TAs that the AI model inference can be applied to are determined according to the following manners:

[0839] According to the AI model configuration determination, if the AI model configuration contains a list of applicable cells / cell groups / TRPs / TRP groups / frequency layers / frequency points / TAs, the list is determined according to the list;

[0840] According to the AI model prediction result determination, if the AI model prediction result includes a list of applicable cells / cell groups / TRPs / TRP groups / frequency layers / frequency points / TAs;

[0841] According to the Cell B SSB or PBCH payload determination, a predefined information bit indicates whether the AI model can be applied to the cell / cell group / TRP / TRP group / frequency layer / frequency point / TA corresponding to the SSB.

[0842] Further, if there are multiple cells / cell groups / TRPs / TRP groups / frequency layers / frequency points / TAs that meet the AI model prediction conditions, the cell / cell group / TRP / TRP group / frequency layer / frequency point / TA that meets the AI model prediction condition can be selected according to the RSRP or priority.

[0843] Embodiment 9: AI model prediction and training related capability determination

[0844] In some embodiments, one or more AI related capabilities are defined for cell search or reselection related detection signal resource information inference or model training:

[0845] The terminal has an AI model capability for determining an alternative cell or alternative cell SSB transmission mode through AI training;

[0846] The terminal has an AI prediction capability for predicting an alternative cell or alternative cell SSB transmission mode through AI model prediction;

[0847] The terminal reports one or more types of assistance information for AI prediction capability for predicting an alternative cell or alternative cell SSB transmission mode through AI model prediction;

[0848] The terminal reports one or more kinds of assistance information to train the AI model for determining the candidate cell or the candidate cell SSB transmission mode;

[0849] The network indicates the AI model training for determining the candidate cell or the candidate cell SSB transmission mode by one or more kinds of assistance information;

[0850] The network indicates the AI prediction capability for predicting the candidate cell or the candidate cell SSB transmission mode by the AI model;

[0851] The network indicates one or more kinds of assistance information for predicting the candidate cell or the candidate cell SSB transmission mode by the AI model;

[0852] The network indicates one or more kinds of assistance information to train the AI model for determining the candidate cell or the candidate cell SSB transmission mode;

[0853] The server indicates the AI model training for determining the candidate cell or the candidate cell SSB transmission mode by one or more kinds of assistance information;

[0854] The server indicates the AI prediction capability for predicting the candidate cell or the candidate cell SSB transmission mode by the AI model;

[0855] The server indicates one or more kinds of assistance information for predicting the candidate cell or the candidate cell SSB transmission mode by the AI model;

[0856] The server indicates one or more kinds of assistance information to train the AI model for determining the candidate cell or the candidate cell SSB transmission mode.

[0857] As a sub-embodiment of the above embodiment, the AI-related capability is determined by one or more of the following ways:

[0858] Depending on the terminal type, such as introducing different AI-related capabilities for different terminal types (such as redcap, IoT);

[0859] Depending on the network type, such as introducing different AI-related capabilities for different network types (such as NTN, TN);

[0860] Indicated by one or more reference signals, such as PRACH resources indicating a certain AI prediction for predicting cell search or reselection-related detection signal resource information;

[0861] Carried by uplink control information, such as physical layer control information (such as UCI information reported by the terminal to the network);

[0862] Carried by RRC signaling;

[0863] Carried by the interface message between the specific terminal and the server side, the specific message here can be a message related to a specific AI model or a message related to all AI models;

[0864] Carried by the interface message between the specific terminal and the network, the specific message here can be a message related to a specific AI model or a message related to all AI models;

[0865] Carried by the interface message between the specific server and the network, the specific message here can be a message related to a specific AI model or a message related to all AI models.

[0866] To sum up, through the embodiments of the present application, the network side device and the terminal can reduce energy consumption when performing cell measurement and cell reselection, and the network side device can perform signal transmission more efficiently, thereby improving the performance of terminal measurement and reselection.

[0867] The transmission control method provided by the embodiments of the present application can be executed by a transmission control device. In the embodiments of the present application, the transmission control device is taken as an example to illustrate the transmission control device provided by the embodiments of the present application.

[0868] The embodiments of the present application provide a transmission control device. As an example, the transmission control device can be a communication device or a component in the communication device, such as a chip. The communication device can be a terminal, a network side device, a server, or the like. For example, 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 are not limited specifically.

[0869] The transmission control apparatus comprises 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, which can include a general-purpose processor, a special-purpose processor, etc., such as a Central Processing Unit (CPU), a microprocessor, a Digital Signal Processor (DSP), an Artificial Intelligent (AI) processor, a GPU, an ASIC, a Network Processor (NP), a Field Programmable Gate Array (FPGA) or other programmable logic devices, gate circuits, transistors, discrete hardware components, etc. The receiving module and the sending module can be implemented by a communication interface, which can include one or more of a transceiver, a pin, a circuit, a bus, a radio frequency unit, etc.

[0870] Specifically, referring to FIG. 8, when the transmission control apparatus is a terminal or a component in the terminal or a network-side device or a component in the network-side device, the transmission control apparatus 800 comprises:

[0871] a first processing module 801 configured to obtain target information, the target information being obtained based on a first model;

[0872] a second processing module 802 configured to perform a first operation based on the target information;

[0873] The target information comprises at least one of the following:

[0874] information of a target cell set;

[0875] target time information, the target time information being used for indicating at least one of the following: time information corresponding to a first flow; time information corresponding to measuring a first signal; time information corresponding to transmitting a second signal;

[0876] target transmission information, the target transmission information comprising at least one of the following: time domain information of a target synchronization signal set; frequency domain information of the target synchronization signal set; spatial domain information of the target synchronization signal set; index information of the target synchronization signal set; transmission mode information of the target synchronization signal set;

[0877] The first operation comprises at least one of the following: turning on or off at least one target cell; switching a state of at least one target cell; transmitting or receiving at least one target signal; performing a second flow; performing a first measurement, the first measurement comprising measuring based on at least one target cell;

[0878] The first procedure comprises at least one of cell selection and cell reselection.

[0879] The first signal comprises at least one of a synchronization signal and a reference signal (RS).

[0880] The second signal comprises at least one of a wake-up signal, a positioning signal, a sounding signal and a random access message.

[0881] The second procedure comprises at least one of cell selection, cell reselection, reselection to a target cell, handover to a target transmission / reception point (TRP), handover to a target transmission configuration indication (TCI) configuration, handover to a target RS.

[0882] The target cell comprises at least one of a physical cell, a carrier and a TRP.

[0883] The target signal comprises at least one of a synchronization signal, a paging signal and a random access channel (RACH).

[0884] Optionally, the information of the target cell set is used to indicate at least one of: at least one target reselection cell; at least one target camping cell; at least one target measurement cell.

[0885] Optionally, the target measurement cell is a cell for synchronization signal transmission and / or RS transmission.

[0886] Optionally, the time domain information of the target synchronization signal set comprises at least one of: a system frame number (SFN) of the target synchronization signal set; a reference time position of the target synchronization signal set; a period of the target synchronization signal set; an interval between synchronization signals of the target synchronization signal set; a start time or an end time of the target synchronization signal set; a number of the target synchronization signal set.

[0887] Optionally, the frequency domain information of the target synchronization signal set comprises at least one of: a synchronization raster corresponding to the target synchronization signal set; a center frequency point of the target synchronization signal set; a frequency band corresponding to the target synchronization signal set.

[0888] Optionally, the spatial domain information of the target synchronization signal set comprises at least one of: a spatial property of the target synchronization signal set; a beam direction of the target synchronization signal set; a TRP corresponding to the target synchronization signal set.

[0889] Optionally, the transmission mode information is used to indicate at least one of: whether to comprise a SIB; whether to be a synchronization signal of on-demand transmission; whether to allow cell access; whether to allow cell camping.

[0890] Optionally, the switching the state of the at least one target cell comprises at least one of:

[0891] switching the state of the at least one target cell from the energy saving state to the normal state or the non-energy saving state;

[0892] switching the state of the at least one target cell from the normal state or the non-energy saving state to the energy saving state.

[0893] Optionally, the transmitting or receiving the at least one target signal comprises:

[0894] transmitting or receiving a target signal corresponding to the at least one target cell based on the target transmission information.

[0895] Optionally, the first operation is performed at a target time, and the target time is determined based on at least one of:

[0896] a predefined or preconfigured time window;

[0897] a predefined or preconfigured time period;

[0898] a predefined or preconfigured timer;

[0899] a predefined or preconfigured time region.

[0900] Optionally, the first processing module is specifically configured to:

[0901] predict target information based on the first model.

[0902] Optionally, the first model comprises at least one of a first artificial intelligence (AI) module, a second AI module, and a third AI module.

[0903] the first processing module is specifically configured to at least one of:

[0904] predict information of the target cell set based on the first AI module;

[0905] predict the target time information based on the second AI module;

[0906] predict the target transmission information based on the third AI module.

[0907] Optionally, the apparatus further comprises:

[0908] a third processing module configured to obtain target configuration information, the target configuration information being used to determine a related parameter of the first model.

[0909] Optionally, the target configuration information is used to indicate at least one of:

[0910] at least one of a cell, a cell group, a TRP and a TRP group corresponding to the first model;

[0911] at least one of a frequency layer and a frequency point corresponding to the first model;

[0912] a tracking area (TA) corresponding to the first model;

[0913] requesting the first model;

[0914] a type of the first model;

[0915] an input parameter of the first model;

[0916] an output parameter of the first model.

[0917] Optionally, the first processing module is specifically configured to perform at least one of the following:

[0918] predict the target information based on the first model in a case where a first indication is received, the first indication being used to indicate that the first device triggers prediction of the first model;

[0919] predict the target information based on the first model in a case where a preset condition is met;

[0920] The preset condition includes at least one of the following:

[0921] a cell reselection related condition;

[0922] a state related condition of the first device.

[0923] Optionally, the cell reselection related condition includes at least one of the following:

[0924] a threshold corresponding to an S-criterion power standard is lower than a first preset threshold, or an interval corresponding to the S-criterion power standard exceeds a first preset interval;

[0925] a threshold corresponding to an S-criterion quality standard is lower than a second preset threshold, or an interval corresponding to the S-criterion quality standard exceeds a second preset interval;

[0926] a threshold corresponding to a measurement power value of layer 1 or layer 3 is lower than a third preset threshold, or an interval corresponding to the measurement power value of layer 1 or layer 3 exceeds a third preset interval;

[0927] a threshold corresponding to a measurement quality value of layer 1 or layer 3 is lower than a fourth preset threshold, or an interval corresponding to the measurement power value of layer 1 or layer 3 exceeds a fourth preset interval.

[0928] Optionally, the state related condition of the first device includes at least one of the following:

[0929] The first device obtains target configuration information, which is used to determine a related parameter of the first model.

[0930] The first device obtains the target configuration information and transmission parameters of synchronization signals of one or more cells.

[0931] Optionally, the apparatus further comprises:

[0932] The sending module is configured to send a third signal, the third signal being used to indicate at least one of the following:

[0933] A target measurement value, the target measurement value being a measurement value corresponding to triggering the first model to perform prediction;

[0934] A physical layer cell index or a physical layer cell group index predicted by the first model;

[0935] A serving cell index or a serving cell group index predicted by the first model;

[0936] Transmission parameters of the first signal predicted by the first model.

[0937] Optionally, the prediction manner of the first model comprises at least one of the following:

[0938] The prediction of the first model is based on one or more preset or preconfigured beams;

[0939] The prediction of the first model is based on one or more preset or preconfigured cells;

[0940] The prediction of the first model is based on one or more preset or preconfigured frequency layers;

[0941] The prediction of the first model is based on one or more preset or preconfigured cell groups;

[0942] The prediction of the first model is based on one or more preset or preconfigured TAs;

[0943] The prediction of the first model is based on one or more preset or preconfigured time domain resources;

[0944] The prediction of the first model is based on one or more preset or preconfigured devices.

[0945] Optionally, the input parameter of the first model comprises at least one of the following:

[0946] Measurement related information of one or more cells;

[0947] Attribute information of one or more cells;

[0948] transmission related information of the first signal corresponding to one or more cells;

[0949] detection related features of the first signal corresponding to one or more cells;

[0950] related information of one or more devices;

[0951] geographical environment information;

[0952] time information.

[0953] Optionally, the measurement related information comprises at least one of:

[0954] S criterion power criterion;

[0955] S criterion quality criterion;

[0956] a measurement power value of layer 1 or layer 3;

[0957] a measurement quality value of layer 1 or layer 3.

[0958] Optionally, the attribute information comprises at least one of:

[0959] a physical layer cell index or a physical layer cell group index;

[0960] a frequency band, a frequency point or a frequency layer where the cell is located;

[0961] whether the cell allows camping.

[0962] Optionally, the transmission related information comprises at least one of:

[0963] an index or a set index;

[0964] at least one of a frequency point, a frequency domain starting position, a frequency band, a carrier, a partial bandwidth BWP and a synchronization raster;

[0965] at least one of a position in time domain, a period, a quantity and a type;

[0966] at least one of a transmission time length, a transmission number and a transmission period;

[0967] at least one of a transmission starting position and a transmission ending position;

[0968] at least one of a beam direction and a beam quantity;

[0969] at least one of a transmission power and antenna configuration information.

[0970] Optionally, the detection related features comprises at least one of:

[0971] a received signal strength indication (RSSI) of the at least one frequency point;

[0972] a detection signal strength of a primary synchronization signal (PSS) or a secondary synchronization signal (SSS) of the at least one frequency point;

[0973] a channel estimation signal-to-noise ratio (SNR) of the at least one frequency point;

[0974] at least one of a synchronization success probability, an access success probability, a hypothetical block error rate (BLER), a physical downlink control channel (PDCCH) block error rate, a SIB1 block error rate, and a physical downlink shared channel (PDSCH) block error rate of the at least one frequency point;

[0975] a reference signal received power (RSRP) of the at least one frequency point;

[0976] a number of time domain symbols of the synchronization signal;

[0977] a time window length of the time domain related detection;

[0978] a PSS or SSS detection signal strength of the at least one time domain position;

[0979] a SNR of the at least one time domain position;

[0980] at least one of a synchronization success probability, an access success probability, a hypothetical BLER, a PDCCH block error rate, a SIB1 block error rate, and a PDSCH block error rate of the at least one time domain position;

[0981] a RSRP of the at least one time domain position;

[0982] a historical beam measurement result;

[0983] a current beam measurement result;

[0984] link quality information.

[0985] Optionally, the related information of the at least one device includes at least one of:

[0986] at least one of a number, a location, a traffic volume, a beam direction, and a channel quality of the at least one device in a connected state;

[0987] at least one of a number and a location of the at least one device in an idle state;

[0988] location information of the at least one device;

[0989] a moving direction and a moving speed of the at least one device.

[0990] Optionally, the synchronization signal corresponding to the one or more cells includes at least one of:

[0991] a synchronization signal being transmitted;

[0992] a synchronization signal not being transmitted;

[0993] a synchronization signal in normal mode;

[0994] a synchronization signal in simplified mode;

[0995] a synchronization signal in aggregated mode;

[0996] a synchronization signal about to be transmitted.

[0997] The transmission control apparatus provided by the embodiments of the present application can implement each process implemented by the method embodiments of FIG. 5, and achieve the same technical effects. To avoid repetition, details are not described herein.

[0998] As shown in FIG. 9, the embodiments of the present application further provide a communication device 900, which includes a processor 901 and a memory 902, and the memory 902 stores programs or instructions executable on the processor 901. For example, when the communication device 900 is a terminal, each step of the above-mentioned first device-side method embodiments is implemented when the programs or instructions are executed by the processor 901, and the same technical effects can be achieved. To avoid repetition, details are not described herein.

[0999] 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. 5. The terminal embodiments correspond to the above-mentioned first device-side method embodiments, and each implementation process and implementation manner of the above-mentioned method embodiments can be applied to the terminal embodiments, and the same technical effects can be achieved. The terminal can be the transmission control apparatus shown in FIG. 8. Specifically, FIG. 10 is a schematic diagram of a hardware structure of a terminal implementing the embodiments of the present application.

[1000] The terminal 1000 includes, but is not limited to, at least part of the components such as a radio frequency unit 1001, a network module 1002, an audio output unit 1003, an input unit 1004, a sensor 1005, a display unit 1006, a user input unit 1007, an interface unit 1008, a memory 1009, and a processor 1010.

[1001] Those skilled in the art can understand that the terminal 1000 can further include a power supply (such as a battery) for supplying power to each component, and the power supply can be logically connected to the processor 1010 through a power management system, so as to realize functions such as power management, discharge management, and power consumption management through the power management system. The terminal structure shown in FIG. 10 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 herein.

[1002] It should be understood that in the embodiments of the present application, the input unit 1004 can include a graphics processor 10041 and a microphone 10042, and the graphics processor 10041 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 1006 can include a display panel 10061, which can be configured in the form of a liquid crystal display, an organic light-emitting diode, etc. The user input unit 1007 includes at least one of a touch panel 10071 and other input devices 10072. The touch panel 10071 is also called a touch screen. The touch panel 10071 can include two parts of a touch detection device and a touch controller. The other input devices 10072 can include, but are not limited to, a physical keyboard, function keys (such as volume control keys, on-off keys, etc.), a trackball, a mouse, a joystick, etc., which will not be described here.

[1003] In the embodiments of the present application, after the radio frequency unit 1001 receives the downlink data from the network side device, it can be transmitted to the processor 1010 for processing; in addition, the radio frequency unit 1001 can send uplink data to the network side device. Generally, the radio frequency unit 1001 includes, but is not limited to, an antenna, an amplifier, a transceiver, a coupler, a low noise amplifier, a duplexer, etc.

[1004] The memory 1009 can be used to store software programs or instructions and various data. The memory 1009 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 1009 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 1009 in the embodiments of the present application includes but is not limited to these and any other suitable types of memory.

[1005] The processor 1010 can include one or more processing units; optionally, the processor 1010 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 1010.

[1006] The processor 1010 is configured to:

[1007] obtain target information, the target information being obtained based on a first model;

[1008] perform a first operation based on the target information;

[1009] The target information includes at least one of the following:

[1010] information of a target cell set;

[1011] target time information, the target time information being used for indicating at least one of the following: time information corresponding to the first procedure; time information corresponding to the measurement of the first signal; time information corresponding to the transmission of the second signal;

[1012] target transmission information, the target transmission information including at least one of the following: time domain information of a target synchronization signal set; frequency domain information of the target synchronization signal set; spatial domain information of the target synchronization signal set; index information of the target synchronization signal set; transmission mode information of the target synchronization signal set;

[1013] the first operation including at least one of the following: turning on or off at least one target cell; switching a state of at least one target cell; transmitting or receiving at least one target signal; performing a second procedure; performing a first measurement, the first measurement including performing measurement based on at least one target cell;

[1014] wherein the first procedure includes at least one of cell selection and cell reselection;

[1015] the first signal including at least one of a synchronization signal and a reference signal (RS);

[1016] the second signal including at least one of a wake-up signal, a positioning signal, a sounding signal and a random access message;

[1017] the second procedure including at least one of cell selection, cell reselection, reselecting or camping on a target cell, switching a target transmission / reception point (TRP), switching a target transmission configuration indication (TCI) configuration, switching a target RS;

[1018] the target cell including at least one of a physical cell, a carrier and a TRP;

[1019] the target signal including at least one of a synchronization signal, a paging signal and a random access channel (RACH).

[1020] In the embodiments of the present application, since the terminal can obtain the target information obtained based on the first model, the target information can provide a basis for the terminal to perform the transmission control related operation (i.e., the first operation), thereby improving the effect of the terminal on transmission control.

[1021] It can be understood that the implementation processes of the implementation manners mentioned in the embodiments can refer to the related descriptions of the transmission control method embodiments, and achieve the same or corresponding technical effects. To avoid repetition, they will not be described here again.

[1022] The embodiment of the present application further provides a network side device, comprising a processor and a communication interface, the communication interface and the processor are coupled, the processor is used for running programs or instructions, and the steps of the method embodiment shown in FIG. 5 are realized. The network side device embodiment corresponds to the above-mentioned first device side method embodiment, each implementation process and implementation manner of the above-mentioned method embodiment can be applied to the network side device embodiment, and the same technical effects can be achieved.

[1023] Specifically, the embodiment of the present application further provides a network side device, which can be the transmission control device shown in FIG. 8. As shown in FIG. 11, the network side device 1100 comprises an antenna 111, a radio frequency device 112, a baseband device 113, a processor 114 and a memory 115. The antenna 111 is connected with the radio frequency device 112. In the uplink direction, the radio frequency device 112 receives information through the antenna 111, and sends the received information to the baseband device 113 for processing. In the downlink direction, the baseband device 113 processes the information to be sent, and sends it to the radio frequency device 112. The radio frequency device 112 processes the received information and sends it out through the antenna 111.

[1024] The method performed by the network side device in the above embodiment can be realized in the baseband device 113, and the baseband device 113 comprises a baseband processor.

[1025] The baseband device 113 may, for example, comprise at least one baseband board, and a plurality of chips are arranged on the baseband board, as shown in FIG. 11. One of the chips is, for example, a baseband processor, which is connected with the memory 115 through a bus interface to call programs in the memory 115 and execute the network device operations shown in the above method embodiment.

[1026] The network side device may, for example, further comprise a network interface 116, which is, for example, a common public radio interface (Common Public Radio Interface, CPRI).

[1027] Specifically, the network side device 1100 of the embodiment of the present application further comprises instructions or programs stored in the memory 115 and executable on the processor 114, the processor 114 calls the instructions or programs in the memory 115 to execute the method performed by each module shown in FIG. 8, and achieves the same technical effects. To avoid repetition, details are not described here.

[1028] Specifically, the embodiment of the present application further provides a network side device. As shown in FIG. 12, the network side device 1200 includes a processor 1201, a network interface 1202 and a memory 1203. The network side device can be the transmission control apparatus shown in FIG. 8. The network interface 1202 is, for example, a common public radio interface (CPRI).

[1029] Specifically, the network side device 1200 of the embodiment of the present application further includes instructions or programs stored in the memory 1203 and executable on the processor 1201, the processor 1201 invokes the instructions or programs in the memory 1203 to execute the method performed by each module shown in FIG. 8, and achieves the same technical effect. To avoid repetition, details are not described herein.

[1030] The embodiment of the present application further provides a readable storage medium, the readable storage medium stores programs or instructions, the programs or instructions are executed by a processor to implement each process of the above-mentioned transmission control method embodiment, and the same technical effect can be achieved. To avoid repetition, details are not described herein.

[1031] The processor is the processor in the terminal in the above-mentioned embodiment. The readable storage medium includes a computer readable storage medium, such as a computer readable only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc. In some examples, the readable storage medium can be a non-transient readable storage medium.

[1032] The embodiment of the present application further provides a chip, the chip includes a processor and a communication interface, the communication interface and the processor are coupled, the processor is used to run programs or instructions to implement each process of the above-mentioned transmission control method embodiment, and the same technical effect can be achieved. To avoid repetition, details are not described herein.

[1033] 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.

[1034] The embodiment of the present application further provides a computer program / program product, the computer program / program product is stored in a storage medium, the computer program / program product is executed by at least one processor to implement each process of the above-mentioned transmission control method embodiment, and the same technical effect can be achieved. To avoid repetition, details are not described herein.

[1035] The embodiment of the present application further provides a communication system, including a terminal and a network side device, the terminal can be used to execute the steps of the transmission control method as described above, and the network side device can be used to execute the steps of the transmission control method as described above. The embodiment of the present application further provides a communication system, including a terminal and a network side device, the terminal can be used to execute the steps of the transmission control method as described above, and the network side device can be used to execute the steps of the transmission control method as described above.

[1036] It should be noted that, as used in this application, the terms "comprises", "comprising", or any other variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but can also include other elements not expressly listed or inherent to such process, method, article, or apparatus. An element proceeded by "comprises... a" does not, without more constraints, exclude the presence of additional identical elements in the process, method, article, or apparatus that comprises the element. Furthermore, it should be noted that the methods and apparatus of the present application can be implemented in a variety of orders of the steps or stages, unless otherwise specifically limited, and that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting. Also, it should be noted that features described in relation to certain examples can be combined in other examples.

[1037] Those skilled in the art can clearly understand that the above-mentioned embodiment method can be realized by means of computer software product and general hardware platform, of course, it can also be realized by hardware. The computer software product is stored in a storage medium (such as ROM, RAM, magnetic disc, optical disc, etc.), and includes a plurality of instructions for making terminal or network side equipment execute the method described in various embodiments of the present application.

[1038] The embodiments of the present application are described above in combination with the drawings, but the present application is not limited to the above-mentioned specific embodiments, and the above-mentioned specific embodiments are only illustrative, but not restrictive. Those skilled in the art can make many forms of embodiments under the inspiration of the present application without departing from the scope of the present application and the scope of protection of the claims.

Claims

A transmission control method, comprising: a first device obtaining target information, the target information being obtained based on a first model; the first device performing a first operation based on the target information; wherein the target information comprises at least one of: information of a target cell set; target time information, the target time information being used to indicate at least one of: time information corresponding to a first procedure; time information corresponding to measuring a first signal; time information corresponding to transmitting a second signal; target transmission information, the target transmission information comprising at least one of: time domain information of a target synchronization signal set; frequency domain information of the target synchronization signal set; spatial domain information of the target synchronization signal set; index information of the target synchronization signal set; transmission mode information of the target synchronization signal set; the first operation comprising at least one of: turning on or off at least one target cell; switching a state of at least one target cell; transmitting or receiving at least one target signal; performing a second procedure; performing a first measurement, the first measurement comprising measuring based on at least one target cell; wherein the first procedure comprises at least one of: cell selection and cell reselection; the first signal comprising at least one of: a synchronization signal and a reference signal (RS); the second signal comprising at least one of: a wake-up signal, a positioning signal, a sounding signal and a random access message; the second procedure comprising at least one of: cell selection, cell reselection, reselecting or camping to a target cell, switching a target transmission / reception point (TRP), switching a target transmission configuration indication (TCI) configuration, switching a target RS; the target cell comprising at least one of: a physical cell, a carrier and a TRP; the target signal comprising at least one of: a synchronization signal, a paging signal and a random access channel (RACH). The method of claim 1, wherein, the information of the target cell set being used to indicate at least one of: at least one target reselection cell; at least one target camping cell; at least one target measurement cell. The method of claim 2, wherein, the target measurement cell being a cell for synchronization signal transmission and / or RS transmission. The method of any one of claims 1 to 3, wherein, the time domain information of the target synchronization signal set comprising at least one of: a system frame number (SFN) of the target synchronization signal set; a reference time position of the target synchronization signal set; a periodicity of the target synchronization signal set; an interval between synchronization signals of the target synchronization signal set; a start time or an end time of the target synchronization signal set; a number of the target synchronization signal set; or, the frequency domain information of the target synchronization signal set comprising at least one of: a synchronization raster corresponding to the target synchronization signal set; a center frequency point of the target synchronization signal set; a frequency band corresponding to the target synchronization signal set; or, the spatial domain information of the target synchronization signal set comprising at least one of: a spatial property of the target synchronization signal set; a beam direction of the target synchronization signal set; a TRP corresponding to the target synchronization signal set. The method of any one of claims 1 to 4, wherein, the transmission mode information being used to indicate at least one of: whether to include a system information block (SIB); whether to be a synchronization signal transmitted on demand; whether to allow cell access; whether to allow cell camping. The method of any one of claims 1 to 5, wherein, The switching the state of the at least one target cell comprises at least one of: switching the state of the at least one target cell from the energy saving state to the normal state or the non-energy saving state; switching the state of the at least one target cell from the normal state or the non-energy saving state to the energy saving state. The method of any one of claims 1 to 6, wherein, The transmitting or receiving the at least one target signal comprises: transmitting or receiving a target signal corresponding to the at least one target cell based on the target transmission information. The method of any one of claims 1 to 7, wherein, The first operation is performed at a target time, and the target time is determined based on at least one of: a predefined or preconfigured time window; a predefined or preconfigured time period; a predefined or preconfigured timer; a predefined or preconfigured time region. The method of any one of claims 1 to 8, wherein, The first device obtains target information, comprising: The first device predicts target information based on the first model. The method of claim 9, wherein, The first model comprises at least one of a first artificial intelligence (AI) module, a second AI module, and a third AI module. The first device predicts target information based on the first model, comprising at least one of: predicting information of the target cell set based on the first AI module; predicting the target time information based on the second AI module; predicting the target transmission information based on the third AI module. The method according to claim 9 or 10, wherein The method further comprises: The first device obtains target configuration information, which is used to determine related parameters of the first model. The method of claim 11, wherein, The target configuration information is used to indicate at least one of: at least one of a cell, a cell group, a TRP, and a TRP group corresponding to the first model; at least one of a frequency layer and a frequency point corresponding to the first model; a tracking area (TA) corresponding to the first model; the first model; a type of the first model; an input parameter of the first model; an output parameter of the first model. The method of any one of claims 9 to 12, wherein, The first device predicts the target information based on the first model, comprising at least one of: The first device predicts the target information based on the first model in a case where a first indication is received, the first indication being used to indicate that the first device triggers prediction of the first model; The first device predicts the target information based on the first model in a case where a preset condition is met. The preset condition comprises at least one of: a cell reselection related condition; a state related condition of the first device. The method of claim 13, wherein, The cell reselection related condition comprises at least one of: a threshold corresponding to an S-criterion power standard is lower than a first preset threshold, or an interval corresponding to the S-criterion power standard exceeds a first preset interval; a threshold corresponding to an S-criterion quality standard is lower than a second preset threshold, or an interval corresponding to the S-criterion quality standard exceeds a second preset interval; a threshold corresponding to a measurement power value of layer 1 or layer 3 is lower than a third preset threshold, or an interval corresponding to the measurement power value of layer 1 or layer 3 exceeds a third preset interval; a threshold corresponding to a measurement quality value of layer 1 or layer 3 is lower than a fourth preset threshold, or an interval corresponding to the measurement power value of layer 1 or layer 3 exceeds a fourth preset interval. The state related condition of the first device comprises at least one of: ​ The first device obtains target configuration information, which is used to determine the related parameters of the first model. The first device obtains the target configuration information and the transmission parameters of the synchronization signals of one or more cells. The method according to claim 13 or 14, wherein Further comprising: The first device sends a third signal, which is used to indicate at least one of the following: Target measurement value, which is the measurement value corresponding to triggering the first model to make a prediction; The physical layer cell index or the physical layer cell group index predicted by the first model; The serving cell index or the serving cell group index predicted by the first model; The transmission parameters of the first signal predicted by the first model. The method of any one of claims 1 to 15, wherein, The prediction mode of the first model includes at least one of the following: Making a prediction based on one or more preset or preconfigured beams; Making a prediction based on one or more preset or preconfigured cells; Making a prediction based on one or more preset or preconfigured frequency layers; Making a prediction based on one or more preset or preconfigured cell groups; Making a prediction based on one or more preset or preconfigured TAs; Making a prediction based on one or more preset or preconfigured time domain resources; Making a prediction based on one or more preset or preconfigured devices. The method of any one of claims 1 to 16, wherein, The input parameters of the first model include at least one of the following: Measurement related information of one or more cells; Attribute information of one or more cells; Transmission related information of the first signal corresponding to one or more cells; Detection related features of the first signal corresponding to one or more cells; Related information of one or more devices; Geographical environment information; Time information. The method of claim 17, wherein, The measurement related information includes at least one of the following: S criterion power standard; S criterion quality standard; Layer 1 or layer 3 measurement power value; Layer 1 or layer 3 measurement quality value; Or, The attribute information includes at least one of the following: Physical layer cell index or physical layer cell group index; Frequency band, frequency point or frequency layer where the cell is located; Whether the cell allows camping; Or, The transmission related information includes at least one of the following: Index or set index; At least one of frequency point, frequency domain starting position, frequency band, carrier, partial bandwidth BWP and synchronization raster; At least one of position, period, number and type in time domain; At least one of transmission time length, transmission times and transmission period; At least one of transmission starting position and transmission ending position; At least one of beam direction and beam number; At least one of transmission power and antenna configuration information; Or, The detection related features include at least one of the following: Received signal strength indication RSSI of at least one frequency point; Detection signal strength of primary synchronization signal PSS or secondary synchronization signal SSS of at least one frequency point; Channel estimation signal to noise ratio SNR of at least one frequency point; at least one of a synchronization success probability, an access success probability, a hypothetical block error rate (BLER), a physical downlink control channel (PDCCH) block error rate, a SIB1 block error rate, and a physical downlink shared channel (PDSCH) block error rate of at least one frequency point; a reference signal received power (RSRP) of at least one frequency point; a number of time domain symbols of a synchronization signal; a time window length of a time domain correlation detection; a PSS or SSS detection signal strength of at least one time domain position; an SNR of at least one time domain position; at least one of a synchronization success probability, an access success probability, a hypothetical BLER, a PDCCH block error rate, a SIB1 block error rate, and a PDSCH block error rate of at least one time domain position; an RSRP of at least one time domain position; a historical beam measurement result; a current beam measurement result; link quality information; or relevant information of the at least one device, including at least one of: at least one of a number, a location, a traffic volume, a beam direction, and a channel quality of at least one device in a connected state; at least one of a number and a location of at least one device in an idle state; location information of at least one device; a moving direction and a moving speed of at least one device. The method of claim 17, wherein, a synchronization signal corresponding to the one or more cells, including at least one of: a synchronization signal being transmitted; a synchronization signal not in a transmitting state; a synchronization signal in a normal mode; a synchronization signal in a simplified mode; a synchronization signal in an aggregated mode; a synchronization signal to be transmitted. A transmission control apparatus, the apparatus comprising: a first processing module configured to obtain target information, the target information being obtained based on a first model; a second processing module configured to perform a first operation based on the target information; wherein the target information includes at least one of: information of a target cell set; target time information, the target time information being used to indicate at least one of: time information corresponding to a first procedure; time information corresponding to measuring a first signal; time information corresponding to transmitting a second signal; target transmission information, the target transmission information including at least one of: time domain information of a target synchronization signal set; frequency domain information of the target synchronization signal set; spatial domain information of the target synchronization signal set; index information of the target synchronization signal set; transmission mode information of the target synchronization signal set; the first operation including at least one of: turning on or off at least one target cell; switching a state of at least one target cell; transmitting or receiving at least one target signal; performing a second procedure; performing a first measurement, the first measurement including measuring based on at least one target cell; wherein the first procedure includes at least one of cell selection and cell reselection; the first signal including at least one of a synchronization signal and a reference signal (RS); the second signal including at least one of a wake-up signal, a positioning signal, a sounding signal, and a random access message; the second procedure including at least one of cell selection, cell reselection, reselecting or camping on a target cell, switching a target transmission / reception point (TRP), switching a target transmission configuration indication (TCI) configuration, switching a target RS. The target cell comprises at least one of a physical cell, a carrier and a TRP; The target signal comprises at least one of a synchronization signal, a paging signal and a random access channel (RACH). The apparatus of claim 20, wherein The state of the at least one target cell is switched, comprising at least one of: Switching the state of the at least one target cell from an energy saving state to a normal state or a non-energy saving state; Switching the state of the at least one target cell from a normal state or a non-energy saving state to an energy saving state. The apparatus of claim 20 or 21, wherein The transmission or reception of the at least one target signal comprises: Transmitting or receiving a target signal corresponding to the at least one target cell based on the target transmission information. The apparatus of any one of claims 20 to 22, wherein The first processing module is specifically configured to: Predict target information based on the first model. The apparatus of claim 23, wherein The first model comprises at least one of a first artificial intelligence (AI) module, a second AI module and a third AI module. The first processing module is specifically configured to at least one of: Predict information of the target cell set based on the first AI module; Predict the target time information based on the second AI module; Predict the target transmission information based on the third AI module. The apparatus of claim 23 or 24, wherein The apparatus further comprises: A third processing module configured to obtain target configuration information, the target configuration information being used to determine a related parameter of the first model. The apparatus of any one of claims 23 to 25, wherein The first processing module is specifically configured to at least one of: In a case where a first indication is received, predict the target information based on the first model, the first indication being used to indicate that the first device triggers prediction of the first model; In a case where a preset condition is met, predict the target information based on the first model; The preset condition comprises at least one of: A cell reselection related condition; A state related condition of the first device. The apparatus of claim 26, wherein Further comprising: A sending module configured to send a third signal, the third signal being used to indicate at least one of: A target measurement value, the target measurement value being a measurement value corresponding to triggering prediction of the first model; A physical layer cell index or a physical layer cell group index predicted by the first model; A serving cell index or a serving cell group index predicted by the first model; A transmission parameter of the first signal predicted by the first model. A communication 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 transmission control method according to any one of claims 1 to 19. 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 transmission control method according to any one of claims 1 to 19. A computer program product comprising computer instructions, the computer instructions being executed by a processor to implement the steps of the transmission control method according to any one of claims 1 to 19.

Images