Transmission control method and device, first equipment and second equipment

Abstract

The invention discloses a transmission control method and device, first equipment and second equipment, and belongs to the technical field of communication, and the transmission control method comprises the steps that the first equipment determines a target result based on a target AI model; the target AI model comprises a first AI model or a second AI model, and the target result comprises a first result determined based on the first AI model or a second result determined based on the second AI model; the first result is used for indicating at least one of the following items; activating or inactivating the first transmission; sending an activation signal or not sending the activation signal; the number of first transmissions to be activated; a range of first transmission to be activated; the second result is used for indicating at least one of the following items: deactivating or not deactivating the first transmission; sending a deactivation signal or not sending the deactivation signal; the number of first transmissions to be deactivated; the range of the first transmission to be deactivated.

Description

Technical Field

[0001] This application belongs to the field of communication technology, and specifically relates to a transmission control method, apparatus, first device and second device. Background Technology

[0002] To control the complexity of transmissions (e.g., downlink transmissions) and reduce power consumption, some transmissions can be configured to be activated or deactivated as needed; these transmissions can also be called flexible transmissions or on-demand transmissions. However, in related technologies, there is no corresponding solution for how to control the activation or deactivation of these transmissions, resulting in poor accuracy in activating or deactivating them. Summary of the Invention

[0003] This application provides a transmission control method, apparatus, first device, and second device, which can improve the accuracy of activation or deactivation control such as flexible transmission or on-demand transmission.

[0004] Firstly, a transmission control method is provided, the method comprising:

[0005] The first device determines the target result based on the target artificial intelligence (AI) model.

[0006] The target AI model includes a first AI model or a second AI model, and the target result includes a first result determined based on the first AI model or a second result determined based on the second AI model.

[0007] The first result is used to indicate at least one of the following;

[0008] Activate or deactivate the first transmission;

[0009] Sending an activation signal or not sending an activation signal, the activation signal being used to activate or request activation of the first transmission;

[0010] The number of first transmissions that need to be activated;

[0011] The range of the first transmission to be activated;

[0012] The second result is used to indicate at least one of the following:

[0013] Deactivate or deactivate the first transmission;

[0014] Send a deactivation signal or not send a deactivation signal, the deactivation signal being used to deactivate or request deactivation of the first transmission;

[0015] The number of first transfers that need to be deactivated;

[0016] The range of the first transmission that needs to be deactivated.

[0017] Secondly, a transmission control device is provided, the device comprising:

[0018] The processing module is used to determine the target result based on the target artificial intelligence (AI) model.

[0019] The target AI model includes a first AI model or a second AI model, and the target result includes a first result determined based on the first AI model or a second result determined based on the second AI model.

[0020] The first result is used to indicate at least one of the following;

[0021] Activate or deactivate the first transmission;

[0022] Sending an activation signal or not sending an activation signal, the activation signal being used to activate or request activation of the first transmission;

[0023] The number of first transmissions that need to be activated;

[0024] The range of the first transmission to be activated;

[0025] The second result is used to indicate at least one of the following:

[0026] Deactivate or deactivate the first transmission;

[0027] Send a deactivation signal or not send a deactivation signal, the deactivation signal being used to deactivate or request deactivation of the first transmission;

[0028] The number of first transfers that need to be deactivated;

[0029] The range of the first transmission that needs to be deactivated.

[0030] Thirdly, a transmission control method is provided, the method comprising:

[0031] The second device performs a second operation, the second operation including at least one of the following:

[0032] At least a portion of the AI ​​model in the training target AI model;

[0033] Send at least a portion of the AI ​​model from the target AI model to the first device;

[0034] Send first input information to the first device, the first input information being used for prediction by the target AI model;

[0035] Send second input information to the first device, the second input information being used for training the target AI model;

[0036] Receive third input information from the first device, the third input information being used for training the target AI model;

[0037] Receive the target result sent by the first device, wherein the target result is the result determined according to the target AI model;

[0038] Receive the supervision results of the target AI model sent by the first device, or send the supervision results of the target AI model to the first device;

[0039] The target AI model is subjected to model supervision to obtain the supervision results of the target AI model;

[0040] Send an eleventh instruction message to the first device, the eleventh instruction message being used to trigger the first device to train the target AI model;

[0041] Send a twelfth instruction message to the first device, the twelfth instruction message being used to trigger the first device to make a prediction based on the target AI model;

[0042] The target AI model includes either a first AI model or a second AI model;

[0043] The first AI model is used to predict at least one of the following:

[0044] Activate or deactivate the target transfer;

[0045] Sending an activation signal or not sending an activation signal, the activation signal being used to activate or request activation of the target transmission;

[0046] The number of target transmissions that need to be activated;

[0047] The range of target transmissions that need to be activated;

[0048] The second AI model is used to predict at least one of the following;

[0049] Deactivate or deactivate the target transfer;

[0050] Send a deactivation signal or not send a deactivation signal, wherein the deactivation signal is used to deactivate or request deactivation of the target transmission;

[0051] The number of target transfers that need to be deactivated;

[0052] The range of the target transmission that needs to be deactivated.

[0053] Fourthly, a transmission control device is provided, the device comprising:

[0054] A processing module is configured to perform a second operation, the second operation including at least one of the following:

[0055] At least a portion of the AI ​​model in the training target AI model;

[0056] Send at least a portion of the AI ​​model from the target AI model to the first device;

[0057] Send first input information to the first device, the first input information being used for prediction by the target AI model;

[0058] Send second input information to the first device, the second input information being used for training the target AI model;

[0059] Receive third input information from the first device, the third input information being used for training the target AI model;

[0060] Receive the target result sent by the first device, wherein the target result is the result determined according to the target AI model;

[0061] Receive the supervision results of the target AI model sent by the first device, or send the supervision results of the target AI model to the first device;

[0062] The target AI model is subjected to model supervision to obtain the supervision results of the target AI model;

[0063] Send an eleventh instruction message to the first device, the eleventh instruction message being used to trigger the first device to train the target AI model;

[0064] Send a twelfth instruction message to the first device, the twelfth instruction message being used to trigger the first device to make a prediction based on the target AI model;

[0065] The target AI model includes either a first AI model or a second AI model;

[0066] The first AI model is used to predict at least one of the following:

[0067] Activate or deactivate the target transfer;

[0068] Sending an activation signal or not sending an activation signal, the activation signal being used to activate or request activation of the target transmission;

[0069] The number of target transmissions that need to be activated;

[0070] The range of target transmissions that need to be activated;

[0071] The second AI model is used to predict at least one of the following;

[0072] Deactivate or deactivate the target transfer;

[0073] Send a deactivation signal or not send a deactivation signal, wherein the deactivation signal is used to deactivate or request deactivation of the target transmission;

[0074] The number of target transfers that need to be deactivated;

[0075] The range of the target transmission that needs to be deactivated.

[0076] Fifthly, a transmission control apparatus is provided, the apparatus being configured to perform the steps of the method described in the first aspect, or to implement the steps of the method described in the third aspect.

[0077] In a sixth aspect, a first device is provided, the first device including a processor and a memory, the memory storing a program or instructions executable on the processor, the program or instructions, when executed by the processor, implementing the steps of the method as described in the first aspect.

[0078] In a seventh aspect, a first device is provided, including a processor and a communication interface, wherein the processor is used to determine a target result based on a target artificial intelligence (AI) model;

[0079] The target AI model includes a first AI model or a second AI model, and the target result includes a first result determined based on the first AI model or a second result determined based on the second AI model.

[0080] The first result is used to indicate at least one of the following;

[0081] Activate or deactivate the first transmission;

[0082] Sending an activation signal or not sending an activation signal, the activation signal being used to activate or request activation of the first transmission;

[0083] The number of first transmissions that need to be activated;

[0084] The range of the first transmission to be activated;

[0085] The second result is used to indicate at least one of the following:

[0086] Deactivate or deactivate the first transmission;

[0087] Send a deactivation signal or not send a deactivation signal, the deactivation signal being used to deactivate or request deactivation of the first transmission;

[0088] The number of first transfers that need to be deactivated;

[0089] The range of the first transmission that needs to be deactivated.

[0090] In an eighth aspect, a second device is provided, the second device including a processor and a memory, the memory storing a program or instructions executable on the processor, the program or instructions, when executed by the processor, implementing the steps of the method as described in the third aspect.

[0091] A ninth aspect provides a second device, including a processor and a communication interface, wherein the processor is configured to perform a second operation, the second operation including at least one of the following:

[0092] At least a portion of the AI ​​model in the training target AI model;

[0093] Send at least a portion of the AI ​​model from the target AI model to the first device;

[0094] Send first input information to the first device, the first input information being used for prediction by the target AI model;

[0095] Send second input information to the first device, the second input information being used for training the target AI model;

[0096] Receive third input information from the first device, the third input information being used for training the target AI model;

[0097] Receive the target result sent by the first device, wherein the target result is the result determined according to the target AI model;

[0098] Receive the supervision results of the target AI model sent by the first device, or send the supervision results of the target AI model to the first device;

[0099] The target AI model is subjected to model supervision to obtain the supervision results of the target AI model;

[0100] Send an eleventh instruction message to the first device, the eleventh instruction message being used to trigger the first device to train the target AI model;

[0101] Send a twelfth instruction message to the first device, the twelfth instruction message being used to trigger the first device to make a prediction based on the target AI model;

[0102] The target AI model includes either a first AI model or a second AI model;

[0103] The first AI model is used to predict at least one of the following:

[0104] Activate or deactivate the target transfer;

[0105] Sending an activation signal or not sending an activation signal, the activation signal being used to activate or request activation of the target transmission;

[0106] The number of target transmissions that need to be activated;

[0107] The range of target transmissions that need to be activated;

[0108] The second AI model is used to predict at least one of the following;

[0109] Deactivate or deactivate the target transfer;

[0110] Send a deactivation signal or not send a deactivation signal, wherein the deactivation signal is used to deactivate or request deactivation of the target transmission;

[0111] The number of target transfers that need to be deactivated;

[0112] The range of the target transmission that needs to be deactivated.

[0113] In a tenth aspect, a readable storage medium is provided, on which a program or instructions are stored, which, when executed by a processor, implement the steps of the method described in the first aspect, or implement the steps of the method described in the third aspect.

[0114] Eleventhly, a wireless communication system is provided, comprising: a first device and a second device, wherein the first device is configured to perform the steps of the transmission control method as described in the first aspect, and the second device is configured to perform the steps of the transmission control method as described in the third aspect.

[0115] In a twelfth aspect, a chip is provided, the chip including a processor and a communication interface coupled to the processor, the processor being configured to run a program or instructions to implement the steps of the method described in the first aspect, or to implement the steps of the method described in the third aspect.

[0116] In a thirteenth aspect, a computer program / program product is provided, which is stored in a storage medium and is executed by at least one processor to implement the steps of the method as described in the first aspect, or to implement the steps of the method as described in the third aspect.

[0117] In this embodiment, the first device determines a target result based on a target AI model; wherein the target AI model includes a first AI model or a second AI model, and the target result includes a first result determined based on the first AI model or a second result determined based on the second AI model; the first result is used to indicate at least one of the following: activating or deactivating a first transmission; sending an activation signal or not sending an activation signal, the activation signal being used to activate or request activation of the first transmission; the number of first transmissions to be activated; the range of first transmissions to be activated; the second result is used to indicate at least one of the following: deactivating or deactivating a first transmission; sending a deactivation signal or not sending a deactivation signal, the deactivation signal being used to deactivate or request deactivation of the first transmission; the number of first transmissions to be deactivated; the range of first transmissions to be deactivated. That is, this embodiment controls the activation or deactivation of the first transmission based on an AI model. Since the AI ​​model has strong learning and computing capabilities, this helps to ensure the accuracy of the activation or deactivation control of the first transmission, thereby improving resource utilization and reducing device energy consumption. Attached Figure Description

[0118] Figure 1 This is a block diagram of a wireless communication system applicable to embodiments of this application;

[0119] Figure 2a This is one of the schematic diagrams illustrating the association between RO and SSB provided in the embodiments of this application;

[0120] Figure 2b This is the second schematic diagram illustrating the association between RO and SSB provided in the embodiments of this application;

[0121] Figure 3a This is a schematic diagram of the neural network provided in an embodiment of this application;

[0122] Figure 3b This is a schematic diagram of a neuron provided in an embodiment of this application;

[0123] Figure 4 This is a schematic diagram of the AI ​​lifecycle management framework provided in the embodiments of this application;

[0124] Figure 5 This is a flowchart of a transmission control method provided in an embodiment of this application;

[0125] Figure 6 This is a flowchart of another transmission control method provided in an embodiment of this application;

[0126] Figure 7 This is a structural diagram of a transmission control device provided in an embodiment of this application;

[0127] Figure 8This is a structural diagram of another transmission control device provided in an embodiment of this application;

[0128] Figure 9 This is a structural diagram of the communication device provided in the embodiments of this application;

[0129] Figure 10 This is a structural diagram of the terminal provided in the embodiments of this application;

[0130] Figure 11 This is a structural diagram of the network-side device provided in the embodiments of this application. Detailed Implementation

[0131] The technical solutions of the embodiments of this application will be clearly described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application are within the scope of protection of this application.

[0132] 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.

[0133] 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.

[0134] It is worth noting that the technologies described in this application are not limited to Long Term Evolution (LTE) / LTE-Advanced (LTE-A) systems, but can also be used in other wireless communication systems, such as Code Division Multiple Access (CDMA), Time Division Multiple Access (TDMA), Frequency Division Multiple Access (FDMA), Orthogonal Frequency Division Multiple Access (OFDMA), Single-carrier Frequency-Division Multiple Access (SC-FDMA), or other systems. The terms "system" and "network" in this application are often used interchangeably, and the described technologies can be used with the systems and radio technologies mentioned above, as well as with other systems and radio technologies. The following description describes New Radio (NR) systems for illustrative purposes, and the term NR is used in most of the following description; however, these technologies can also be applied to systems other than NR systems, such as 6th generation (6G) radio systems. th Generation 6G communication system.

[0135] Figure 1This diagram illustrates a block diagram of a wireless communication system applicable to embodiments of this application. The wireless communication system includes a terminal 11 and a network-side device 12. The terminal 11 can be a mobile phone, tablet computer, laptop computer, notebook computer, personal digital assistant (PDA), handheld computer, netbook, ultra-mobile personal computer (UMPC), mobile internet device (MID), augmented reality (AR), virtual reality (VR) device, robot, wearable device, flight vehicle, vehicle user equipment (VUE), shipboard equipment, pedestrian user equipment (PUE), smart home devices (home appliances with wireless communication capabilities, such as refrigerators, televisions, washing machines, or furniture), game consoles, personal computers (PCs), ATMs, or self-service machines, etc. Wearable devices include: smartwatches, smart bracelets, smart headphones, smart glasses, smart jewelry (smart bracelets, smart chains, smart rings, smart necklaces, smart anklets, smart anklets, etc.), smart wristbands, smart clothing, etc. Among these, in-vehicle devices can also be referred to as in-vehicle terminals, in-vehicle controllers, in-vehicle modules, in-vehicle components, in-vehicle chips, or in-vehicle units, etc. It should be noted that the specific type of terminal 11 is not limited in this application embodiment. Network-side equipment 12 may include access network equipment or core network equipment, wherein access network equipment may also be referred to as Radio Access Network (RAN) equipment, radio access network function, or radio access network unit. Access network equipment may include base stations, Wireless Local Area Network (WLAN) access points (AS), or Wireless Fidelity (WiFi) nodes, etc.The term "base station" can be referred to as Node B (NB), Evolved Node B (eNB), Next Generation Node B (gNB), New Radio Node B (NR Node B), Access Point, Relay Base Station (RBS), Serving Base Station (SBS), Base Transceiver Station (BTS), Radio Base Station, Radio Transceiver, Basic Service Set (BSS), Extended Service Set (ESS), Home Node B (HNB), Home Evolved Node B, Transmit / Receive Point (TRP), or any other suitable term in the relevant field, as long as the same technical effect is achieved. The term "base station" is not limited to any specific technical terminology. It should be noted that this application embodiment only uses a base station in an NR system as an example for description and does not limit the specific type of base station.

[0136] Core network equipment, also known as core network nodes, core network functions, or core network elements, includes, but is not limited to, at least one of the following: Mobility Management Entity (MME), Access and Mobility Management Function (AMF), Session Management Function (SMF), User Plane Function (UPF), Policy Control Function (PCF), Policy and Charging Rules Function (PCRF), Edge Application Server Discovery Function (EASDF), Unified Data Management (UDM), Unified Data Repository (UDR), Home Subscriber Server (HSS), Centralized network configuration (CNC), Network Repository Function (NRF), Network Exposure Function (NEF), Local NEF (or L-NEF), and Binding Support Function. Support Functions (BSF), Application Functions (AF), Location Management Functions (LMF), Gateway Mobile Location Centres (GMLC), and Network Data Analytics Functions (NWDAF), etc. It should be noted that this application embodiment only uses core network equipment in the NR system as an example and does not limit the specific type of core network equipment. If the name of the core network equipment mentioned in this application embodiment changes in subsequent protocol versions (e.g., 6G), it will still be within the scope of protection of this application.

[0137] Optionally, the core network equipment can be implemented by one or more functional modules in a single device, or by multiple devices working together; this application does not specifically limit this. It is understood that the aforementioned functional modules can be network elements in hardware devices, software functional modules running on dedicated hardware, or virtualized functional modules instantiated on a platform (e.g., a cloud platform).

[0138] For ease of understanding, the following describes some aspects of the embodiments of this application:

[0139] I. Synchronous Signal Block (SSB) Transmission Method in 5G NR

[0140] For a primary cell (PCell) or a primary secondary cell (PScell), the base station must send periodic SSBs, and the SSB period must be less than or equal to 20ms for the initial search terminal to be able to successfully search for it.

[0141] For intra-band secondary cells (SCells), the base station can transmit SSBs, in which case the SSB-related parameters are configured when adding the Scell; alternatively, it can not transmit SSBs, in which case the SSB-related parameters are not configured when adding the Scell, and the terminal obtains the timing through the SSB on the Pcell.

[0142] For inter-band Scells, the base station must send an SSB and configure the relevant SSB parameters when adding the Scell.

[0143] II. Mapping Rules from SSB to Physical Random Access Opportunity (PRACH Occasion, RO) in 5G NR

[0144] The configuration parameters for PRACH resources and SSB-ROs are configured in System Information Block (SIB) 1 (i.e., SIB1). In NR, a cell can configure multiple Frequency Division Multiplexing (FDM) PRACH transmission opportunities (ROs) at a time-domain location of a Physical Random Access Channel (PRACH). At any given time, the number of ROs that can perform FDM can be {1, 2, 4, 8}, which is determined by the higher-layer parameter msg1-FDM.

[0145] The random access preamble can only be transmitted on the time-domain resources configured by the parameter PRACHConfigurationIndex and the frequency-domain resources configured by the parameter msg1-FDM. PRACH frequency-domain resources n RA ∈{0,1,…,M-1}, where M equals the higher-layer parameter msg1-FDM. At initial access, the PRACH frequency domain resource n RA Starting with the lowest frequency RO resource within the initial active uplink bandwidth part, number them in ascending order; otherwise, use the PRACH frequency domain resource n. RA Number the resources in ascending order, starting with the lowest frequency RO resource within the active uplink bandwidth part. For example, in... Figure 2a In this context, the number of ROs in FDM at a given time is 8 (msg1-FDM=8). The RO resources are numbered sequentially from low to high frequency as RO#0~RO#7.

[0146] In NR, there is an association between ROs and the actual transmitted synchronization signals / physical broadcast channel blocks (SS / PBCH blocks). ROs are associated with SSBs in a frequency domain (from low to high frequency) followed by a time domain. An SSB may be associated with multiple consecutive ROs, or multiple SSBs may be associated with one RO. In this case, different SSBs correspond to different preambles, which are configured by the network through the parameter ssb-perRACH-OccasionAndCB-PreamblesPerSSB. In the parameter ssb-perRACH-OccasionAndCB-PreamblesPerSSB, oneEighth represents one SSB associated with 8 consecutive ROs, and eight represents 8 SSBs associated with one RO; {n4, n8, n12, ...} represents the number of preambles associated with each SSB on a RO. For example, n4 represents the number of preambles associated with each SSB on a RO, and n8 represents the number of preambles associated with each SSB on a RO.

[0147] After all SSBs have completed one round of association with RO, they constitute an SSB-RO mapping cycle. An SSB-RO association period may contain one or more SSB-RO mapping cycles. An SSB-RO association pattern period may contain one or more SSB-RO association periods. The SSB-RO mapping repeats with the association pattern period as the cycle, and the maximum association pattern period is 160ms.

[0148] Typically, base stations can use different beams to transmit different SSBs. The number of SSBs is configured via the `ssb-PositionsInBurst` parameter; for Frequency Range (FR) 2, the maximum number of SSBs is 64. The UE selects the RO / "RO and preamble combination" associated with the SSB with the strongest signal based on the strength of the received downlink beam / SSB, and then transmits `Msg1`. In this way, the network can determine the SSB selected by the UE based on the received preamble's RO / "RO and preamble combination" and transmit `Msg2` on the corresponding downlink beam to ensure the quality of downlink signal reception.

[0149] by Figure 2a For example, at any given time, there are 8 ROs in the FDM, and 4 SSBs are actually transmitted, namely SSB#0, SSB#1, SSB#2, and SSB#3. Each SSB is associated with 2 ROs. If the UE determines to send PRACH / Msg1 on the RO corresponding to SSB#0, then the UE selects one RO from RO#0 and RO#1 to send the PRACH.

[0150] by Figure 2b For example, at a given moment, the number of ROs in an FDM is 2, and the actual number of SSBs transmitted is 8, namely SSB#0, SSB#1, ..., SSB#7, with each pair of SSBs associated with one RO. When multiple SSBs share a single RO, the Preamble sets associated with these multiple SSBs are different; that is, the same Preamble cannot simultaneously belong to different Preamble sets associated with different SSBs. Figure 2b Taking RO#0 as an example, RO#0 has a total of 60 preambles, of which the preambles with indices 0 to 29 are associated with SSB#0, and the preambles with indices 30 to 59 are associated with SSB#1.

[0151] Before sending PRACH, the UE first selects an SSB with an RSRP higher than a threshold based on the RSRP of the received beam (e.g., SSB). If multiple SSBs have RSRPs higher than the threshold, the terminal can select any SSB with an RSRP higher than the threshold. If there is no SSB with an RSRP higher than the threshold, the UE selects an SSB based on the implementation.

[0152] Based on the network (NW) configuration, the UE obtains the mapping between SSBs and ROs. After selecting an SSB, the RO corresponding to the selected SSB is used as the RO for transmitting PRACH / preamble / Msg1. If the selected SSB is associated with multiple ROs, the terminal can choose one of the ROs to transmit PRACH / preamble / Msg1.

[0153] For example, Figure 2a In the example shown, assuming the UE selects SSB#1, the UE can choose between RO#2 and RO#3 to send PRACH / Msg1; Figure 2b In the example shown, if the UE selects SSB#1, the UE can choose the nearest available RO (RO#0 or 4) associated with SSB#1 to transmit PRACH / Msg1. Within the selected RO, the UE selects a preamble from the preamble set associated with the selected SSB for PRACH transmission. Figure 2b As shown, if an RO is associated with two SSBs, then the available preamble set associated with each SSB in an RO will be divided into two subsets, each corresponding to one SSB. The UE will select a preamble sequence from the preamble subset corresponding to the selected SSB for PRACH / Msg1 transmission.

[0154] III. Artificial Intelligence (AI) / Machine Learning (ML)

[0155] Artificial intelligence (AI) has been widely applied in various fields. Integrating AI into wireless communication networks to significantly improve technical indicators such as throughput, latency, and user capacity is an important task for future wireless communication networks. AI modules can be implemented in various ways, such as neural networks, decision trees, support vector machines, and Bayesian classifiers. This application uses neural networks as an example for illustration, but it does not limit the specific type of AI module.

[0156] For example, a neural network can be as follows Figure 3a As shown, a neural network is composed of neurons, and each neuron can... Figure 3b As shown in the diagram. Here, a1, a2, ..., aK are the inputs, w is the weight (multiplicative coefficient), b is the bias (additive coefficient), and σ(.) is the activation function. Common activation functions include Sigmoid, tanh, and the Rectified Linear Unit (ReLU), etc.

[0157] The parameters of a neural network are optimized using gradient optimization algorithms. Gradient optimization algorithms are a class of algorithms that minimize or maximize an objective function (also known as 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 obtain the predicted output f(x) based on the input x, and calculate the difference between the predicted value and the true value (f(x) - Y), which is the loss function. The goal is to find suitable W and b that minimize the value of the above loss function, where a smaller loss value indicates that the model is closer to the reality.

[0158] Most common optimization algorithms are based on the error back propagation (BP) algorithm. The basic idea of ​​the BP algorithm is that the learning process consists of two parts: forward propagation of the signal and backward propagation of the error. During forward propagation, the input sample is introduced from the input layer, processed layer by layer by the hidden layers, and then propagated to the output layer. If the actual output of the output layer does not match the expected output, the process transitions to the error back propagation stage. Error back propagation involves propagating the output error back to the input layer layer by layer through the hidden layers, distributing the error to all units in each layer, thus obtaining the error signal of each unit. This error signal serves as the basis for adjusting the weights of each unit. This process of adjusting the weights through forward and backward propagation is repeated continuously. This continuous adjustment of weights is the learning and training process of the network. This process continues until the error of the network output is reduced to an acceptable level, or until the predetermined number of learning iterations is reached.

[0159] Common optimization algorithms include gradient descent, stochastic gradient descent (SGD), mini-batch gradient descent, momentum method, Nesterov (named after the inventor, specifically stochastic gradient descent with momentum), adaptive gradient descent (Adagrad), Adadelta, root mean square propagation (RMSprop), and adaptive momentum estimation (Adam).

[0160] During error backpropagation, these optimization algorithms calculate the gradient based on the error / loss obtained from the loss function with respect to the current neuron, add the learning rate, previous gradients / derivatives / partial derivatives, etc., and then pass the gradient to the previous layer.

[0161] Generally, the AI ​​algorithms and models selected vary depending on the type of problem being solved. The main method for improving 5G network performance using AI is to enhance or replace existing algorithms or processing modules with neural network-based algorithms and AI models. In specific scenarios, neural network-based algorithms and AI models can achieve better performance than deterministic algorithms. Commonly used neural networks include deep neural networks, convolutional neural networks, and recurrent neural networks. Existing AI tools can be used to build, train, and validate neural networks.

[0162] IV. Fine-tuning

[0163] In practice, due to the insufficient size of real-time acquired datasets, directly training a neural network often fails to achieve convergence. A common approach is to pre-train the network using a large amount of offline collected data until it converges. Then, the parameters of the pre-trained neural network are fine-tuned using real-time acquired data to adapt the network to the real-world environment. Fine-tuning can be considered a training process that uses the parameters of the pre-trained neural network as initialization. During the fine-tuning phase, the parameters of some layers can be frozen; generally, layers closer to the input are frozen, while layers closer to the output are activated. This ensures that the network can still converge. The smaller the amount of data during the fine-tuning phase, the more layers should be frozen, with only a small number of layers near the output being fine-tuned.

[0164] V. Generalization of Neural Networks

[0165] Generalization refers to the ability of a neural network to produce reasonable outputs on data not encountered during its training or learning process. To address the generalization problem caused by the variable wireless transmission environment, neural network-based wireless communication systems offer two solutions. The first is to train different neural networks under different transmission conditions, obtaining multiple sets of network parameters, and then switching these parameters as the actual environment changes. The second is to train a common neural network based on mixed data, where the network parameters do not change with the environment. Each approach has its advantages and disadvantages: the first approach performs excellently under different transmission conditions, but requires storing multiple network parameters and switching them as needed, which incurs signaling overhead and frequent switching issues; the second approach only requires storing one set of neural network parameters without switching, but it cannot achieve optimal performance under every transmission condition. The construction method of the mixed dataset affects the performance of the second approach.

[0166] VI. Labels

[0167] In machine learning and deep learning, labels typically refer to the identifiers or annotations of the true category or target value of a data sample. Labels are used to represent the information that the model should learn and predict. The following examples illustrate this:

[0168] Labels in classification tasks: In classification tasks, labels indicate which category a data sample belongs to. For example, in image classification, each image sample has a label that indicates the category of the object or scene contained in the image, such as "dog" or "cat".

[0169] Labels in object detection: In object detection tasks, labels typically include the object's location information (e.g., the object's bounding box) and category information. Each label identifies a target object in an image, including its location and category. Labels in regression tasks:

[0170] In regression tasks, labels typically represent the continuous or real-valued objective to be predicted. For example, in a house price prediction task, the label could be the actual selling price of a house.

[0171] Labels in sequence labeling: In natural language processing, labels in sequence labeling tasks are often used for tasks such as part-of-speech tagging and named entity recognition. Labels are used to represent the attributes or categories of each word or character in a text sequence.

[0172] Labels are a crucial component in supervised learning tasks, used to train machine learning models. Models learn patterns and regularities by comparing themselves to true labels in order to make predictions or classifications on unseen data. The quality and accuracy of the labels are critical to the model's performance.

[0173] VII. AI Life Cycle Management (LCM)

[0174] AI / ML model lifecycle management includes multiple AI functional modules: model training, model deployment, model inference, model monitoring, and model updates. For example, a specific framework for AI lifecycle management can be as follows: Figure 4 As shown.

[0175] (1) Model training

[0176] This function performs AI model training, validation, and testing, generating model performance metrics that can be used as part of the model testing process. If needed, it also handles data preparation based on the training data provided by the data collection function, such as data preprocessing and cleaning, formatting, and transformation.

[0177] Training / Update Model: If a model storage function is available, it is used to transfer trained, validated, and tested AI models to the model storage function, or to transfer updated versions of the model to the model storage function.

[0178] (2) Model Management

[0179] This module monitors the operation of AI models or the deployment of AI functions, such as model selection / activation / deactivation / switching / rollback, and provides feedback on model monitoring performance. It is also responsible for making decisions based on data received from the data collection and inference modules to ensure correct inference operations.

[0180] Management instructions: Information used by the model management function to input to the model inference function. This information may include selecting / deactivating / activating / switching models or reverting to non-AI / ML operations (i.e., operations independent of the inference process) using AI models or AI / ML-based functions.

[0181] Model transfer request: Used to request a model from the model storage function.

[0182] Performance Feedback / Retraining Request: Information required for model training functions to input, such as for model (re)training or updating purposes.

[0183] (3) Model reasoning

[0184] The data (i.e., inference data) provided by the data collection function is used as input to provide the output of the applied AI model. If necessary, the inference function is also responsible for data preparation based on the inference data provided by the data collection function (e.g., data preprocessing and cleaning, formatting and transformation).

[0185] Inference output: Data used by management functions to monitor the performance of AI models or AI / ML functions.

[0186] VIII. AI Model

[0187] The AI ​​model in this application embodiment can also be referred to as an AI unit, machine learning (ML) model, ML unit, AI structure, AI function, AI characteristic, machine learning model, neural network, neural network function, neural network functionality, etc. Alternatively, the aforementioned AI unit can refer to a processing unit capable of implementing specific algorithms, formulas, processing flows, capabilities, etc., related to AI. Or, the AI ​​unit can be a processing method, algorithm, function, module, or unit for a specific dataset. Alternatively, the AI ​​unit can be a processing method, algorithm, function, module, or unit running on AI / ML related hardware such as GPU, NPU, TPU, and ASIC. This application embodiment does not specifically limit this. Optionally, the specific dataset includes at least one of the input and output of the AI ​​unit.

[0188] Optionally, the identifier (i.e., ID) of the AI ​​model may be an AI model identifier, an AI structure identifier, an AI algorithm identifier, or an identifier of a specific dataset associated with the AI ​​unit, or an identifier of a specific scenario, environment, channel characteristics, or device related to the AI / ML, or an identifier of a function, feature, capability, or module related to the AI / ML. This application embodiment does not specifically limit this.

[0189] Optionally, the index of the AI ​​model can be described in various ways, such as functionalityID and / or model ID, physical model ID, logical model ID, global model ID, or local model ID.

[0190] It should also be noted that AI in the embodiments of this application can also be represented as machine learning, which has a variety of implementation methods, such as neural networks, decision trees, support vector machines, Bayesian classifiers, etc. The embodiments of this application do not make specific limitations on this.

[0191] The transmission control method provided in this application will be described in detail below with reference to the accompanying drawings and through some embodiments and application scenarios.

[0192] Please see Figure 5 , Figure 5 This is a flowchart of a transmission control method provided in an embodiment of this application. This method can be executed by a first device, such as... Figure 5 As shown, it includes the following steps:

[0193] Step 501: The first device determines the target result based on the target AI model;

[0194] The target AI model includes a first AI model or a second AI model, and the target result includes a first result determined based on the first AI model or a second result determined based on the second AI model.

[0195] The first result is used to indicate at least one of the following;

[0196] Activate or deactivate the first transmission;

[0197] Sending an activation signal or not sending an activation signal, the activation signal being used to activate or request activation of the first transmission;

[0198] The number of first transmissions that need to be activated;

[0199] The range of the first transmission to be activated;

[0200] The second result is used to indicate at least one of the following:

[0201] Deactivate or deactivate the first transmission;

[0202] Send a deactivation signal or not send a deactivation signal, the deactivation signal being used to deactivate or request deactivation of the first transmission;

[0203] The number of first transfers that need to be deactivated;

[0204] The range of the first transmission that needs to be deactivated.

[0205] In this embodiment, the first device can be a terminal, a network-side device, or a server, etc. For example, the terminal can be, but is not limited to, the type of terminal 11 listed above; the network-side device can be, but is not limited to, the type of network-side device 12 listed above; the server can be a device used for training or predicting or providing AI-related information, or it can be a third server, or it can be a device provided by an over-the-top (OTT) service provider, a third-party service provider, or the Internet, etc. This application embodiment does not specifically limit this.

[0206] The aforementioned first transmission can be a flexible transmission or an on-demand transmission. This flexible or on-demand transmission can also be referred to as a transmission that needs to be activated or deactivated, or a transmission with a switch, etc.

[0207] For example, the first transmission described above may include, but is not limited to, at least one of the following: a first signal transmitted on demand, a first channel transmitted on demand, and a first resource transmitted on demand. The first signal may include, but is not limited to, at least one of on-demand synchronization signals, on-demand reference signals, on-demand broadcast signals, and on-demand control signals. For example, the on-demand synchronization signal may include on-demand SSB, and the on-demand reference signal may include, but is not limited to, at least one of on-demand Sounding Reference Signal (SRS), on-demand Channel State Information Reference Signal (CSI-RS), and on-demand Tracking Reference Signal (TRS). The first channel may include, but is not limited to, at least one of on-demand Physical Broadcast Channel (PBCH), on-demand Physical Random Access Channel (PRACH), on-demand MsgA Physical Uplink Sharing Channel (PUSCH), on-demand Configured Grant (CG) PUSCH, and on-demand control channel. The aforementioned first resource may include, but is not limited to, at least one of on-demand synchronization signal resources, on-demand reference signal resources, on-demand broadcast signal resources, and on-demand control signal resources. The aforementioned resources may include, at least one of time-frequency resources, demodulation reference signal (DMRS) resources, and sequences for on-demand signal transmission. The sequences for on-demand signal transmission may include, but are not limited to, at least one of joining sequences, code division multiplexing sequences, and DMRS sequences. For ease of description, this application embodiment uses on-demand SSB as an example for the first transmission.

[0208] The aforementioned target AI model may include a first AI model or a second AI model. The first AI module is used for activation control of the first transmission, and the second AI model is used for deactivation control of the first transmission. The aforementioned first result may be the result obtained by the first device through reasoning, prediction, or processing based on the first AI model, and the aforementioned second result may be the reasoning result obtained by the first device through reasoning, prediction, or processing based on the second AI model.

[0209] Activating the first transmission as described above can be understood as allowing the sending of the first transmission. Taking the first transmission as an on-demand SSB as an example, activating the on-demand SSB can be understood as allowing the network-side device to send an on-demand SSB on the corresponding on-demand SSB resource.

[0210] The above-mentioned deactivation of the first transmission can be understood as disallowing the sending of the first transmission. Taking the first transmission as ondemand SSB as an example, the above-mentioned deactivation of ondemand SSB can be understood as disallowing network-side devices from sending ondemand SSB on the corresponding ondemand SSB resource.

[0211] It should be noted that the above-mentioned activation or deactivation of the first transmission can apply to all first transmissions or only to a portion of them. Taking the first transmission as an on-demand SSB as an example, the above-mentioned activation of the on-demand SSB can activate some SSB indices on the on-demand SSB or can activate all SSB indices on the on-demand SSB; the above-mentioned deactivation of the on-demand SSB can deactivate some SSB indices on the on-demand SSB or can deactivate all SSB indices on the on-demand SSB.

[0212] The scope of the aforementioned first transmission may include the location range of the first transmission, the index range of the first transmission, etc. The location range may include, but is not limited to, the cell range, the tracking area (TA) range, or the geographical location range. For the scope of the first transmission to be activated, it can be understood as activating the first transmission within the aforementioned location range or the first transmission within the aforementioned index range. For the scope of the first transmission to be deactivated, it can be understood as deactivating the first transmission within the aforementioned location range or the first transmission within the aforementioned index range. Taking the first transmission as an ondemand SSB as an example, the scope of the aforementioned first transmission may include the SSB index range of the on demand SSB.

[0213] The following describes this embodiment in different scenarios:

[0214] Scenario 1: The first device determines a first result based on a first AI model, and the first result is used to indicate at least one of the following:

[0215] Activate or deactivate the first transmission;

[0216] Sending an activation signal or not sending an activation signal, the activation signal being used to activate or request activation of the first transmission;

[0217] The number of first transmissions that need to be activated;

[0218] The range of the first transmission to be activated.

[0219] The following explanation uses the first transmission as an example of downlink transmission:

[0220] Scenario 1: If the first device is a terminal, the above first result is used to indicate at least one of the following: activate or deactivate the first transmission; send an activation signal or not send an activation signal, the activation signal being used to activate or request activation of the first transmission; the number of first transmissions to be activated; the range of first transmissions to be activated.

[0221] For example, if the first result is used to indicate the activation of the first transmission or the sending of an activation signal, the terminal sends an activation signal to the network-side device to activate or request the activation of the first transmission; if the first result is used to indicate the non-activation of the first transmission or the non-sending of an activation signal, the terminal may not send an activation signal to activate or request the activation of the first transmission; if the first result indicates the number of first transmissions to be activated or the range of first transmissions to be activated, the terminal may send an activation signal to the network-side device to activate or request the activation of the first transmission, and the activation signal may carry information such as the number of first transmissions to be activated or the range of first transmissions to be activated.

[0222] Scenario 2: If the first device is a network-side device, the above first result is used to indicate at least one of the following: whether to activate or not to activate the first transmission; the number of first transmissions to be activated; and the scope of the first transmissions to be activated.

[0223] For example, if the first result indicates that the first transmission should be activated, the network-side device may activate the first transmission; if the first result indicates that the first transmission should not be activated, the network-side device may not activate the first transmission; if the first result indicates the number of first transmissions to be activated or the range of first transmissions to be activated, the network-side device may activate the first transmission based on the number of first transmissions to be activated or the range of first transmissions to be activated.

[0224] Scenario 3: If the first device is a server, the server sends the first result to the terminal or network-side device. When the server sends the first result to the terminal, the first result indicates at least one of the following: activating or deactivating the first transmission; sending an activation signal or not sending an activation signal, the activation signal being used to activate or request activation of the first transmission; the number of first transmissions to be activated; and the scope of the first transmissions to be activated. When the server sends the first result to the network-side device, the first result indicates at least one of the following: activating or deactivating the first transmission; the number of first transmissions to be activated; and the scope of the first transmissions to be activated.

[0225] It should be noted that the behavior of the terminal or network device after obtaining the first result sent by the server can be referred to the relevant descriptions of Scenario 1 and Scenario 2 above, and will not be repeated here.

[0226] Scenario 2: The first device determines a second result based on a second AI model, and the second result is used to indicate at least one of the following:

[0227] Deactivate or deactivate the first transmission;

[0228] Send a deactivation signal or not send a deactivation signal, the deactivation signal being used to deactivate or request deactivation of the first transmission;

[0229] The number of first transfers that need to be deactivated;

[0230] The range of the first transmission that needs to be deactivated.

[0231] The following explanation uses the first transmission as an example of downlink transmission:

[0232] Scenario 4: If the first device is a terminal, the above second result is used to indicate at least one of the following: deactivate or not deactivate the first transmission; send a deactivation signal or not send a deactivation signal, the deactivation signal being used to deactivate or request deactivation of the first transmission; the number of first transmissions to be deactivated; the range of first transmissions to be deactivated.

[0233] For example, if the second result is used to indicate deactivation of the first transmission or to send a deactivation signal, the terminal sends a deactivation signal to the network-side device to deactivate or request deactivation of the first transmission; if the second result is used to indicate not to deactivate the first transmission or not to send a deactivation signal, the terminal may not send a deactivation signal to deactivate or request deactivation of the first transmission; if the second result indicates the number of first transmissions to be deactivated or the range of first transmissions to be deactivated, the terminal may send a deactivation signal to the network-side device to deactivate or request deactivation of the first transmission, and the deactivation signal may carry information such as the number of first transmissions to be deactivated or the range of first transmissions to be deactivated.

[0234] Scenario 5: If the first device is a network-side device, the above second result is used to indicate at least one of the following: deactivating or not deactivating the first transmission; the number of first transmissions to be deactivated; the range of first transmissions to be deactivated.

[0235] For example, if the second result indicates that the first transmission should be deactivated, the network-side device may deactivate the first transmission; if the second result indicates that the first transmission should not be deactivated, the network-side device may not deactivate the first transmission; if the second result indicates the number of first transmissions to be deactivated or the range of first transmissions to be deactivated, the network-side device may deactivate the first transmission based on the number of first transmissions to be deactivated or the range of first transmissions to be deactivated.

[0236] Scenario 6: If the first device is a server, the server sends the second result to the terminal or network-side device. When the server sends the second result to the terminal, the second result indicates at least one of the following: deactivating or not deactivating the first transmission; sending a deactivation signal or not sending a deactivation signal, the deactivation signal being used to deactivate or request deactivation of the first transmission; the number of first transmissions to be deactivated; and the range of the first transmissions to be deactivated. When the server sends the second result to the network-side device, the second result indicates at least one of the following: deactivating or not deactivating the first transmission; the number of first transmissions to be deactivated; and the range of the first transmissions to be deactivated.

[0237] It should be noted that the behavior of the terminal or network-side device after obtaining the second result sent by the server can be referred to the relevant descriptions of scenarios four and five above, and will not be repeated here.

[0238] In this embodiment, the first device determines a target result based on a target AI model; wherein the target AI model includes a first AI model or a second AI model, and the target result includes a first result determined based on the first AI model or a second result determined based on the second AI model; the first result is used to indicate at least one of the following: activating or deactivating a first transmission; sending an activation signal or not sending an activation signal, the activation signal being used to activate or request activation of the first transmission; the number of first transmissions to be activated; the range of first transmissions to be activated; the second result is used to indicate at least one of the following: deactivating or deactivating a first transmission; sending a deactivation signal or not sending a deactivation signal, the deactivation signal being used to deactivate or request deactivation of the first transmission; the number of first transmissions to be deactivated; the range of first transmissions to be deactivated. That is, this embodiment controls the activation or deactivation of the first transmission based on an AI model. Since the AI ​​model has strong learning and computing capabilities, this helps to ensure the accuracy of the activation or deactivation control of the first transmission, thereby improving resource utilization and reducing device energy consumption.

[0239] Optionally, the first device determines the target result based on the target AI model, including:

[0240] The first device determines the target result based on the first input information and the target AI model;

[0241] The first input information includes at least one of the following:

[0242] Time information;

[0243] Terminal status information;

[0244] Status information of network-side devices;

[0245] Server status information;

[0246] The signal strength and signal quality obtained by the terminal from measuring the reference signal associated with the second transmission, or the value determined based on the signal strength and signal quality obtained by the terminal from measuring the reference signal associated with the second transmission;

[0247] The value determined by the terminal based on at least one of the signal strength and signal quality measured by the second transmission, or based on at least one of the signal strength and signal quality measured by the terminal based on the second transmission;

[0248] The number of times the terminal failed to access the physical random access channel PRACH corresponding to the third transmission or the number of times it failed to receive the access response message.

[0249] The number of PRACH retransmissions performed by the terminal on the PRACH resources associated with the third transport;

[0250] The first indication information is used to indicate whether the terminal fails to access the PRACH resource associated with the third transmission after attempting two-step random access and then falling back to four-step random access.

[0251] The second indication information is used to indicate whether the power of the terminal transmitting the PRACH signal on the third transmission associated PRACH resource is greater than or equal to the first threshold.

[0252] The third indication information is used to indicate at least one of the following: whether the terminal receives a first random access response (RAR) message, the number of first RAR messages received within a first time period, and the number of first RAR messages received within the first time period being greater than or equal to a second threshold; wherein, the first RAR message is a RAR message whose included preamble identifier is not a preamble identifier sent by the terminal on the PRACH resource associated with the third transmission;

[0253] The fourth indication information is used to indicate whether the number of times the terminal sends the activation signal is less than or equal to the first number, or the fourth indication information is used to indicate whether the number of times the terminal sends the deactivation signal is less than or equal to the second number;

[0254] The fifth indication information is used to indicate whether the timing advance (TA) for activating signal transmission is effective, or the fifth indication information is used to indicate whether the TA for deactivating signal transmission is effective;

[0255] The sixth indication information is used to indicate whether the interval between the current time and the time of the previous activation signal is greater than or equal to the first interval, or the sixth indication information is used to indicate whether the interval between the current time and the time of the previous deactivation signal is greater than or equal to the second interval;

[0256] The seventh indication information is used to indicate whether the interval between the time of the previous activation or deactivation of the first transmission and the current time is greater than or equal to the third interval;

[0257] The eighth indication information is used to indicate whether the terminal has sent an activation signal for the fourth transmission, or the eighth indication information is used to indicate whether the terminal has sent a deactivation signal for the fourth transmission.

[0258] The ninth indication information is used to indicate whether the fifth transmission has been activated, or the ninth indication information is used to indicate whether the fifth transmission has been deactivated;

[0259] The tenth indication information is used to indicate whether the terminal has detected the sixth transmission;

[0260] Information on sudden events;

[0261] The frequency domain characteristics of the first transmission;

[0262] The temporal characteristics of the first transmission;

[0263] The spatial characteristics of the first transmission;

[0264] The second transmission is different from the first transmission, and the third transmission is a transmission associated with PRACH.

[0265] For example, the time information described above can be used to indicate a specific time, such as 13:25:38, or it can be used to indicate a time range, such as 13:00 to 14:00, morning or afternoon, day or night, etc.

[0266] The aforementioned time information may be timing information obtained through a first radio access technology (RAT), such as, but not limited to, Bluetooth, Wi-Fi, 3G, 4G, or 5G.

[0267] The aforementioned terminal status information can be used to reflect the relevant status of the terminal. Optionally, the terminal status information may include at least one of the following: the terminal's location information, the terminal's distribution information, the terminal's direction of movement, the terminal's speed of movement, the terminal's energy consumption status, the terminal's battery status, the terminal's network scenario information, the terminal's environmental information, and the terminal's sensing information.

[0268] The location information of the terminal mentioned above can be the terminal's geographical coordinates, such as Global Positioning System (GPS) coordinates, or the terminal's location range information, such as the street to which the terminal is located, or the terminal's location information relative to the cell it is camping in, the cell it is accessing, or a certain TRP or a group of TRPs, such as being due east of the cell it is camping in.

[0269] The distribution information of the aforementioned terminals may include the number of terminals in different areas (e.g., the stationed cell, the access cell, a certain TRP, or a group of TRPs).

[0270] The direction of movement of the aforementioned terminal can be an absolute direction, such as 40 degrees east of south; or it can be a relative direction, such as the direction relative to a certain base station.

[0271] The network scenario information of the aforementioned terminals, such as indoor hotspot (inH), urban macro (UMa) cell or rural macro (RMa) cell, or homogeneous / heterogeneous network, i.e., whether there is overlapping coverage.

[0272] The environmental information of the aforementioned terminal, such as weather information.

[0273] The aforementioned terminal's sensing information includes, for example, sensing whether there are obstacles and / or the number of obstacles under the beam corresponding to the second transmission (e.g., normal SSB), or sensing whether there are obstacles and / or the number of obstacles under the beam corresponding to the first transmission, or sensing the number of terminals covered by the beams corresponding to the first and second transmissions, etc.

[0274] The aforementioned status information of the network-side device is used to reflect the relevant status of the network-side device. Optionally, the status information of the network-side device includes at least one of the following: the energy consumption status of the network-side device, the power status of the network-side device, the environmental information of the network-side device, and the sensing information of the network-side device.

[0275] The environmental information of the aforementioned network-side equipment, such as weather information. The sensing information of the aforementioned network-side equipment, such as sensing whether there are obstacles and / or the number of obstacles under the beam corresponding to the second transmission, or sensing whether there are obstacles and / or the number of obstacles under the beam corresponding to the first transmission, or sensing the number of terminals covered by the beams corresponding to the first and second transmissions, etc.

[0276] The server status information described above is used to reflect the relevant status of the server. Optionally, the server status information includes at least one of the following: the server's environmental information, and the server's perception information.

[0277] The aforementioned server's environmental information, such as weather information. The aforementioned server's sensing information, such as sensing whether there are obstacles and / or the number of obstacles under the beam corresponding to the second transmission, or sensing whether there are obstacles and / or the number of obstacles under the beam corresponding to the first transmission, or sensing the number of terminals covered by the beams corresponding to the first and second transmissions, etc.

[0278] The second transmission described above differs from the first transmission. The second transmission can be a normal transmission, an inflexible transmission, a non-on-demand transmission, or a transmission that does not support activation or deactivation. For example, the second transmission may include at least one of a second signal, a second channel, and a second resource. The second signal may include, but is not limited to, at least one of a synchronization signal, a reference signal, a broadcast signal, and a control signal. For instance, the synchronization signal may include a normal SSB, and the reference signal may include, but is not limited to, at least one of normal SRS, normal CSI-RS, and normal TRS. The second channel may include, but is not limited to, at least one of PBCH, PRACH, CG PUSCH, MsgA PUSCH, and a control channel. The second resource may include, but is not limited to, at least one of a synchronization signal resource, a reference signal resource, a broadcast signal resource, and a control signal resource.

[0279] The reference signal associated with the second transmission mentioned above may include, but is not limited to, at least one of SSB, CSI-RS, TRS, MsgA, MsgAPUSCH, PRACH, and CG PUSCH.

[0280] The aforementioned reference signal may include a reference signal from one cell or reference signals from multiple cells. Cells may have the same frequency carrier or different frequency carriers, and may be within a band or in different bands. Different bands may be continuous or discontinuous. The association between the reference signal and the active signal or active signal resources also includes, but is not limited to, the association between SSB and active signal resources, the relationship between CSI-RS and active signal resources, the relationship between TRS and active signal resources, the association between PRACH resources and active signal resources, the association between MsgA resources and active signal resources, the association between MsgA PUSCH resources and active signal resources, and the association between CG PUSCH and active signal resources.

[0281] For example, the signal strength mentioned above may include Reference Signal Received Power (RSRP). The signal quality mentioned above may include Reference Signal Received Quality (RSRQ).

[0282] The aforementioned third transmission is a transmission associated with PRACH, and it differs from the first transmission. This third transmission can be a normal transmission, an inflexible transmission, a non-on-demand transmission, or a transmission that does not support activation or deactivation, etc.

[0283] For example, the aforementioned third transmission may include at least one of a third signal, a third channel, and a third resource. The third signal may include, but is not limited to, at least one of a synchronization signal, a reference signal, a broadcast signal, and a control signal. For instance, the synchronization signal may include a normal SSB, and the reference signal may include, but is not limited to, at least one of normal SRS, normal CSI-RS, and normal TRS. The third channel may include, but is not limited to, at least one of PBCH, PRACH, CG PUSCH, MsgA PUSCH, and a control channel. The third resource may include, but is not limited to, at least one of synchronization signal resources, reference signal resources, broadcast signal resources, and control signal resources.

[0284] At least one of the aforementioned first threshold, second threshold, first count, second count, first interval, and second interval can be a value predefined by the protocol or a configured value, for example, a value configured by the network-side device.

[0285] The first time period mentioned above can be the length of a RAR window, or multiple RAR window lengths, or a window configured for the network, or a window specified for the protocol, for example, 10ms.

[0286] The second threshold mentioned above may be configured by the network or specified by the protocol, or it may be related to the number of ROs associated with the second transmission (e.g., normal SSB) and / or the number of configured preambles. For example, the second threshold mentioned above is the floor function of the total number of preambles configured on the ROs associated with the normal SSB divided by the number of ROs associated with the normal SSB.

[0287] Optionally, the fourth transmission described above may be a transmission associated with the first transmission described above. For example, the fourth transmission may include at least one of a fourth signal transmitted on demand, a fourth channel transmitted on demand, and a fourth resource transmitted on demand. For instance, the fourth transmission may include paging, a Physical Downlink Shared Channel (PDSCH), a Physical Downlink Control Channel (PDCCH), a Positioning Reference Signal (PRS), a TRS, a PRACH, a Physical Uplink Control Channel (PUCCH), a Physical Uplink Sharing Channel (PUSCH), CSI-RS, a Phase Tracking Reference Signal (PTRS), a MsgA signal / channel, etc.

[0288] Optionally, the fifth transmission may be a transmission associated with the first transmission. For example, the fifth transmission may include at least one of a fifth signal transmitted on demand, a fifth channel transmitted on demand, and a fifth resource transmitted on demand. For instance, the fifth transmission may include at least one of paging, PDSCH, PDCCH, PRS, TRS, PRACH, PUCCH, PUSCH, CSI-RS, PTRS, MsgA signal / channel, etc.

[0289] The aforementioned fifth transmission may be a transmission associated with the aforementioned first transmission. For example, the aforementioned fifth transmission may include at least one of a fifth signal transmitted on demand, a fifth channel transmitted on demand, and a fifth resource transmitted on demand. For instance, the aforementioned fifth transmission may include at least one of paging, PDSCH, PDCCH, PRS, TRS, PRACH, PUCCH, PUSCH, CSI-RS, PTRS, MsgA signal / channel, etc.

[0290] The aforementioned sixth transmission can be a transmission associated with the aforementioned first transmission. Exemplarily, the aforementioned sixth transmission can include at least one of an on-demand sixth signal, an on-demand sixth channel, and an on-demand sixth resource. For example, the aforementioned sixth transmission can include at least one of SSB, paging, PDSCH, PDCCH, PRS, TRS, PUSCH signals / channels, etc. For example, if on-demand PDCCH is already activated, on-demand SSB may also need to be activated.

[0291] The above information on sudden events is used to indicate sudden events, such as concerts, earthquakes, etc.

[0292] For example, the frequency domain characteristics of the first transmission described above may include at least one of the following:

[0293] The potential locations of synchronization signals in the frequency range of the synchronization raster or Global Synchronization Channel Number (GSCN), for example, the frequency domain locations where synchronization signals may occur as defined in the protocol;

[0294] The number of frequency domain resource blocks (RBs) or subcarriers of the synchronization signal.

[0295] For example, the time-domain characteristics of the first transmission may include the number of time-domain symbols of the synchronization signal, or the length of the time window for time-domain correlation detection of the synchronization signal, etc.

[0296] It should be noted that, when the target AI model is the first AI model, the fourth indication information is used to indicate whether the number of times the terminal sends the activation signal is less than or equal to the first number; the fifth indication information is used to indicate whether the TA used to send the activation signal is valid; the sixth indication information is used to indicate whether the interval between the current time and the time of the previous activation signal is greater than or equal to the first interval; the seventh indication information is used to indicate whether the interval between the time of the previous activation of the first transmission and the current time is greater than or equal to the third interval; the eighth indication information is used to indicate whether the terminal has sent the activation signal of the fourth transmission; and the ninth indication information is used to indicate whether the fifth transmission has been activated. When the target AI model is the second AI model, the fourth indication information is used to indicate whether the number of times the terminal sends the deactivation signal is less than or equal to the second number; the fifth indication information is used to indicate whether the TA used to send the deactivation signal is valid; the sixth indication information is used to indicate whether the interval between the current time and the time of the previous sending of the deactivation signal is greater than or equal to the second interval; the seventh indication information is used to indicate whether the interval between the time of the previous deactivation of the first transmission and the current time is greater than or equal to the third interval; the eighth indication information is used to indicate whether the terminal has sent the deactivation signal of the fourth transmission; and the ninth indication information is used to indicate whether the fifth transmission has been deactivated.

[0297] Specifically, the first device can input the aforementioned first input information into the target AI model for reasoning, prediction, or processing to obtain the target result.

[0298] In this embodiment, the first device determines the target result based on the first input information and the target AI model, which helps to further improve the accuracy of the activation or deactivation control of the first transmission, thereby further improving resource utilization and reducing device power consumption.

[0299] In some alternative embodiments, the first device may receive at least a portion of the first input information from at least one of the second and third devices. For example, when the first device is a terminal, the terminal can obtain the status information of the network-side device from the network-side device and the status information of the server from the server; when the first device is either a network-side device or a server, the network-side device or server can obtain at least one of the following from the terminal: the terminal's status information; at least one of the signal strength and signal quality obtained by the terminal from measuring the reference signal associated with the second transmission, or a value determined based on at least one of the signal strength and signal quality obtained by the terminal from measuring the reference signal associated with the second transmission; at least one of the signal strength and signal quality measured by the terminal based on the second transmission, or a value determined based on at least one of the signal strength and signal quality measured by the terminal based on the second transmission; the number of random access failures or access response message reception failures of the terminal on the physical random access channel (PRACH) corresponding to the third transmission; the number of PRACH retransmissions performed by the terminal on the PRACH resources associated with the third transmission; first indication information; second indication information; third indication information; fourth indication information; fifth indication information; sixth indication information; seventh indication information; eighth indication information; ninth indication information; tenth indication information.

[0300] Optionally, the triggering conditions for using the first AI model to make predictions include at least one of the following:

[0301] Terminal power-on;

[0302] The terminal performs an initial cell search;

[0303] The terminal performs initial cell selection;

[0304] The time taken for the terminal to perform the initial search using the traditional method reached the first duration;

[0305] The terminal did not remain logged into the new cell during the second time period.

[0306] The terminal performs cell reselection;

[0307] The terminal performs cell handover;

[0308] The timer used to trigger the prediction timed out;

[0309] Before random access is triggered;

[0310] Before the initial access is triggered;

[0311] Beam failure detected;

[0312] Wireless link failure detected;

[0313] Based on at least one piece of information from the input information of the first AI model, it is determined that the first AI model needs to be used for prediction.

[0314] For example, the aforementioned first duration can be predefined by the protocol or configured by the network-side device.

[0315] The aforementioned new cell can be understood as any cell different from the cell the terminal previously camped on. For example, the aforementioned second time period can be a preset duration from the time the terminal attempts to camp on the new cell to the time period from the time the terminal initiates cell handover.

[0316] If at least one of the above-mentioned input information based on the first AI model determines that the first AI model needs to be used for prediction, for example, if the signal strength or signal quality obtained by the terminal measuring the reference signal associated with the second transmission (e.g., normal SSB) is less than a preset threshold, it indicates that the second transmission may be unavailable, and at this time it is necessary to predict whether the first transmission (e.g., on demand SSB) can be activated.

[0317] For example, when the first device is a terminal, if the triggering conditions for using the first AI model to make a prediction are met, the terminal uses the first AI model to make a prediction and obtains a first result. If the first device is a network-side device or a server, the terminal can send the twelfth instruction information to the network-side device or server when the triggering conditions for using the first AI model to make a prediction are met, to trigger the network-side device or server to make a prediction based on the first AI model. Accordingly, upon receiving the twelfth instruction information, the network-side device or server uses the first AI model to make a prediction and obtains a first result.

[0318] In this embodiment, when the above triggering conditions are met, the first device uses the first AI model to make a prediction to obtain a first result, and then performs activation control on the first transmission based on the first result. This can reduce some unnecessary activation of the first transmission and help to further reduce device power consumption.

[0319] Optionally, the triggering conditions for using the second AI model to make predictions include at least one of the following:

[0320] Terminal power-on;

[0321] The terminal performs an initial cell search;

[0322] The terminal performs initial cell selection;

[0323] The time taken for the terminal to perform the initial search using traditional methods exceeds the second search duration;

[0324] The terminal did not remain logged into the new cell during the third time period;

[0325] The terminal performs cell reselection;

[0326] The terminal performs cell handover;

[0327] The timer used to trigger the prediction timed out;

[0328] Before random access is triggered;

[0329] Before the initial access is triggered;

[0330] Beam failure detected;

[0331] Wireless link failure detected;

[0332] The power consumption of network-side devices exceeds the first threshold;

[0333] The terminal's energy consumption exceeds the second threshold;

[0334] The terminal's battery level is below the third threshold;

[0335] Based on at least one of the input information of the second AI model, it is determined that the second AI model needs to be used for prediction.

[0336] For example, the second duration can be predefined by the protocol or configured by the network-side device.

[0337] The aforementioned new cell can be understood as any cell different from the cell where the terminal previously camped. For example, the aforementioned third time period can be a preset time period from the time the terminal attempts to camp on the new cell to the time period from the time the terminal initiates cell handover.

[0338] For example, at least one of the first threshold, second threshold and third threshold mentioned above may be predefined by the protocol or configured by the network-side device.

[0339] At least one piece of information from the input information based on the second AI model determines that the second AI model needs to be used for prediction. For example, if the signal strength or signal quality obtained by the terminal measuring the reference signal associated with the second transmission (e.g., normal SSB) is greater than a preset threshold, it indicates that the second transmission is available. At this time, it is necessary to predict whether the first transmission (e.g., on demand SSB) can be deactivated to save power.

[0340] For example, when the first device is a terminal, if the triggering conditions for using the second AI model to make a prediction are met, the terminal uses the second AI model to make a prediction and obtains a second result. If the first device is a network-side device or a server, the terminal can send the twelfth instruction information to the network-side device or server when the triggering conditions for using the second AI model to make a prediction are met, thereby triggering the network-side device or server to make a prediction based on the second AI model. Accordingly, upon receiving the twelfth instruction information, the network-side device or server uses the second AI model to make a prediction and obtains a second result.

[0341] In this embodiment, when the above triggering conditions are met, the first device uses the second AI model to make a prediction to obtain a first result, and then performs deactivation control on the first transmission based on the second result, which helps to further reduce device power consumption.

[0342] Optionally, after the first device determines the target result based on the target artificial intelligence (AI) model, the method further includes:

[0343] The first device performs a first operation, which includes at least one of the following:

[0344] Send at least a portion of the input information of the target AI model and at least one of the target results;

[0345] The process reverts to using a non-AI method to determine whether to activate or deactivate the first transmission.

[0346] Trigger the switching of the target AI model;

[0347] Trigger the retraining of the target AI model;

[0348] This triggers the supervision of the target AI model.

[0349] For example, the first device can send at least a portion of the input information of the target AI model and at least one of the target results to the device used for training the target AI model. Then, the device used for training the target AI model can perform fine-tuning or updating operations on the target AI model based on at least a portion of the input information of the target AI model and at least one of the target results.

[0350] The aforementioned non-AI approach, also known as the legacy approach, refers to a method that does not utilize an AI model to determine the activation or deactivation of the first transmission. It is understood that this non-AI approach is in contrast to the approach that determines the activation or deactivation of the first transmission based on a target AI model.

[0351] The above triggers the switching of the target AI model, for example, by changing the input information of the target AI model or by changing the AI ​​model used for the first transmission activation or deactivation control.

[0352] In some optional embodiments, the first device may perform the first operation if the prediction based on the target AI model fails. This helps to ensure the accuracy of the activation or deactivation control of the first transmission. The failure of the target AI model prediction may include failing to obtain the target result based on the target AI model, or the target result predicted by the target AI model being inaccurate. For example, if the target result indicates activation of on-demand SSB, after the network-side device activates on-demand SSB, no terminal selects the on-demand SSB beam, or the measured value of the on-demand SSB beam is less than a preset value.

[0353] Optionally, the step of reverting to a non-AI method to determine whether to activate or deactivate the first transmission includes:

[0354] If at least one of the following conditions is met, the process reverts to using a non-AI method to determine whether to activate or deactivate the first transmission;

[0355] If the prediction is not successfully completed even after the first device has used the target AI model for a period of time exceeding the third time limit;

[0356] The first device failed to make a prediction using the target AI model.

[0357] In this embodiment, the aforementioned third duration can be predefined by the protocol, configured by the network-side device, or determined by the first device.

[0358] Optionally, the method further includes at least one of the following:

[0359] The first device acquires the metrics of the target AI model;

[0360] The first device sends the metrics of the target AI model;

[0361] The metrics of the target AI model include at least one of the following:

[0362] The complexity of the target AI model;

[0363] The latency predicted by the target AI model;

[0364] The success rate of the target AI model's predictions;

[0365] The reliability of the results output by the target AI model.

[0366] The complexity of the aforementioned target AI model is defined with different complexity index requirements for different types / capabilities of network-side devices, terminals, or servers. For example, for ordinary terminals, the complexity of the AI ​​model used must not exceed the first value.

[0367] The latency predicted by the aforementioned target AI model can be understood as the duration of prediction, inference, or processing using the target AI model. Specifically, the duration of prediction, inference, or processing using the target AI model cannot exceed a first preset duration.

[0368] The success rate predicted by the aforementioned target AI model can be understood as the success rate of prediction, inference, or processing using the aforementioned target AI model within a specific time period. For example, the success rate predicted by the aforementioned target AI model can be the ratio of the number of successful predictions made using the aforementioned target AI model within a specific time period to the total number of predictions made within the specific time period. Alternatively, the success rate predicted by the aforementioned target AI model can be a value determined based on at least two success rates statistically analyzed over at least two specific time periods, such as the average of at least two success rates, where the success rate statistically analyzed for each specific time period is the ratio of the number of successful predictions made using the aforementioned target AI model within that specific time period to the total number of predictions made within that specific time period. The aforementioned specific time period can be a predefined duration by the protocol or a duration configured by the network-side device.

[0369] Specifically, the success rate of using the target AI model for prediction, inference, or processing must not be less than the second value.

[0370] When the target AI model is a first AI model, the reliability of the output of the first AI model can refer to the probability that the activated first transmission is used and successfully completes the relevant function, such as random access. When the target AI model is a second AI model, the reliability of the output of the second AI model can refer to the probability that the inactive first transmission is used and successfully completes the relevant function, such as random access. Specifically, the probability is required to be less than or equal to a third value, or the probability is required to be greater than or equal to a fourth value.

[0371] The aforementioned metrics for the first device to acquire the target AI model include metrics for the first device to determine the target AI model, or metrics for the first device to receive the target AI model.

[0372] Optionally, the method further includes:

[0373] The first device trains at least a portion of the AI ​​model in the target AI model;

[0374] or,

[0375] The first device receives at least a portion of the AI ​​model from the target AI model.

[0376] In one embodiment, the first device trains the target AI model and uses the target AI model for inference.

[0377] In another embodiment, the second device trains a target AI model and sends it to the first device, which then uses the target AI model for inference.

[0378] In another embodiment, a first device trains a portion of the target AI model, a second device trains another portion of the target AI model, and sends the trained AI model portion to the first device, which then uses the target AI model for inference.

[0379] Wherein, a portion of the first device training target AI model and another portion of the second device training target AI model may include one or more of the following:

[0380] The terminal reports the output of the AI ​​model training to the network device, and the network device uses the information reported by the terminal (i.e. the output of the terminal AI model training) as one of the input information for its own AI model training.

[0381] The network-side device sends the output of the AI ​​model training to the terminal, and the terminal uses the information sent by the network-side device (i.e. the output of the network-side AI model training) as one of the input information for its own AI model training.

[0382] The terminal-side or network-side device performs offline AI model training, and then fine-tunes the AI ​​model in the actual network.

[0383] The second device mentioned above can be a terminal, a network-side device, or a server.

[0384] Optionally, the triggering type for training the target AI model includes at least one of the following: conditional or event triggering, periodic triggering, and semi-static triggering.

[0385] Optionally, the conditions or events that trigger the training of the target AI model include at least one of the following:

[0386] The configuration information of the first transmission has changed;

[0387] The configuration information for the second transmission has changed;

[0388] The activation or deactivation method of the first transmission changes;

[0389] The target AI model failed to predict;

[0390] The target AI model fails to make predictions N times consecutively, where N is a positive integer;

[0391] The number of times the target AI model failed to predict reached the fourth threshold;

[0392] The target AI model was used for prediction;

[0393] The terminal reselects to a new cell.

[0394] The tracking area of ​​the terminal has changed;

[0395] The environment in which the terminal is located has changed;

[0396] The second transmission is different from the first transmission.

[0397] The first and second transmissions in this embodiment can be referred to the relevant descriptions in the foregoing embodiments, and will not be repeated here.

[0398] The activation method for the first transmission described above has changed; for example, activation is now performed by the terminal sending an activation signal instead of by the network-side device. Similarly, the deactivation method for the first transmission has changed; for example, deactivation is now performed by the terminal sending a deactivation signal instead of by the network-side device.

[0399] The aforementioned failure of the target AI model prediction may include failing to obtain the target result based on the target AI model, or the target result predicted based on the target AI model being inaccurate. For example, if the target result indicates the activation of on demand SSB, after the network-side device activates on demand SSB, no terminal selects the on demand SSB beam or the measured value of the on demand SSB beam is less than the preset value.

[0400] The environment in which the aforementioned terminal is located changes; for example, the aforementioned terminal can obtain information about the changes in the environment through sensing.

[0401] At least one of N, the fourth threshold, etc. mentioned above can be predefined by the protocol or configured by the network-side device.

[0402] Optionally, the configuration information of the first transmission includes at least one of the following: the number of the first transmissions, the range of the first transmissions, the beam configuration corresponding to the first transmissions, the transmission power of the first transmissions, and the period of the first transmissions;

[0403] or,

[0404] The configuration information of the second transmission includes at least one of the following: the number of second transmissions, the range of the second transmission, the beam configuration corresponding to the second transmission, the transmission power of the second transmission, and the period of the second transmission.

[0405] Taking the first or second transmission as an example, the configuration information may include at least one of the following: the number of SSBs, the index value of the SSB, the beam configuration corresponding to the SSB, the transmission power of the SSB, and the period of the SSB.

[0406] In this embodiment, when the conditions or events described above for triggering the training of the target AI model are met, the first device can perform training of the target AI model, which helps to ensure the accuracy of the prediction results based on the target AI model.

[0407] Optionally, the configuration information for periodic triggering includes at least one of the following: the starting point of periodic model training, the interval of periodic model training, the number of model training sessions within a period, and the duration of model training within a period.

[0408] The starting point for the aforementioned periodic model training is, for example, model training only begins after the terminal has been stationary in the cell for a certain period of time.

[0409] The intervals for the aforementioned periodic model training, for example, triggering at least one model training session every interval T.

[0410] Optionally, the semi-static triggering includes at least one of the following:

[0411] The semi-static triggering configuration information is sent and / or activated based on specific conditions or events.

[0412] The configuration information for the semi-static trigger is configured via Radio Resource Control (RRC), and / or the semi-static training of the model is activated or deactivated via physical control information.

[0413] The aforementioned physical control information, such as downlink control information (DCI).

[0414] In some optional embodiments, the above-described target AI model is trained based on target input information, wherein the target input information includes at least one of the following:

[0415] Time information;

[0416] Terminal status information;

[0417] Status information of network-side devices;

[0418] Server status information;

[0419] The frequency domain characteristics of the eleventh transmission;

[0420] The temporal characteristics of the eleventh transmission;

[0421] The spatial characteristics of the eleventh transmission;

[0422] The signal strength obtained by the terminal from the reference signal associated with the twelfth transmission is at least one of the signal strength and signal quality obtained from the reference signal associated with the twelfth transmission, or the value determined based on at least one of the signal strength and signal quality obtained by the terminal from the reference signal associated with the twelfth transmission;

[0423] The value determined by the terminal based on at least one of the signal strength and signal quality measured by the twelfth transmission, or based on at least one of the signal strength and signal quality measured by the terminal based on the twelfth transmission;

[0424] The number of times the terminal failed to access the physical random access channel PRACH corresponding to the thirteenth transmission or the number of times it failed to receive the access response message.

[0425] The number of PRACH retransmissions performed by the terminal on the PRACH resource associated with the thirteenth transmission;

[0426] The thirteenth instruction information is used to indicate whether the terminal fails to access the PRACH resource associated with the thirteenth transmission after attempting two steps of random access and then falling back to four steps of random access.

[0427] The fourteenth indication information is used to indicate whether the power of the terminal transmitting the PRACH signal on the PRACH resource associated with the thirteenth transmission is greater than or equal to the first threshold.

[0428] The fifteenth indication information is used to indicate at least one of the following: whether the terminal receives a second random access response (RAR) message, the number of second RAR messages received within a first time period, and the number of second RAR messages received within the first time period being greater than or equal to a second threshold; wherein the second RAR message is a RAR message whose included preamble identifier is not a preamble identifier sent by the terminal on the PRACH resource associated with the thirteenth transmission.

[0429] The sixteenth indication information is used to indicate whether the number of times the terminal sends an activation signal is less than or equal to the first number, or the sixteenth indication information is used to indicate whether the number of times the terminal sends a deactivation signal is less than or equal to the second number;

[0430] The seventeenth indication information is used to indicate whether the timing advance TA for activating signal transmission is valid, or the seventeenth indication information is used to indicate whether the timing advance TA for deactivating signal transmission is valid;

[0431] The eighteenth indication information is used to indicate whether the interval between the current time and the time of the previous activation signal is greater than or equal to the first interval, or the eighteenth indication information is used to indicate whether the interval between the current time and the time of the previous deactivation signal is greater than or equal to the second interval.

[0432] The nineteenth instruction information is used to indicate whether the interval between the time of the previous activation or deactivation of the eleventh transmission and the current time is greater than or equal to the third interval;

[0433] The twentieth indication information is used to indicate whether the terminal has sent the fourteenth transmission activation signal, or whether the twentieth indication information is used to indicate whether the terminal has sent the fourteenth transmission deactivation signal.

[0434] The 21st indication information is used to indicate whether the 15th transmission has been activated, or whether the 21st indication information has been deactivated.

[0435] The twenty-second instruction message is used to indicate whether the terminal has detected the sixteenth transmission;

[0436] Information on sudden events;

[0437] The twelfth transmission is different from the eleventh transmission, and the thirteenth transmission is a transmission associated with PRACH.

[0438] It is understood that the aforementioned target input information corresponds to the aforementioned first input information. The various parameter items of the aforementioned target input information can be found in the relevant descriptions of the various parameter items of the aforementioned first input information, and will not be repeated here. Furthermore, the parameter items included in the aforementioned first input information may be the same as the parameter items included in the aforementioned target input information, or the parameter items included in the aforementioned first input information may be a subset of the parameter items included in the aforementioned target input information.

[0439] For example, the target input information mentioned above may include the most recent P times of input information used to determine whether to activate or deactivate on-demand transmission, where P is a positive integer.

[0440] In some optional embodiments, the labels used for training the first AI model include at least one of the following:

[0441] Activate or deactivate the eleventh transmission;

[0442] Send an activation signal or not send an activation signal, the activation signal being used to activate or request activation of the eleventh transmission;

[0443] The number of eleventh transmissions that need to be activated;

[0444] The range of the eleventh transmission that needs to be activated.

[0445] The labels used for training the second AI model mentioned above include at least one of the following:

[0446] Deactivate or deactivate the eleventh transmission;

[0447] Send a deactivation signal or not send a deactivation signal, the deactivation signal being used to deactivate or request deactivation of the eleventh transmission;

[0448] The number of eleventh transfers that need to be deactivated;

[0449] The range of the eleventh transmission that needs to be deactivated.

[0450] Optionally, the method further includes:

[0451] The first device receives second input information, which is used for training the target AI model;

[0452] or,

[0453] The first device sends third input information, which is used for training the target AI model.

[0454] For example, when the target AI model is trained by a first device, the first device can receive second input information from a second device, which is used for training the target AI model. When the target AI model is trained by a second device, the first device can send third input information to the second device. The second device can be a terminal, a server, or a network-side device.

[0455] The second input information may include some or all of the information in the target input information. The third input information may include some or all of the information in the target input information.

[0456] Optionally, the first device is a terminal;

[0457] The first device receives the second input information, including:

[0458] The first device receives second input information sent by the network-side device through at least one of the following: Media Access Control (MAC) Control Element (CE); RRC message; Non-access Stratum (NAS) message; User plane data; System Information Block (SIB); Physical Layer Signaling; Physical Downlink Shared Channel; MSG 2; MSG 4; MSG B;

[0459] or,

[0460] The first device sends third input information, including at least one of the following:

[0461] The first device sends the third input information to the network-side device through at least one of the following: MAC CE; RRC message; NAS message; user plane data; MSG 1; MSG A; MSG 3; physical uplink control channel; physical uplink shared channel; random access channel; uplink reference signal;

[0462] The first device sends the third input information to the server through the first interface message.

[0463] The aforementioned physical layer signaling, such as Layer 1 signaling of PDCCH. The aforementioned uplink reference signals, such as sounding reference signal (SRS) or wake-up signal (WUS).

[0464] The first interface message mentioned above is an interface message between the terminal and the server, such as an OTT interface message.

[0465] Optionally, the first device is a network-side device;

[0466] The first device receives the second input information, including:

[0467] The first device receives second input information sent by the terminal via at least one of the following: MAC CE; RRC message; NAS message; user plane data; MSG 1; MSG A; MSG 3; physical uplink control channel; physical uplink shared channel; random access channel; uplink reference signal;

[0468] or,

[0469] The first device sends third input information, including at least one of the following:

[0470] The first device sends the third input information to the terminal via at least one of the following: MAC CE; RRC message; Layer NAS message; User plane data; DCI information; SIB; Physical layer signaling; Physical downlink shared channel; MSG 2; MSG 4; MSG B;

[0471] The first device sends the third input information to the server through the second interface message.

[0472] The second interface message mentioned above is an interface message between the network-side device and the server.

[0473] Optionally, the first device is a server;

[0474] The first device receives third input information, including:

[0475] The first device receives third input information from at least one of the terminal and the network-side device.

[0476] It is understandable that the server can receive third-party input information based on the interface messages between the server and the terminal, and the server can receive third-party input information based on the interface messages between the server and the network-side device.

[0477] It is understandable that the third-party input information received by the server from the terminal is different from the third-party input information received by the server from the network-side device.

[0478] Optionally, the triggering conditions for sending or receiving the second or third input information include at least one of the following:

[0479] Terminal resides in the community;

[0480] The terminal selects a cell for the first time;

[0481] Terminal reselects cell;

[0482] The terminal enters RRC connection state;

[0483] The terminal has been in an inactive state for four consecutive hours.

[0484] For example, when the first device is a terminal, the first device may send the second input information to the network-side device or server when the above triggering conditions are met, or it may request the network-side device or server to obtain the third input information; when the first device is a network-side device or server, the terminal may send the third input information to the first device when the above triggering conditions are met, or the terminal may request the first device to obtain the second input information.

[0485] The aforementioned fourth duration can be a duration predefined by the protocol, or it can be a duration configured by the network-side device.

[0486] Specifically, when the triggering conditions for sending or receiving the second or third input information are met, the sending or receiving of the second or third input information can be triggered at least once. For example, the periodic or semi-static sending or receiving of the second or third input information can be triggered.

[0487] Optionally, the criteria for determining whether the first AI model has completed training include at least one of the following:

[0488] The loss function used for training the first AI model satisfies the first preset condition;

[0489] When the output of the first AI model indicates that the seventh transmission is activated, the measurement result obtained by the terminal based on the seventh transmission satisfies the second preset condition.

[0490] If the output of the first AI model indicates that the seventh transmission is activated, the probability that the terminal successfully detects the seventh transmission after the seventh transmission is activated is greater than or equal to the third threshold.

[0491] If the output of the first AI model indicates that the seventh transmission is activated, the terminal detects that the duration of the seventh transmission is less than or equal to the fourth threshold after the seventh transmission is activated.

[0492] When the output of the first AI model indicates that the seventh transmission is activated, the probability that the terminal successfully accesses the network based on the seventh transmission is greater than or equal to the fifth threshold.

[0493] If the output of the first AI model indicates that the seventh transmission is not activated, the probability that the terminal successfully accesses the network based on the eighth transmission is greater than or equal to the sixth threshold.

[0494] When the output of the first AI model indicates that the seventh transmission is activated, the probability or frequency of the terminal selecting the seventh transmission for random access is greater than or equal to the seventh threshold.

[0495] When the output of the first AI model indicates that the seventh transmission is activated, the probability or frequency of the terminal selecting the eighth transmission for random access is greater than or equal to the eighth threshold.

[0496] The number of training iterations for the first AI model has reached a first preset value;

[0497] The number of iterations for fine-tuning the first AI model reaches the second preset value.

[0498] The loss function used for training the first AI model can be related to at least one of the following:

[0499] The mean square error or normalized mean square error between the predicted and actual results;

[0500] The mean absolute error between the predicted result and the actual result.

[0501] The loss function used for training the first AI model satisfies a first preset condition. For example, the loss function used for training the first AI model satisfies a predefined index or a predefined value. For instance, the training error (e.g., the mean squared error or normalized mean squared error between the predicted result and the actual result, the mean absolute error between the predicted result and the actual result, etc.) is less than a predefined value.

[0502] The aforementioned seventh transmission may include at least one of on-demand transmitted seventh signals, on-demand transmitted seventh channels, and on-demand transmitted seventh resources. The aforementioned seventh signals may include, but are not limited to, at least one of on-demand synchronization signals, on-demand reference signals, on-demand broadcast signals, and on-demand control signals. For example, the aforementioned on-demand synchronization signals may include on-demand SSB, and the aforementioned on-demand reference signals may include, but are not limited to, at least one of on-demand SRS, on-demand CSI-RS, and on-demand TRS. The aforementioned seventh channels may include, but are not limited to, at least one of on-demand PBCH, on-demand PRACH, on-demand MsgA PUSCH, on-demand CGPUSCH, and on-demand control channels. The aforementioned seventh resources may include, but are not limited to, at least one of on-demand synchronization signal resources, on-demand reference signal resources, on-demand broadcast signal resources, and on-demand control signal resources. Exemplarily, the seventh transmission may be the same as the eleventh transmission in the aforementioned target input information.

[0503] The measurement results obtained based on the seventh transmission may include, but are not limited to, at least one of RSRP, RSRQ, Received Signal Strength Indication (RSSI), and Signal Noise Ratio (SNR). The measurement results satisfy a second preset condition, for example, RSRP, RSRQ, RSSI, or SNR is greater than or equal to the corresponding threshold.

[0504] At least one of the aforementioned first preset condition, second preset condition, third threshold, fourth threshold, fifth threshold, sixth threshold, seventh threshold, eighth threshold, first preset value, and second preset value is predefined by the protocol or configured by the network-side device.

[0505] The eighth transmission described above differs from the seventh transmission described above. The eighth transmission can be a conventional transmission, an inflexible transmission, a non-on-demand transmission, or a transmission that does not support activation or deactivation, etc. For example, the eighth transmission may include at least one of an eighth signal, an eighth channel, and an eighth resource. The eighth signal may include, but is not limited to, at least one of synchronization signals, reference signals, broadcast signals, and control signals. For example, the synchronization signal may include normal SSB, and the reference signal may include, but is not limited to, at least one of normal SRS, normal CSI-RS, and normal TRS. The eighth channel may include, but is not limited to, at least one of PBCH, PRACH, CG PUSCH, MsgA PUSCH, and control channels. The eighth resource may include, but is not limited to, at least one of synchronization signal resources, reference signal resources, broadcast signal resources, and control signal resources. For example, the eighth transmission may be the same as the twelfth transmission in the target input information described above.

[0506] Optionally, the criteria for determining whether the training of the second AI model is complete include at least one of the following:

[0507] The loss function used for training the second AI model satisfies the third preset condition;

[0508] If the result output by the second AI model indicates that the ninth transmission should not be activated, the measurement result obtained by the terminal based on the ninth transmission satisfies the fourth preset condition.

[0509] If the output of the second AI model indicates that the ninth transmission should not be activated, the probability that the terminal detects the ninth transmission is greater than or equal to the ninth threshold.

[0510] If the result output by the second AI model indicates that the ninth transmission should not be activated, the terminal detects that the duration of the ninth transmission is less than or equal to the tenth threshold.

[0511] If the output of the second AI model indicates that the ninth transmission should not be activated, the probability that the terminal successfully accesses the network based on the ninth transmission is greater than or equal to the eleventh threshold.

[0512] When the output of the second AI model indicates that the ninth transmission should be activated, the probability that the terminal will successfully access the network based on the tenth transmission is greater than or equal to the twelfth threshold.

[0513] If the output of the second AI model indicates that the ninth transmission should not be activated, the probability or frequency of the terminal selecting the ninth transmission for random access is greater than or equal to the thirteenth threshold.

[0514] When the output of the second AI model indicates that the ninth transmission should be activated, the probability or frequency of the terminal selecting the tenth transmission for random access is greater than or equal to the fourteenth threshold.

[0515] The second AI model has been trained a third preset number of times;

[0516] The second AI model has reached the fourth preset number of iterations for fine-tuning.

[0517] The loss function used for training the second AI model satisfies a third preset condition. For example, the loss function used for training the second AI model satisfies a predefined index or a predefined value. For instance, the training error (e.g., the mean squared error or normalized mean squared error between the predicted result and the actual result, the mean absolute error between the predicted result and the actual result, etc.) is less than a predefined value.

[0518] The aforementioned ninth transmission may include at least one of on-demand transmitted ninth signals, on-demand transmitted ninth channels, and on-demand transmitted ninth resources. The aforementioned ninth signals may include, but are not limited to, at least one of on-demand synchronization signals, on-demand reference signals, on-demand broadcast signals, and on-demand control signals. For example, the aforementioned on-demand synchronization signals may include on-demand SSB, and the aforementioned on-demand reference signals may include, but are not limited to, at least one of on-demand SRS, on-demand CSI-RS, and on-demand TRS. The aforementioned ninth channels may include, but are not limited to, at least one of on-demand PBCH, on-demand PRACH, on-demand MsgA PUSCH, on-demand CGPUSCH, and on-demand control channels. The aforementioned ninth resources may include, but are not limited to, at least one of on-demand synchronization signal resources, on-demand reference signal resources, on-demand broadcast signal resources, and on-demand control signal resources. Exemplarily, the ninth transmission may be the same as the eleventh transmission in the aforementioned target input information.

[0519] The measurement results obtained based on the ninth transmission may include, but are not limited to, at least one of RSRP, RSRQ, RSSI, and SNR. The measurement results satisfy a fourth preset condition, for example, RSRP, RSRQ, RSSI, or SNR is greater than or equal to the corresponding threshold.

[0520] At least one of the aforementioned third preset condition, fourth preset condition, ninth threshold, tenth threshold, eleventh threshold, twelfth threshold, thirteenth threshold, fourteenth threshold, third preset value, and fourth preset value is predefined by the protocol or configured by the network-side device.

[0521] The tenth transmission described above differs from the ninth transmission described above. The tenth transmission can be a regular transmission, an inflexible transmission, a non-on-demand transmission, or a transmission that does not support activation or deactivation, etc. For example, the tenth transmission may include at least one of a tenth signal, a tenth channel, and a tenth resource. The tenth signal may include, but is not limited to, at least one of a synchronization signal, a reference signal, a broadcast signal, and a control signal. For example, the synchronization signal may include a normalSSB. The tenth channel may include, but is not limited to, at least one of a PBCH, PRACH, CG PUSCH, MsgA PUSCH, and a control channel. The tenth resource may include, but is not limited to, at least one of a synchronization signal resource, a reference signal resource, a broadcast signal resource, and a control signal resource. For example, the tenth transmission may be the same as the twelfth transmission in the target input information described above.

[0522] Optionally, if the target AI model is trained by the first device, the first information of the target AI model is determined according to the type of the first device;

[0523] The first information includes at least one of the following: model information of the target AI model, input information for training the target AI model, label information for training the target AI model, and execution method for training the target AI model.

[0524] The model information for the aforementioned target AI model may include model structure or model algorithm, etc. For example, the AI ​​model used for training the AI ​​model may differ depending on the type of first device. For instance, a overly complex AI model may not be applicable to a less capable first device.

[0525] For example, the input or label information used for training the target AI model may differ for different types of first devices. For instance, a less capable first device may use less input information for model training than a more capable first device.

[0526] For example, the execution method of AI model training can differ depending on the type of first device. For instance, for a first device with weaker capabilities, model training can be performed only on a second device, or only a small portion of the joint model training can be performed on the first device. For example, if the first device is a terminal, model training involving user privacy data can be performed on the terminal side.

[0527] For example, the artificial intelligence model used for model training differs for different types of first devices.

[0528] In some optional embodiments, when the target AI model is trained by a second device, the first information of the target AI model is determined according to the type of the second device;

[0529] The first information includes at least one of the following: model information of the target AI model, input information for training the target AI model, label information for training the target AI model, and execution method for training the target AI model.

[0530] In this embodiment, the first information of the target AI model is determined based on the type of device used to train the target AI model, which helps to ensure the probability of successful training of the target AI model.

[0531] Optionally, the triggering conditions for updating or retraining the target AI model include at least one of the following:

[0532] The configuration information of the first transmission has changed;

[0533] The configuration information for the second transmission has changed;

[0534] The activation or deactivation method of the first transmission changes;

[0535] The terminal moves to a new cell, a new tracking area, or a new geographical location;

[0536] The change in the terminal's moving speed is greater than or equal to a fifth preset value, or the rate of change in the terminal's moving speed is greater than or equal to a sixth preset value.

[0537] It has been five hours since the last model update or retraining.

[0538] Timeout for a timer used to trigger model updates or retraining;

[0539] M consecutive model supervisions have occurred or M model supervisions have been triggered, where M is a positive integer;

[0540] The target AI model failed to predict;

[0541] The target AI model fails to predict K times consecutively, where K is a positive integer;

[0542] The number of times the target AI model failed to predict reached the fifth threshold;

[0543] The target AI model was used for prediction;

[0544] The environment in which the terminal is located has changed.

[0545] For changes in the configuration information of the first transmission, the configuration information of the second transmission, the activation or deactivation method of the first transmission, the failure of the target AI model prediction, and the change in the environment of the terminal in this embodiment, please refer to the relevant descriptions in the foregoing embodiments, which will not be repeated here.

[0546] At least one of the aforementioned fifth preset value, sixth preset value, fifth duration, M, K, and third duration can be predefined by the protocol or configured by the network-side device.

[0547] In this embodiment, the target AI model is updated or retrained when the triggering conditions for updating or retraining the target AI model are met. This helps to ensure the accuracy of the first transmission activation or deactivation control based on the target AI model.

[0548] In practical applications, when the inference environment differs significantly from the training environment, the activation or deactivation performance of the first transport based on the AI ​​model will become very poor, resulting in a mismatch. Therefore, it is necessary to supervise the actual inference performance of the first transport activation or deactivation based on the AI ​​model and trigger adjustment measures based on the model supervision results.

[0549] Optionally, the method further includes:

[0550] The first device acquires the model supervision results of the target AI model;

[0551] or,

[0552] The first device sends the model supervision results of the target AI model.

[0553] For example, the above-mentioned model supervision results may include at least one of the following: error information or accuracy information between the prediction results and actual results of the target AI model, performance indicators of the communication system (e.g., cell search latency, cell dwell success rate, timing error, etc.), and model-related information of the target AI model (e.g., runtime of the target AI model, or memory space occupied by the target AI model).

[0554] In one embodiment, the first device can acquire the model supervision results of the target AI model, and then determine whether it is necessary to update or retrain the target AI model, or whether it is necessary to switch the target AI model, based on the model supervision results of the target AI model.

[0555] In another embodiment, the first device can perform model supervision on the target AI model, obtain model supervision results, and send the model supervision results to the second device, so that the second device can determine whether the target AI model needs to be updated or retrained based on the model supervision results. The second device can be a device used for training or managing the target AI model, for example, it can be a terminal, a network-side device, or a server.

[0556] Optionally, the first device acquires the model supervision results of the target AI model, including:

[0557] The first device performs model supervision on the target AI model to obtain the model supervision result of the target AI model;

[0558] or,

[0559] The first device receives the model supervision results of the target AI model.

[0560] For example, the first device can receive model supervision results of the target AI model from the second device, which can be a device used for training or managing the target AI model, such as a terminal, network-side device, or server.

[0561] Optionally, the configuration information for supervising the target AI model includes at least one of the following:

[0562] Identification of AI models that require model supervision;

[0563] The cycle of model supervision;

[0564] The duration of model supervision;

[0565] Information related to the detection window in model supervision;

[0566] Triggering conditions for model supervision;

[0567] Metrics for model supervision.

[0568] The detection window information related to the above model supervision may include at least one of the following: the duration of the detection window and the number of samples to be detected.

[0569] The metrics for model supervision mentioned above include, for example, error information or accuracy information between the predicted results and the actual results.

[0570] Optionally, the triggering conditions for the supervision of the target AI model include at least one of the following:

[0571] The target AI model does not meet the supervision index, or the target AI model does not meet the fifth preset condition, or the duration of the target AI model not meeting the supervision index reaches the sixth duration, or the duration of the target AI model not meeting the supervision index reaches the sixth duration.

[0572] The target result of the target AI model does not meet the sixth preset condition, or the duration for which the target result of the target AI model does not meet the sixth preset condition reaches the seventh duration;

[0573] The target AI model does not meet at least one of its metrics, or at least one of its metrics does not meet the seventh preset condition.

[0574] The target result of the above-mentioned target AI model does not meet the sixth preset condition. For example, the first device fails to complete a specific function (such as random access) that depends on the first transmission (e.g., on-demand SSB) or the second transmission (e.g., normal SSB) after using the target AI model for more than Q time. Q is the time predefined by the protocol or configured by the network-side device; or the first device fails to successfully complete AI inference using the target AI model.

[0575] The metrics for the aforementioned target AI model can be found in the relevant descriptions of the foregoing embodiments, and will not be repeated here.

[0576] If at least one of the above-mentioned metrics of the target AI model is not met, for example, the first device determines to activate the first transmission (e.g., on demand SSB) or not to deactivate the first transmission based on the target AI model, but the RSRP measured based on the first transmission does not meet the requirements; or, the latency predicted by the target AI model exceeds the preset duration.

[0577] Optionally, the metrics for supervising the target AI model include at least one of the following:

[0578] Error information or accuracy information between the prediction results and actual results of the target AI model;

[0579] Performance metrics of a communication system;

[0580] The model-related information of the target AI model.

[0581] In this embodiment, the performance indicators of the aforementioned communication system include, for example, cell search latency, cell dwell success rate, and timing error. It should be noted that these performance indicators can be obtained statistically within a monitoring window.

[0582] The aforementioned model-related information of the target AI model, such as the runtime of the target AI model or the amount of memory space occupied by the target AI model.

[0583] Optionally, the method further includes at least one of the following:

[0584] The first device sends information about its AI-related capabilities.

[0585] The first device determines the AI-related capability information of the second device;

[0586] The AI-related capability information is used to indicate at least one of the following:

[0587] It may or may not have the ability to train an AI model for predicting the activation or deactivation of a target.

[0588] It may or may not have the ability to predict the activation or deactivation of target transmission through AI models;

[0589] It may or may not have the ability to send first auxiliary information, which is used to predict the activation or deactivation of the target transmission through an AI model;

[0590] It may or may not have the ability to send second auxiliary information, which is used to train an AI model for predicting the activation or deactivation of the target transmission.

[0591] The aforementioned target transmission may include, but is not limited to, at least one of the following: signals transmitted on demand, channels transmitted on demand, and resources transmitted on demand.

[0592] In one embodiment, the first device may send AI-related capability information of the first device to the second device. For example, if the AI-related capability information of the first device indicates that the first device has the ability to train an AI model for predicting the activation or deactivation of the target transmission, the second device may determine that the first device shall train the AI ​​model for predicting the activation or deactivation of the target transmission; if the AI-related capability information of the first device indicates that the first device does not have the ability to train an AI model for predicting the activation or deactivation of the target transmission, the second device may determine that the training of the AI ​​model for predicting the activation or deactivation of the target transmission shall be performed.

[0593] In another embodiment, the first device can determine the AI-related capability information of the second device. For example, if the AI-related capability information of the second device indicates that the second device has the ability to train an AI model for predicting the activation or deactivation of the target transmission, the first device can determine that the training of the AI ​​model for predicting the activation or deactivation of the target transmission will be performed by the second device; if the AI-related capability information of the second device indicates that the second device does not have the ability to train an AI model for predicting the activation or deactivation of the target transmission, the first device can determine that the training of the AI ​​model for predicting the activation or deactivation of the target transmission will be performed.

[0594] Optionally, the first device determines the AI-related capability information of the second device, including:

[0595] The first device determines the AI-related capability information of the second device based on at least one of the following:

[0596] The equipment type of the second device;

[0597] AI-related capability information indicated by reference signals;

[0598] The control information sent by the second device carries AI-related capability information;

[0599] The AI-related capability information carried in the RRC signaling sent by the second device;

[0600] The AI-related capability information carried in the interface messages between the first device and the second device.

[0601] For example, the first device can determine the AI-related capability information of the second device based on the device type of the second device. For example, different AI-related capabilities can be introduced for different terminal types (e.g., Reduced Capability (RedCap), Internet of Things (IoT), etc.), or different AI-related capabilities can be introduced for different network types (e.g., Non-Terrestrial Network (NTN), Terrestrial Network (TN), etc.).

[0602] The AI-related capability information indicated by the reference signal mentioned above, for example, indicates the ability to predict target transmission activation via PRACH resource.

[0603] The aforementioned control information may include uplink control information or physical layer control information, etc.

[0604] The interface messages between the first device and the second device can be specific interface messages, which may be specific to a particular AI model or applicable to all AI models. For example, if one of the first and second devices is a terminal and the other is a network-side device, the interface messages between them can be interface messages between the terminal and the network-side device. If one of the first and second devices is a terminal and the other is a server, the interface messages between them can be interface messages between the terminal and the server. If one of the first and second devices is a network-side device and the other is a server, the interface messages between them can be interface messages between the network-side device and the server.

[0605] It is understood that the second device can determine the AI-related capability information of the first device based on at least one of the following:

[0606] The device type of the first device;

[0607] AI-related capability information indicated by reference signals;

[0608] The control information sent by the first device carries AI-related capability information;

[0609] The AI-related capability information carried in the RRC signaling sent by the first device;

[0610] The AI-related capability information carried in the interface messages between the first device and the second device.

[0611] Optionally, the first device is a server, and the method further includes:

[0612] The server sends the target result to the terminal or network-side device.

[0613] Wherein, when the server sends the first result to the terminal, the first result is used to indicate at least one of the following: activating or deactivating the first transmission; sending an activation signal or not sending an activation signal, the activation signal being used to activate or request activation of the first transmission; the number of first transmissions to be activated; and the scope of the first transmissions to be activated. Where the server sends the first result to the network-side device, the first result is used to indicate at least one of the following: activating or deactivating the first transmission; the number of first transmissions to be activated; and the scope of the first transmissions to be activated.

[0614] When the server sends the second result to the terminal, the second result indicates at least one of the following: deactivating or not deactivating the first transmission; sending a deactivation signal or not sending a deactivation signal, the deactivation signal being used to deactivate or request deactivation of the first transmission; the number of first transmissions to be deactivated; and the range of first transmissions to be deactivated. When the server sends the second result to the network-side device, the second result indicates at least one of the following: deactivating or not deactivating the first transmission; the number of first transmissions to be deactivated; and the range of first transmissions to be deactivated.

[0615] It should be noted that the behavior of the terminal or network-side device after obtaining the first result sent by the server can be referred to the relevant descriptions of Scenario 1 and Scenario 2 above, and will not be repeated here. The behavior of the terminal or network-side device after obtaining the second result sent by the server can be referred to the relevant descriptions of Scenario 4 and Scenario 5 above, and will not be repeated here.

[0616] Please see Figure 6 , Figure 6 This is a flowchart of a transmission control method provided in an embodiment of this application. This method can be executed by a second device, such as... Figure 6 As shown, it includes the following steps:

[0617] Step 601: The second device performs a second operation, which includes at least one of the following:

[0618] At least a portion of the AI ​​model in the training target AI model;

[0619] Send at least a portion of the AI ​​model from the target AI model to the first device;

[0620] Send first input information to the first device, the first input information being used for prediction by the target AI model;

[0621] Send second input information to the first device, the second input information being used for training the target AI model;

[0622] Receive third input information from the first device, the third input information being used for training the target AI model;

[0623] Receive the target result sent by the first device, wherein the target result is the result determined according to the target AI model;

[0624] Receive the supervision results of the target AI model sent by the first device, or send the supervision results of the target AI model to the first device;

[0625] The target AI model is subjected to model supervision to obtain the supervision results of the target AI model;

[0626] Send an eleventh instruction message to the first device, the eleventh instruction message being used to trigger the first device to train the target AI model;

[0627] Send a twelfth instruction message to the first device, the twelfth instruction message being used to trigger the first device to make a prediction based on the target AI model;

[0628] The target AI model includes either a first AI model or a second AI model;

[0629] The first AI model is used to predict at least one of the following:

[0630] Activate or deactivate the target transfer;

[0631] Sending an activation signal or not sending an activation signal, the activation signal being used to activate or request activation of the target transmission;

[0632] The number of target transmissions that need to be activated;

[0633] The range of target transmissions that need to be activated;

[0634] The second AI model is used to predict at least one of the following;

[0635] Deactivate or deactivate the target transfer;

[0636] Send a deactivation signal or not send a deactivation signal, wherein the deactivation signal is used to deactivate or request deactivation of the target transmission;

[0637] The number of target transfers that need to be deactivated;

[0638] The range of the target transmission that needs to be deactivated.

[0639] The aforementioned target transmission can be any on-demand transmission or flexible transmission. For example, the aforementioned target transmission may include at least one of on-demand transmission signals, on-demand transmission channels, and on-demand transmission resources. The aforementioned on-demand transmission signals may include, but are not limited to, at least one of on-demand synchronization signals, on-demand reference signals, on-demand broadcast signals, and on-demand control signals. For example, the aforementioned on-demand synchronization signals may include on-demand SSB, and the aforementioned on-demand reference signals may include, but are not limited to, at least one of SRS, CSI-RS, and TRS. The aforementioned on-demand transmission channels may include, but are not limited to, at least one of on-demand PBCH, on-demand PRACH, on-demand MsgA PUSCH, on-demand CG PUSCH, and on-demand control channels. The aforementioned on-demand transmission resources may include, but are not limited to, at least one of on-demand synchronization signal resources, on-demand reference signal resources, on-demand broadcast signal resources, and on-demand control signal resources.

[0640] Optionally, at least a portion of the AI ​​model in the training target AI model includes:

[0641] Train at least a portion of the AI ​​model in the target AI model based on the target input information;

[0642] The target input information includes at least one of the following:

[0643] Time information;

[0644] Terminal status information;

[0645] Status information of network-side devices;

[0646] Server status information;

[0647] The frequency domain characteristics of the eleventh transmission;

[0648] The temporal characteristics of the eleventh transmission;

[0649] The spatial characteristics of the eleventh transmission;

[0650] The signal strength and signal quality obtained by the terminal measuring the reference signal of the twelfth transmission association, or the value determined based on the signal strength and signal quality obtained by the terminal measuring the reference signal of the twelfth transmission association;

[0651] The value determined by the terminal based on at least one of the signal strength and signal quality measured by the twelfth transmission, or based on at least one of the signal strength and signal quality measured by the terminal based on the twelfth transmission;

[0652] The number of times the terminal failed to access the physical random access channel PRACH corresponding to the thirteenth transmission or the number of times it failed to receive the access response message.

[0653] The number of PRACH retransmissions performed by the terminal on the PRACH resource associated with the thirteenth transmission;

[0654] The thirteenth instruction information is used to indicate whether the terminal fails to access the PRACH resource associated with the thirteenth transmission after attempting two steps of random access and then falling back to four steps of random access.

[0655] The fourteenth indication information is used to indicate whether the power of the terminal transmitting the PRACH signal on the PRACH resource associated with the thirteenth transmission is greater than or equal to the first threshold.

[0656] The fifteenth indication information is used to indicate at least one of the following: whether the terminal receives a second random access response (RAR) message, the number of second RAR messages received within a first time period, and the number of second RAR messages received within the first time period being greater than or equal to a second threshold; wherein the second RAR message is a RAR message whose included preamble identifier is not a preamble identifier sent by the terminal on the PRACH resource associated with the thirteenth transmission.

[0657] The sixteenth indication information is used to indicate whether the number of times the terminal sends an activation signal is less than or equal to the first number, or the sixteenth indication information is used to indicate whether the number of times the terminal sends a deactivation signal is less than or equal to the second number;

[0658] The seventeenth indication information is used to indicate whether the timing advance TA for activating signal transmission is valid, or the seventeenth indication information is used to indicate whether the timing advance TA for deactivating signal transmission is valid;

[0659] The eighteenth indication information is used to indicate whether the interval between the current time and the time of the previous activation signal is greater than or equal to the first interval, or the eighteenth indication information is used to indicate whether the interval between the current time and the time of the previous deactivation signal is greater than or equal to the second interval.

[0660] The nineteenth instruction information is used to indicate whether the interval between the time of the previous activation or deactivation of the eleventh transmission and the current time is greater than or equal to the third interval;

[0661] The twentieth indication information is used to indicate whether the terminal has sent the fourteenth transmission activation signal, or whether the twentieth indication information is used to indicate whether the terminal has sent the fourteenth transmission deactivation signal.

[0662] The 21st indication information is used to indicate whether the 15th transmission has been activated, or whether the 21st indication information has been deactivated.

[0663] The twenty-second instruction message is used to indicate whether the terminal has detected the sixteenth transmission;

[0664] Information on sudden events;

[0665] The twelfth transmission is different from the eleventh transmission, and the thirteenth transmission is a transmission associated with PRACH.

[0666] The aforementioned eleventh transmission may include at least one of an eleventh signal transmitted on demand, an eleventh channel transmitted on demand, and an eleventh resource transmitted on demand. The eleventh signal may include, but is not limited to, at least one of on-demand synchronization signals, on-demand reference signals, on-demand broadcast signals, and on-demand control signals. For example, the on-demand synchronization signal may include on-demand SSB, and the on-demand reference signal may include, but is not limited to, at least one of SRS, CSI-RS, and TRS. The eleventh channel may include, but is not limited to, at least one of on-demand PBCH, on-demand PRACH, on-demand MsgA PUSCH, on-demand CG PUSCH, and on-demand control channel. The eleventh resource may include, but is not limited to, at least one of on-demand synchronization signal resources, on-demand reference signal resources, on-demand broadcast signal resources, and on-demand control signal resources.

[0667] The twelfth transmission described above differs from the eleventh transmission. The twelfth transmission can be a normal transmission, an inflexible transmission, a non-on-demand transmission, or a transmission that does not support activation or deactivation. For example, the twelfth transmission may include at least one of a twelfth signal, a twelfth channel, and a twelfth resource. The twelfth signal may include, but is not limited to, at least one of synchronization signals, reference signals, broadcast signals, and control signals. For example, the synchronization signal may include a normal SSB. The twelfth channel may include, but is not limited to, at least one of PBCH, PRACH, CG PUSCH, MsgAPUSCH, and control channels. The twelfth resource may include, but is not limited to, at least one of synchronization signal resources, reference signal resources, broadcast signal resources, and control signal resources.

[0668] The reference signal for the twelfth transmission association mentioned above can be found in the relevant description of the reference signal for the second transmission association mentioned above, and will not be repeated here.

[0669] The thirteenth transmission mentioned above is a transmission associated with PRACH. Please refer to the relevant description of the third transmission mentioned above, which will not be repeated here.

[0670] The fourteenth transmission mentioned above can be found in the relevant description of the fourth transmission mentioned above, and will not be repeated here.

[0671] The above-mentioned fifteenth transmission can be found in the relevant description of the fifth transmission mentioned above, and will not be repeated here.

[0672] The sixteenth transmission mentioned above can be found in the relevant description of the sixth transmission mentioned above, and will not be repeated here.

[0673] Optionally, the status information of the terminal includes at least one of the following: the location information of the terminal, the distribution information of the terminal, the direction of movement of the terminal, the speed of movement of the terminal, the energy consumption status of the terminal, the battery status of the terminal, the network scene information of the terminal, the environmental information of the terminal, and the perception information of the terminal.

[0674] or,

[0675] The status information of the network-side device includes at least one of the following: the energy consumption status of the network-side device, the power status of the network-side device, the environmental information of the network-side device, and the sensing information of the network-side device;

[0676] or,

[0677] The server's status information includes at least one of the following: the server's environmental information, and the server's perception information.

[0678] Optionally, the target AI model is a first AI model, and sending the eleventh instruction information to the first device includes:

[0679] The eleventh indication message is sent to the first device if at least one of the following conditions is met:

[0680] Terminal power-on;

[0681] The terminal performs an initial cell search;

[0682] The terminal performs initial cell selection;

[0683] The time taken for the terminal to perform the initial search using traditional methods reached the first duration;

[0684] The terminal did not remain logged into the new cell during the second time period.

[0685] The terminal performs cell reselection;

[0686] The terminal performs cell handover;

[0687] The timer used to trigger the prediction timed out;

[0688] Before random access is triggered;

[0689] Before the initial access is triggered;

[0690] Beam failure detected;

[0691] Wireless link failure detected.

[0692] Optionally, the target AI model is a second AI model, and sending the eleventh instruction information to the first device includes:

[0693] The eleventh indication message is sent to the first device if at least one of the following conditions is met:

[0694] Terminal power-on;

[0695] The terminal performs an initial cell search;

[0696] The terminal performs initial cell selection;

[0697] The time taken for the terminal to perform the initial search using traditional methods exceeds the second search duration;

[0698] The terminal did not remain logged into the new cell during the third time period;

[0699] The terminal performs cell reselection;

[0700] The terminal performs cell handover;

[0701] The timer used to trigger the prediction timed out;

[0702] Before random access is triggered;

[0703] Before the initial access is triggered;

[0704] Beam failure detected;

[0705] Wireless link failure detected;

[0706] The power consumption of network-side devices exceeds the first threshold;

[0707] The terminal's energy consumption exceeds the second threshold;

[0708] The terminal's battery level is below the third threshold.

[0709] Optionally, the method further includes:

[0710] The second device receives the metrics of the target AI model from the first device;

[0711] or,

[0712] The second device sends the metrics of the target AI model to the first device;

[0713] The metrics of the target AI model include at least one of the following:

[0714] The complexity of the target AI model;

[0715] The latency predicted by the target AI model;

[0716] The success rate of the target AI model's predictions;

[0717] The reliability of the results output by the target AI model.

[0718] Optionally, the triggering type for training the target AI model includes at least one of the following: conditional or event triggering, periodic triggering, and semi-static triggering.

[0719] Optionally, the conditions or events that trigger the training of the target AI model include at least one of the following:

[0720] The configuration information for the first transmission has changed;

[0721] The configuration information for the second transmission has changed;

[0722] The activation or deactivation method of the first transmission changes;

[0723] The target AI model failed to predict;

[0724] The target AI model fails to make predictions N times consecutively, where N is a positive integer;

[0725] The number of times the target AI model failed to predict reached the fourth threshold;

[0726] The target AI model was used for prediction;

[0727] The terminal reselects to a new cell.

[0728] The tracking area of ​​the terminal has changed;

[0729] The environment in which the terminal is located has changed;

[0730] The second transmission is different from the first transmission.

[0731] Optionally, the triggering conditions for sending or receiving the second or third input information include at least one of the following:

[0732] Terminal resides in the community;

[0733] The terminal selects a cell for the first time;

[0734] Terminal reselects cell;

[0735] The terminal enters RRC connection state;

[0736] The terminal has been in an inactive state for four consecutive hours.

[0737] Optionally, the criteria for determining whether the first AI model has completed training include at least one of the following:

[0738] The loss function used for training the first AI model satisfies the first preset condition;

[0739] When the output of the first AI model indicates that the seventh transmission is activated, the measurement result obtained by the terminal based on the seventh transmission satisfies the second preset condition.

[0740] If the output of the first AI model indicates that the seventh transmission is activated, the probability that the terminal successfully detects the seventh transmission after the seventh transmission is activated is greater than or equal to the third threshold.

[0741] If the output of the first AI model indicates that the seventh transmission is activated, the terminal detects that the duration of the seventh transmission is less than or equal to the fourth threshold after the seventh transmission is activated.

[0742] When the output of the first AI model indicates that the seventh transmission is activated, the probability that the terminal successfully accesses the network based on the seventh transmission is greater than or equal to the fifth threshold.

[0743] If the output of the first AI model indicates that the seventh transmission is not activated, the probability that the terminal successfully accesses the network based on the eighth transmission is greater than or equal to the sixth threshold.

[0744] When the output of the first AI model indicates that the seventh transmission is activated, the probability or frequency of the terminal selecting the seventh transmission for random access is greater than or equal to the seventh threshold.

[0745] When the output of the first AI model indicates that the seventh transmission is activated, the probability or frequency of the terminal selecting the eighth transmission for random access is greater than or equal to the eighth threshold.

[0746] The number of training iterations for the first AI model has reached a first preset value;

[0747] The number of iterations for fine-tuning the first AI model reaches the second preset value.

[0748] Optionally, the criteria for determining whether the training of the second AI model is complete include at least one of the following:

[0749] The loss function used for training the second AI model satisfies the third preset condition;

[0750] If the result output by the second AI model indicates that the ninth transmission should not be activated, the measurement result obtained by the terminal based on the ninth transmission satisfies the fourth preset condition.

[0751] If the output of the second AI model indicates that the ninth transmission should not be activated, the probability that the terminal detects the ninth transmission is greater than or equal to the ninth threshold.

[0752] If the result output by the second AI model indicates that the ninth transmission should not be activated, the terminal detects that the duration of the ninth transmission is less than or equal to the tenth threshold.

[0753] If the output of the second AI model indicates that the ninth transmission should not be activated, the probability that the terminal successfully accesses the network based on the ninth transmission is greater than or equal to the eleventh threshold.

[0754] When the output of the second AI model indicates that the ninth transmission should be activated, the probability that the terminal will successfully access the network based on the tenth transmission is greater than or equal to the twelfth threshold.

[0755] If the output of the second AI model indicates that the ninth transmission should not be activated, the probability or frequency of the terminal selecting the ninth transmission for random access is greater than or equal to the thirteenth threshold.

[0756] When the output of the second AI model indicates that the ninth transmission should be activated, the probability or frequency of the terminal selecting the tenth transmission for random access is greater than or equal to the fourteenth threshold.

[0757] The second AI model has been trained a third preset number of times;

[0758] The second AI model has reached the fourth preset number of iterations for fine-tuning.

[0759] Optionally, if the target AI model is trained by the second device, the first information of the target AI model is determined according to the type of the second device;

[0760] The first information includes at least one of the following: model information of the target AI model, input information for training the target AI model, label information for training the target AI model, and execution method for training the target AI model.

[0761] Optionally, the triggering conditions for updating or retraining the target AI model include at least one of the following:

[0762] The configuration information for the first transmission has changed;

[0763] The configuration information for the second transmission has changed;

[0764] The activation or deactivation method of the first transmission changes;

[0765] The terminal moves to a new cell, a new tracking area, or a new geographical location;

[0766] The change in the terminal's moving speed is greater than or equal to a fifth preset value, or the rate of change in the terminal's moving speed is greater than or equal to a sixth preset value.

[0767] It has been five hours since the last model update or retraining.

[0768] Timeout for a timer used to trigger model updates or retraining;

[0769] M consecutive model supervisions have occurred or M model supervisions have been triggered, where M is a positive integer;

[0770] The target AI model failed to predict;

[0771] The target AI model fails to predict K times consecutively, where K is a positive integer;

[0772] The number of times the target AI model failed to predict reached the fifth threshold;

[0773] The target AI model was used for prediction;

[0774] The environment in which the terminal is located has changed.

[0775] Optionally, the configuration information for supervising the target AI model includes at least one of the following:

[0776] Identification of AI models that require model supervision;

[0777] The cycle of model supervision;

[0778] The duration of model supervision;

[0779] Information related to the detection window in model supervision;

[0780] Triggering conditions for model supervision;

[0781] Metrics for model supervision.

[0782] Optionally, the triggering conditions for the supervision of the target AI model include at least one of the following:

[0783] The target AI model does not meet the supervision index, or the target AI model does not meet the fifth preset condition, or the duration of the target AI model not meeting the supervision index reaches the sixth duration, or the duration of the target AI model not meeting the supervision index reaches the sixth duration.

[0784] The target result of the target AI model does not meet the sixth preset condition, or the duration for which the target result of the target AI model does not meet the sixth preset condition reaches the seventh duration;

[0785] The target AI model does not meet at least one of its metrics, or at least one of its metrics does not meet the seventh preset condition.

[0786] Optionally, the metrics for supervising the target AI model include at least one of the following:

[0787] Error information or accuracy information between the prediction results and actual results of the target AI model;

[0788] Performance metrics of a communication system;

[0789] The model-related information of the target AI model.

[0790] Optionally, the method further includes at least one of the following:

[0791] The second device sends information about its AI-related capabilities.

[0792] The second device determines the AI-related capability information of the first device;

[0793] The AI-related capability information is used to indicate at least one of the following:

[0794] It may or may not have the ability to train an AI model for predicting the activation or deactivation of a target.

[0795] It may or may not have the ability to predict the activation or deactivation of target transmission through AI models;

[0796] It may or may not have the ability to send first auxiliary information, which is used to predict the activation or deactivation of the target transmission through an AI model;

[0797] It may or may not have the ability to send second auxiliary information, which is used to train an AI model for predicting the activation or deactivation of the target transmission.

[0798] It should be noted that the implementation method of this method can be found in [reference needed]. Figure 5 The relevant descriptions of the embodiments shown are not repeated here.

[0799] It should be noted that the transmission control method provided in this application can be executed by a transmission control device. This application uses the example of a transmission control device executing the transmission control method to illustrate the transmission control device provided in this application.

[0800] This application provides a transmission control device. As an example, the transmission control device may be a communication device or a component within a communication device, such as a chip. The communication device may be a terminal, a network-side device, or a server, etc. Exemplarily, the terminal may include, but is not limited to, the type of terminal 11 listed above, and the network-side device may include, but is not limited to, the type of network-side device 12 listed above. This application does not impose specific limitations.

[0801] The transmission control device includes a receiving module, a transmitting module, and a processing module. These modules can be implemented in software or hardware. When implemented in hardware, the processing module can be implemented by a processor. For example, the processor can include general-purpose processors, special-purpose processors, such as a Central Processing Unit (CPU), microprocessor, Digital Signal Processor (DSP), Artificial Intelligence (AI) processor, Graphics Processing Unit (GPU), Application Specific Integrated Circuit (ASIC), Network Processor (NP), Field Programmable Gate Array (FPGA), or other programmable logic devices, gate circuits, transistors, discrete hardware components, etc. The receiving and transmitting modules can be implemented by a communication interface, which can include one or more of the following: transceiver, pins, circuits, bus, radio frequency unit, etc.

[0802] For details, see Figure 7 When the transmission control device is the first device or a component of the first device, the transmission control device 700 includes a processing module 701 for determining the target result based on the target artificial intelligence (AI) model.

[0803] The target AI model includes a first AI model or a second AI model, and the target result includes a first result determined based on the first AI model or a second result determined based on the second AI model.

[0804] The first result is used to indicate at least one of the following;

[0805] Activate or deactivate the first transmission;

[0806] Sending an activation signal or not sending an activation signal, the activation signal being used to activate or request activation of the first transmission;

[0807] The number of first transmissions that need to be activated;

[0808] The range of the first transmission to be activated;

[0809] The second result is used to indicate at least one of the following:

[0810] Deactivate or deactivate the first transmission;

[0811] Send a deactivation signal or not send a deactivation signal, the deactivation signal being used to deactivate or request deactivation of the first transmission;

[0812] The number of first transfers that need to be deactivated;

[0813] The range of the first transmission that needs to be deactivated.

[0814] Optionally, the processing module is specifically used for:

[0815] The target result is determined based on the first input information and the target AI model;

[0816] The first input information includes at least one of the following:

[0817] Time information;

[0818] Terminal status information;

[0819] Status information of network-side devices;

[0820] Server status information;

[0821] The signal strength and signal quality obtained by the terminal from measuring the reference signal associated with the second transmission, or the value determined based on the signal strength and signal quality obtained by the terminal from measuring the reference signal associated with the second transmission;

[0822] The value determined by the terminal based on at least one of the signal strength and signal quality measured by the second transmission, or based on at least one of the signal strength and signal quality measured by the terminal based on the second transmission;

[0823] The number of times the terminal failed to access the physical random access channel PRACH corresponding to the third transmission or the number of times it failed to receive the access response message.

[0824] The number of PRACH retransmissions performed by the terminal on the PRACH resources associated with the third transport;

[0825] The first indication information is used to indicate whether the terminal fails to access the PRACH resource associated with the third transmission after attempting two-step random access and then falling back to four-step random access.

[0826] The second indication information is used to indicate whether the power of the terminal transmitting the PRACH signal on the third transmission associated PRACH resource is greater than or equal to the first threshold.

[0827] The third indication information is used to indicate at least one of the following: whether the terminal receives a first random access response (RAR) message, the number of first RAR messages received within a first time period, and the number of first RAR messages received within the first time period being greater than or equal to a second threshold; wherein, the first RAR message is a RAR message whose included preamble identifier is not a preamble identifier sent by the terminal on the third transmission associated PRACH resource.

[0828] The fourth indication information is used to indicate whether the number of times the terminal sends the activation signal is less than or equal to the first number, or the fourth indication information is used to indicate whether the number of times the terminal sends the deactivation signal is less than or equal to the second number;

[0829] The fifth indication information is used to indicate whether the timing advance TA for activating signal transmission is valid, or the fifth indication information is used to indicate whether the timing advance TA for deactivating signal transmission is valid;

[0830] The sixth indication information is used to indicate whether the interval between the current time and the time of the previous activation signal is greater than or equal to the first interval, or the sixth indication information is used to indicate whether the interval between the current time and the time of the previous deactivation signal is greater than or equal to the second interval;

[0831] The seventh indication information is used to indicate whether the interval between the time of the previous activation or deactivation of the first transmission and the current time is greater than or equal to the third interval;

[0832] The eighth indication information is used to indicate whether the terminal has sent an activation signal for the fourth transmission, or the eighth indication information is used to indicate whether the terminal has sent a deactivation signal for the fourth transmission.

[0833] The ninth indication information is used to indicate whether the fifth transmission has been activated, or the ninth indication information is used to indicate whether the fifth transmission has been deactivated;

[0834] The tenth indication information is used to indicate whether the terminal has detected the sixth transmission;

[0835] Information on sudden events;

[0836] The frequency domain characteristics of the first transmission;

[0837] The temporal characteristics of the first transmission;

[0838] The spatial characteristics of the first transmission;

[0839] The second transmission is different from the first transmission, and the third transmission is a transmission associated with PRACH.

[0840] Optionally, the status information of the terminal includes at least one of the following: the location information of the terminal, the distribution information of the terminal, the direction of movement of the terminal, the speed of movement of the terminal, the energy consumption status of the terminal, the battery status of the terminal, the network scene information of the terminal, the environmental information of the terminal, and the perception information of the terminal.

[0841] or,

[0842] The status information of the network-side device includes at least one of the following: the energy consumption status of the network-side device, the power status of the network-side device, the environmental information of the network-side device, and the sensing information of the network-side device;

[0843] or,

[0844] The server's status information includes at least one of the following: the server's environmental information, and the server's perception information.

[0845] Optionally, the triggering conditions for using the first AI model to make predictions include at least one of the following:

[0846] Terminal power-on;

[0847] The terminal performs an initial cell search;

[0848] The terminal performs initial cell selection;

[0849] The time taken for the terminal to perform the initial search using traditional methods reached the first duration;

[0850] The terminal did not remain logged into the new cell during the second time period.

[0851] The terminal performs cell reselection;

[0852] The terminal performs cell handover;

[0853] The timer used to trigger the prediction timed out;

[0854] Before random access is triggered;

[0855] Before the initial access is triggered;

[0856] Beam failure detected;

[0857] Wireless link failure detected;

[0858] Based on at least one piece of information from the input information of the first AI model, it is determined that the first AI model needs to be used for prediction.

[0859] Optionally, the triggering conditions for using the second AI model to make predictions include at least one of the following:

[0860] Terminal power-on;

[0861] The terminal performs an initial cell search;

[0862] The terminal performs initial cell selection;

[0863] The time taken for the terminal to perform the initial search using traditional methods exceeds the second search duration;

[0864] The terminal did not remain logged into the new cell during the third time period;

[0865] The terminal performs cell reselection;

[0866] The terminal performs cell handover;

[0867] The timer used to trigger the prediction timed out;

[0868] Before random access is triggered;

[0869] Before the initial access is triggered;

[0870] Beam failure detected;

[0871] Wireless link failure detected;

[0872] The power consumption of network-side devices exceeds the first threshold;

[0873] The terminal's energy consumption exceeds the second threshold;

[0874] The terminal's battery level is below the third threshold;

[0875] Based on at least one of the input information of the second AI model, it is determined that the second AI model needs to be used for prediction.

[0876] Optionally, the processing module is further configured to:

[0877] After determining the target result based on the target artificial intelligence (AI) model, a first operation is performed, which includes at least one of the following:

[0878] Send at least a portion of the input information of the target AI model and at least one of the target results;

[0879] The process reverts to using a non-AI method to determine whether to activate or deactivate the first transmission.

[0880] Trigger the switching of the target AI model;

[0881] Trigger the retraining of the target AI model;

[0882] This triggers the supervision of the target AI model.

[0883] Optionally, the fallback to determining whether to activate or deactivate the first transmission using a non-AI method includes:

[0884] If at least one of the following conditions is met, the process reverts to using a non-AI method to determine whether to activate or deactivate the first transmission;

[0885] The prediction was not successfully completed even after the prediction time using the target AI model exceeded the third time period;

[0886] The target AI model failed to make a prediction.

[0887] Optionally, the device further includes at least one of the following:

[0888] A receiving module is used to acquire the metrics of the target AI model;

[0889] A sending module is used to send the metrics of the target AI model;

[0890] The metrics of the target AI model include at least one of the following:

[0891] The complexity of the target AI model;

[0892] The latency predicted by the target AI model;

[0893] The success rate of the target AI model's predictions;

[0894] The reliability of the results output by the target AI model.

[0895] Optionally, the processing module is further configured to train at least a portion of the AI ​​model in the target AI model;

[0896] or,

[0897] The device further includes a receiving module for receiving at least a portion of the AI ​​model in the target AI model.

[0898] Optionally, the triggering type for training the target AI model includes at least one of the following: conditional or event triggering, periodic triggering, and semi-static triggering.

[0899] Optionally, the conditions or events that trigger the training of the target AI model include at least one of the following:

[0900] The configuration information of the first transmission has changed;

[0901] The configuration information for the second transmission has changed;

[0902] The activation or deactivation method of the first transmission changes;

[0903] The target AI model failed to predict;

[0904] The target AI model fails to make predictions N times consecutively, where N is a positive integer;

[0905] The number of times the target AI model failed to predict reached the fourth threshold;

[0906] The target AI model was used for prediction;

[0907] The terminal reselects to a new cell.

[0908] The tracking area of ​​the terminal has changed;

[0909] The environment in which the terminal is located has changed;

[0910] The second transmission is different from the first transmission.

[0911] Optionally, the configuration information of the first transmission includes at least one of the following: the number of the first transmissions, the range of the first transmissions, the beam configuration corresponding to the first transmissions, the transmission power of the first transmissions, and the period of the first transmissions;

[0912] or,

[0913] The configuration information of the second transmission includes at least one of the following: the number of second transmissions, the range of the second transmission, the beam configuration corresponding to the second transmission, the transmission power of the second transmission, and the period of the second transmission.

[0914] Optionally, the configuration information for periodic triggering includes at least one of the following: the starting point of periodic model training, the interval of periodic model training, the number of model training sessions within a period, and the duration of model training within a period.

[0915] Optionally, the semi-static triggering includes at least one of the following:

[0916] The semi-static triggering configuration information is sent and / or activated based on specific conditions or events.

[0917] The configuration information for the semi-static trigger is configured via Radio Resource Control (RRC), and / or the semi-static training of the model is activated or deactivated via Physical Control Information.

[0918] Optionally, the device further includes:

[0919] A receiving module is used to receive second input information, which is used for training the target AI model;

[0920] or,

[0921] The sending module is used to send third input information, which is used for training the target AI model.

[0922] Optionally, the receiving module is specifically used for:

[0923] The receiving network-side device sends second input information via at least one of the following: Media Access Control Unit (MAC CE); RRC message; Non-Access Stratum (NAS) message; User plane data; System Information Block (SIB); Physical Layer Signaling; Physical Downlink Shared Channel; MSG 2; MSG 4; MSG B;

[0924] or,

[0925] The sending module is specifically used for at least one of the following:

[0926] The third input information is sent to the network-side device via at least one of the following: MAC CE; RRC message; NAS message; user plane data; MSG 1; MSG A; MSG 3; physical uplink control channel; physical uplink shared channel; random access channel; uplink reference signal;

[0927] The third input information is sent to the server via the first interface message.

[0928] Optionally, the receiving module is specifically used for:

[0929] The first device receives second input information sent by the terminal via at least one of the following: MAC CE; RRC message; NAS message; user plane data; MSG 1; MSG A; MSG 3; physical uplink control channel; physical uplink shared channel; random access channel; uplink reference signal;

[0930] or,

[0931] The sending module is specifically used for at least one of the following:

[0932] The third input information is sent to the terminal via at least one of the following: MAC CE; RRC message; Layer NAS message; User plane data; DCI information; SIB; Physical layer signaling; Physical downlink shared channel; MSG 2; MSG 4; MSG B;

[0933] The first device sends the third input information to the server through the second interface message.

[0934] Optionally, the receiving module is specifically used for:

[0935] Receive third input information from at least one of the terminal and network-side devices.

[0936] Optionally, the triggering conditions for sending or receiving the second or third input information include at least one of the following:

[0937] Terminal resides in the community;

[0938] The terminal selects a cell for the first time;

[0939] Terminal reselects cell;

[0940] The terminal enters RRC connection state;

[0941] The terminal has been in an inactive state for four consecutive hours.

[0942] Optionally, the criteria for determining whether the first AI model has completed training include at least one of the following:

[0943] The loss function used for training the first AI model satisfies the first preset condition;

[0944] When the output of the first AI model indicates that the seventh transmission is activated, the measurement result obtained by the terminal based on the seventh transmission satisfies the second preset condition.

[0945] If the output of the first AI model indicates that the seventh transmission is activated, the probability that the terminal successfully detects the seventh transmission after the seventh transmission is activated is greater than or equal to the third threshold.

[0946] If the output of the first AI model indicates that the seventh transmission is activated, the terminal detects that the duration of the seventh transmission is less than or equal to the fourth threshold after the seventh transmission is activated.

[0947] When the output of the first AI model indicates that the seventh transmission is activated, the probability that the terminal successfully accesses the network based on the seventh transmission is greater than or equal to the fifth threshold.

[0948] If the output of the first AI model indicates that the seventh transmission is not activated, the probability that the terminal successfully accesses the network based on the eighth transmission is greater than or equal to the sixth threshold.

[0949] When the output of the first AI model indicates that the seventh transmission is activated, the probability or frequency of the terminal selecting the seventh transmission for random access is greater than or equal to the seventh threshold.

[0950] When the output of the first AI model indicates that the seventh transmission is activated, the probability or frequency of the terminal selecting the eighth transmission for random access is greater than or equal to the eighth threshold.

[0951] The number of training iterations for the first AI model has reached a first preset value;

[0952] The number of iterations for fine-tuning the first AI model reaches the second preset value.

[0953] Optionally, the criteria for determining whether the training of the second AI model is complete include at least one of the following:

[0954] The loss function used for training the second AI model satisfies the third preset condition;

[0955] If the result output by the second AI model indicates that the ninth transmission should not be activated, the measurement result obtained by the terminal based on the ninth transmission satisfies the fourth preset condition.

[0956] If the output of the second AI model indicates that the ninth transmission should not be activated, the probability that the terminal detects the ninth transmission is greater than or equal to the ninth threshold.

[0957] If the result output by the second AI model indicates that the ninth transmission should not be activated, the terminal detects that the duration of the ninth transmission is less than or equal to the tenth threshold.

[0958] If the output of the second AI model indicates that the ninth transmission should not be activated, the probability that the terminal successfully accesses the network based on the ninth transmission is greater than or equal to the eleventh threshold.

[0959] When the output of the second AI model indicates that the ninth transmission should be activated, the probability that the terminal will successfully access the network based on the tenth transmission is greater than or equal to the twelfth threshold.

[0960] If the output of the second AI model indicates that the ninth transmission should not be activated, the probability or frequency of the terminal selecting the ninth transmission for random access is greater than or equal to the thirteenth threshold.

[0961] When the output of the second AI model indicates that the ninth transmission should be activated, the probability or frequency of the terminal selecting the tenth transmission for random access is greater than or equal to the fourteenth threshold.

[0962] The second AI model has been trained a third preset number of times;

[0963] The second AI model has reached the fourth preset number of iterations for fine-tuning.

[0964] Optionally, if the target AI model is trained by the first device, the first information of the target AI model is determined according to the type of the first device;

[0965] The first information includes at least one of the following: model information of the target AI model, input information for training the target AI model, label information for training the target AI model, and execution method for training the target AI model.

[0966] Optionally, the triggering conditions for updating or retraining the target AI model include at least one of the following:

[0967] The configuration information of the first transmission has changed;

[0968] The configuration information for the second transmission has changed;

[0969] The activation or deactivation method of the first transmission changes;

[0970] The terminal moves to a new cell, a new tracking area, or a new geographical location;

[0971] The change in the terminal's moving speed is greater than or equal to a fifth preset value, or the rate of change in the terminal's moving speed is greater than or equal to a sixth preset value.

[0972] It has been five hours since the last model update or retraining.

[0973] Timeout for a timer used to trigger model updates or retraining;

[0974] M consecutive model supervisions have occurred or M model supervisions have been triggered, where M is a positive integer;

[0975] The target AI model failed to predict;

[0976] The target AI model fails to predict K times consecutively, where K is a positive integer;

[0977] The number of times the target AI model failed to predict reached the fifth threshold;

[0978] The target AI model was used for prediction;

[0979] The environment in which the terminal is located has changed.

[0980] Optionally, the processing module is further configured to obtain the model supervision results of the target AI model;

[0981] or,

[0982] The device also includes a sending module for sending the model supervision results of the target AI model.

[0983] Optionally, the processing module is specifically used for:

[0984] The target AI model is subjected to model supervision to obtain the model supervision results of the target AI model;

[0985] or,

[0986] Receive the model supervision results of the target AI model.

[0987] Optionally, the configuration information for supervising the target AI model includes at least one of the following:

[0988] Identification of AI models that require model supervision;

[0989] The cycle of model supervision;

[0990] The duration of model supervision;

[0991] Information related to the detection window in model supervision;

[0992] Triggering conditions for model supervision;

[0993] Metrics for model supervision.

[0994] Optionally, the triggering conditions for the supervision of the target AI model include at least one of the following:

[0995] The target AI model does not meet the supervision index, or the target AI model does not meet the fifth preset condition, or the duration of the target AI model not meeting the supervision index reaches the sixth duration, or the duration of the target AI model not meeting the supervision index reaches the sixth duration.

[0996] The target result of the target AI model does not meet the sixth preset condition, or the duration for which the target result of the target AI model does not meet the sixth preset condition reaches the seventh duration;

[0997] The target AI model does not meet at least one of its metrics, or at least one of its metrics does not meet the seventh preset condition.

[0998] Optionally, the metrics for supervising the target AI model include at least one of the following:

[0999] Error information or accuracy information between the prediction results and actual results of the target AI model;

[1000] Performance metrics of a communication system;

[1001] The model-related information of the target AI model.

[1002] Optionally, the device further includes a sending module for sending AI-related capability information of the first device;

[1003] or,

[1004] The processing module is also used to determine the AI-related capability information of the second device;

[1005] The AI-related capability information is used to indicate at least one of the following:

[1006] It may or may not have the ability to train an AI model for predicting the activation or deactivation of a target.

[1007] It may or may not have the ability to predict the activation or deactivation of target transmission through AI models;

[1008] It may or may not have the ability to send first auxiliary information, which is used to predict the activation or deactivation of the target transmission through an AI model;

[1009] It may or may not have the ability to send second auxiliary information, which is used to train an AI model for predicting the activation or deactivation of the target transmission.

[1010] Optionally, the processing module is specifically used for:

[1011] The AI-related capability information of the second device is determined based on at least one of the following:

[1012] The equipment type of the second device;

[1013] AI-related capability information indicated by reference signals;

[1014] The control information sent by the second device carries AI-related capability information;

[1015] The AI-related capability information carried in the RRC signaling sent by the second device;

[1016] The AI-related capability information carried in the interface messages between the first device and the second device.

[1017] Optionally, the device further includes:

[1018] The sending module is used to send the target result to the terminal or network-side device.

[1019] The transmission control device provided in this application embodiment can achieve... Figure 5 The various processes implemented in the method embodiments achieve the same technical effect, and will not be described again here to avoid repetition.

[1020] See Figure 8When the transmission control device is a second device or a component of the second device, the transmission control device 800 includes a processing module 801 for performing a second operation, the second operation including at least one of the following:

[1021] At least a portion of the AI ​​model in the training target AI model;

[1022] Send at least a portion of the AI ​​model from the target AI model to the first device;

[1023] Send first input information to the first device, the first input information being used for prediction by the target AI model;

[1024] Send second input information to the first device, the second input information being used for training the target AI model;

[1025] Receive third input information from the first device, the third input information being used for training the target AI model;

[1026] Receive the target result sent by the first device, wherein the target result is the result determined according to the target AI model;

[1027] Receive the supervision results of the target AI model sent by the first device, or send the supervision results of the target AI model to the first device;

[1028] The target AI model is subjected to model supervision to obtain the supervision results of the target AI model;

[1029] Send an eleventh instruction message to the first device, the eleventh instruction message being used to trigger the first device to train the target AI model;

[1030] Send a twelfth instruction message to the first device, the twelfth instruction message being used to trigger the first device to make a prediction based on the target AI model;

[1031] The target AI model includes either a first AI model or a second AI model;

[1032] The first AI model is used to predict at least one of the following:

[1033] Activate or deactivate the target transfer;

[1034] Sending an activation signal or not sending an activation signal, the activation signal being used to activate or request activation of the target transmission;

[1035] The number of target transmissions that need to be activated;

[1036] The range of target transmissions that need to be activated;

[1037] The second AI model is used to predict at least one of the following;

[1038] Deactivate or deactivate the target transfer;

[1039] Send a deactivation signal or not send a deactivation signal, wherein the deactivation signal is used to deactivate or request deactivation of the target transmission;

[1040] The number of target transfers that need to be deactivated;

[1041] The range of the target transmission that needs to be deactivated.

[1042] Optionally, the processing module is specifically used for:

[1043] Train at least a portion of the AI ​​model in the target AI model based on the target input information;

[1044] The target input information includes at least one of the following:

[1045] Time information;

[1046] Terminal status information;

[1047] Status information of network-side devices;

[1048] Server status information;

[1049] The frequency domain characteristics of the eleventh transmission;

[1050] The temporal characteristics of the eleventh transmission;

[1051] The spatial characteristics of the eleventh transmission;

[1052] The signal strength and signal quality obtained by the terminal measuring the reference signal of the twelfth transmission association, or the value determined based on the signal strength and signal quality obtained by the terminal measuring the reference signal of the twelfth transmission association;

[1053] The value determined by the terminal based on at least one of the signal strength and signal quality measured by the twelfth transmission, or based on at least one of the signal strength and signal quality measured by the terminal based on the twelfth transmission;

[1054] The number of times the terminal failed to access the physical random access channel PRACH corresponding to the thirteenth transmission or the number of times it failed to receive the access response message.

[1055] The number of PRACH retransmissions performed by the terminal on the PRACH resource associated with the thirteenth transmission;

[1056] The thirteenth instruction information is used to indicate whether the terminal fails to access the PRACH resource associated with the thirteenth transmission after attempting two steps of random access and then falling back to four steps of random access.

[1057] The fourteenth indication information is used to indicate whether the power of the terminal transmitting the PRACH signal on the PRACH resource associated with the thirteenth transmission is greater than or equal to the first threshold.

[1058] The fifteenth indication information is used to indicate at least one of the following: whether the terminal receives a second random access response (RAR) message, the number of second RAR messages received within a first time period, and the number of second RAR messages received within the first time period being greater than or equal to a second threshold; wherein the second RAR message is a RAR message whose included preamble identifier is not a preamble identifier sent by the terminal on the PRACH resource associated with the thirteenth transmission.

[1059] The sixteenth indication information is used to indicate whether the number of times the terminal sends an activation signal is less than or equal to the first number, or the sixteenth indication information is used to indicate whether the number of times the terminal sends a deactivation signal is less than or equal to the second number;

[1060] The seventeenth indication information is used to indicate whether the timing advance TA for activating signal transmission is valid, or the seventeenth indication information is used to indicate whether the timing advance TA for deactivating signal transmission is valid;

[1061] The eighteenth indication information is used to indicate whether the interval between the current time and the time of the previous activation signal is greater than or equal to the first interval, or the eighteenth indication information is used to indicate whether the interval between the current time and the time of the previous deactivation signal is greater than or equal to the second interval.

[1062] The nineteenth instruction information is used to indicate whether the interval between the time of the previous activation or deactivation of the eleventh transmission and the current time is greater than or equal to the third interval;

[1063] The twentieth indication information is used to indicate whether the terminal has sent the fourteenth transmission activation signal, or whether the twentieth indication information is used to indicate whether the terminal has sent the fourteenth transmission deactivation signal.

[1064] The 21st indication information is used to indicate whether the 15th transmission has been activated, or whether the 21st indication information has been deactivated.

[1065] The twenty-second instruction message is used to indicate whether the terminal has detected the sixteenth transmission;

[1066] Information on sudden events;

[1067] The twelfth transmission is different from the eleventh transmission, and the thirteenth transmission is a transmission associated with PRACH.

[1068] Optionally, the status information of the terminal includes at least one of the following: the location information of the terminal, the distribution information of the terminal, the direction of movement of the terminal, the speed of movement of the terminal, the energy consumption status of the terminal, the battery status of the terminal, the network scene information of the terminal, the environmental information of the terminal, and the perception information of the terminal.

[1069] or,

[1070] The status information of the network-side device includes at least one of the following: the energy consumption status of the network-side device, the power status of the network-side device, the environmental information of the network-side device, and the sensing information of the network-side device;

[1071] or,

[1072] The server's status information includes at least one of the following: the server's environmental information, and the server's perception information.

[1073] Optionally, the target AI model is a first AI model, and sending the eleventh instruction information to the first device includes:

[1074] The eleventh indication message is sent to the first device if at least one of the following conditions is met:

[1075] Terminal power-on;

[1076] The terminal performs an initial cell search;

[1077] The terminal performs initial cell selection;

[1078] The time taken for the terminal to perform the initial search using traditional methods reached the first duration;

[1079] The terminal did not remain logged into the new cell during the second time period.

[1080] The terminal performs cell reselection;

[1081] The terminal performs cell handover;

[1082] The timer used to trigger the prediction timed out;

[1083] Before random access is triggered;

[1084] Before the initial access is triggered;

[1085] Beam failure detected;

[1086] Wireless link failure detected.

[1087] Optionally, the target AI model is a second AI model, and sending the eleventh instruction information to the first device includes:

[1088] The eleventh indication message is sent to the first device if at least one of the following conditions is met:

[1089] Terminal power-on;

[1090] The terminal performs an initial cell search;

[1091] The terminal performs initial cell selection;

[1092] The time taken for the terminal to perform the initial search using traditional methods exceeds the second search duration;

[1093] The terminal did not remain logged into the new cell during the third time period;

[1094] The terminal performs cell reselection;

[1095] The terminal performs cell handover;

[1096] The timer used to trigger the prediction timed out;

[1097] Before random access is triggered;

[1098] Before the initial access is triggered;

[1099] Beam failure detected;

[1100] Wireless link failure detected;

[1101] The power consumption of network-side devices exceeds the first threshold;

[1102] The terminal's energy consumption exceeds the second threshold;

[1103] The terminal's battery level is below the third threshold.

[1104] Optionally, the device further includes:

[1105] A receiving module is used to receive the metrics of the target AI model from the first device;

[1106] or,

[1107] The sending module is used to send the metrics of the target AI model to the first device;

[1108] The metrics of the target AI model include at least one of the following:

[1109] The complexity of the target AI model;

[1110] The latency predicted by the target AI model;

[1111] The success rate of the target AI model's predictions;

[1112] The reliability of the results output by the target AI model.

[1113] Optionally, the triggering type for training the target AI model includes at least one of the following: conditional or event triggering, periodic triggering, and semi-static triggering.

[1114] Optionally, the conditions or events that trigger the training of the target AI model include at least one of the following:

[1115] The configuration information for the first transmission has changed;

[1116] The configuration information for the second transmission has changed;

[1117] The activation or deactivation method of the first transmission changes;

[1118] The target AI model failed to predict;

[1119] The target AI model fails to make predictions N times consecutively, where N is a positive integer;

[1120] The number of times the target AI model failed to predict reached the fourth threshold;

[1121] The target AI model was used for prediction;

[1122] The terminal reselects to a new cell.

[1123] The tracking area of ​​the terminal has changed;

[1124] The environment in which the terminal is located has changed;

[1125] The second transmission is different from the first transmission.

[1126] Optionally, the triggering conditions for sending or receiving the second or third input information include at least one of the following:

[1127] Terminal resides in the community;

[1128] The terminal selects a cell for the first time;

[1129] Terminal reselects cell;

[1130] The terminal enters RRC connection state;

[1131] The terminal has been in an inactive state for four consecutive hours.

[1132] Optionally, the criteria for determining whether the first AI model has completed training include at least one of the following:

[1133] The loss function used for training the first AI model satisfies the first preset condition;

[1134] When the output of the first AI model indicates that the seventh transmission is activated, the measurement result obtained by the terminal based on the seventh transmission satisfies the second preset condition.

[1135] If the output of the first AI model indicates that the seventh transmission is activated, the probability that the terminal successfully detects the seventh transmission after the seventh transmission is activated is greater than or equal to the third threshold.

[1136] If the output of the first AI model indicates that the seventh transmission is activated, the terminal detects that the duration of the seventh transmission is less than or equal to the fourth threshold after the seventh transmission is activated.

[1137] When the output of the first AI model indicates that the seventh transmission is activated, the probability that the terminal successfully accesses the network based on the seventh transmission is greater than or equal to the fifth threshold.

[1138] If the output of the first AI model indicates that the seventh transmission is not activated, the probability that the terminal successfully accesses the network based on the eighth transmission is greater than or equal to the sixth threshold.

[1139] When the output of the first AI model indicates that the seventh transmission is activated, the probability or frequency of the terminal selecting the seventh transmission for random access is greater than or equal to the seventh threshold.

[1140] When the output of the first AI model indicates that the seventh transmission is activated, the probability or frequency of the terminal selecting the eighth transmission for random access is greater than or equal to the eighth threshold.

[1141] The number of training iterations for the first AI model has reached a first preset value;

[1142] The number of iterations for fine-tuning the first AI model reaches the second preset value.

[1143] Optionally, the criteria for determining whether the training of the second AI model is complete include at least one of the following:

[1144] The loss function used for training the second AI model satisfies the third preset condition;

[1145] If the result output by the second AI model indicates that the ninth transmission should not be activated, the measurement result obtained by the terminal based on the ninth transmission satisfies the fourth preset condition.

[1146] If the output of the second AI model indicates that the ninth transmission should not be activated, the probability that the terminal detects the ninth transmission is greater than or equal to the ninth threshold.

[1147] If the result output by the second AI model indicates that the ninth transmission should not be activated, the terminal detects that the duration of the ninth transmission is less than or equal to the tenth threshold.

[1148] If the output of the second AI model indicates that the ninth transmission should not be activated, the probability that the terminal successfully accesses the network based on the ninth transmission is greater than or equal to the eleventh threshold.

[1149] When the output of the second AI model indicates that the ninth transmission should be activated, the probability that the terminal will successfully access the network based on the tenth transmission is greater than or equal to the twelfth threshold.

[1150] If the output of the second AI model indicates that the ninth transmission should not be activated, the probability or frequency of the terminal selecting the ninth transmission for random access is greater than or equal to the thirteenth threshold.

[1151] When the output of the second AI model indicates that the ninth transmission should be activated, the probability or frequency of the terminal selecting the tenth transmission for random access is greater than or equal to the fourteenth threshold.

[1152] The second AI model has been trained a third preset number of times;

[1153] The second AI model has reached the fourth preset number of iterations for fine-tuning.

[1154] Optionally, if the target AI model is trained by the second device, the first information of the target AI model is determined according to the type of the second device;

[1155] The first information includes at least one of the following: model information of the target AI model, input information for training the target AI model, label information for training the target AI model, and execution method for training the target AI model.

[1156] Optionally, the triggering conditions for updating or retraining the target AI model include at least one of the following:

[1157] The configuration information for the first transmission has changed;

[1158] The configuration information for the second transmission has changed;

[1159] The activation or deactivation method of the first transmission changes;

[1160] The terminal moves to a new cell, a new tracking area, or a new geographical location;

[1161] The change in the terminal's moving speed is greater than or equal to a fifth preset value, or the rate of change in the terminal's moving speed is greater than or equal to a sixth preset value.

[1162] It has been five hours since the last model update or retraining.

[1163] Timeout for a timer used to trigger model updates or retraining;

[1164] M consecutive model supervisions have occurred or M model supervisions have been triggered, where M is a positive integer;

[1165] The target AI model failed to predict;

[1166] The target AI model fails to predict K times consecutively, where K is a positive integer;

[1167] The number of times the target AI model failed to predict reached the fifth threshold;

[1168] The target AI model was used for prediction;

[1169] The environment in which the terminal is located has changed.

[1170] Optionally, the configuration information for supervising the target AI model includes at least one of the following:

[1171] Identification of AI models that require model supervision;

[1172] The cycle of model supervision;

[1173] The duration of model supervision;

[1174] Information related to the detection window in model supervision;

[1175] Triggering conditions for model supervision;

[1176] Metrics for model supervision.

[1177] Optionally, the triggering conditions for the supervision of the target AI model include at least one of the following:

[1178] The target AI model does not meet the supervision index, or the target AI model does not meet the fifth preset condition, or the duration of the target AI model not meeting the supervision index reaches the sixth duration, or the duration of the target AI model not meeting the supervision index reaches the sixth duration.

[1179] The target result of the target AI model does not meet the sixth preset condition, or the duration for which the target result of the target AI model does not meet the sixth preset condition reaches the seventh duration;

[1180] The target AI model does not meet at least one of its metrics, or at least one of its metrics does not meet the seventh preset condition.

[1181] Optionally, the metrics for supervising the target AI model include at least one of the following:

[1182] Error information or accuracy information between the prediction results and actual results of the target AI model;

[1183] Performance metrics of a communication system;

[1184] The model-related information of the target AI model.

[1185] Optionally, the device further includes a sending module for sending AI-related capability information of the second device;

[1186] or,

[1187] The processing module is also used to determine the AI-related capability information of the first device;

[1188] The AI-related capability information is used to indicate at least one of the following:

[1189] It may or may not have the ability to train an AI model for predicting the activation or deactivation of a target.

[1190] It may or may not have the ability to predict the activation or deactivation of target transmission through AI models;

[1191] It may or may not have the ability to send first auxiliary information, which is used to predict the activation or deactivation of the target transmission through an AI model;

[1192] It may or may not have the ability to send second auxiliary information, which is used to train an AI model for predicting the activation or deactivation of the target transmission.

[1193] The transmission control device provided in this application embodiment can achieve... Figure 6 The various processes implemented in the method embodiments achieve the same technical effect, and will not be described again here to avoid repetition.

[1194] like Figure 9As shown, this application embodiment also provides a communication device 900, including a processor 901 and a memory 902. The memory 902 stores a program or instructions that can run on the processor 901. For example, when the communication device 900 is a first device, when the program or instructions are executed by the processor 901, they implement the various steps of the above-described first device-side transmission control method embodiment and achieve the same technical effect. When the communication device 900 is a second device, when the program or instructions are executed by the processor 901, they implement the various steps of the above-described second device-side transmission control method embodiment and achieve the same technical effect. To avoid repetition, this will not be repeated here.

[1195] This application embodiment also provides a terminal, including a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is used to run programs or instructions to implement, for example... Figure 5 or Figure 6 The steps in the method embodiment shown are illustrated. This terminal embodiment corresponds to the above-described terminal-side method embodiment. All implementation processes and methods of the above-described method embodiments can be applied to this terminal embodiment and achieve the same technical effect. The terminal can be... Figure 7 or Figure 8 The transmission control device shown. Specifically, Figure 10 A schematic diagram of the hardware structure of a terminal to implement an embodiment of this application.

[1196] The terminal 1000 includes, but is not limited to, at least some of the following components: radio frequency unit 1001, network module 1002, audio output unit 1003, input unit 1004, sensor 1005, display unit 1006, user input unit 1007, interface unit 1008, memory 1009, and processor 1010.

[1197] Those skilled in the art will understand that the terminal 1000 may also include a power supply (such as a battery) for supplying power to various components. The power supply can be logically connected to the processor 1010 through a power management system, thereby enabling functions such as managing charging, discharging, and power consumption through the power management system. Figure 10 The terminal structure shown does not constitute a limitation on the terminal. The terminal may include more or fewer components than shown, or combine certain components, or have different component arrangements, which will not be elaborated here.

[1198] It should be understood that, in this embodiment, the input unit 1004 may include a graphics processor 10041 and a microphone 10042. The graphics processor 10041 processes image data of still images or videos obtained by an image capture device (such as a camera) in video capture mode or image capture mode. The display unit 1006 may include a display panel 10061, which may be configured in the form of a liquid crystal display, an organic light-emitting diode, or the like. The user input unit 1007 includes a touch panel 10071 and at least one of other input devices 10072. The touch panel 10071 is also called a touch screen. The touch panel 10071 may include a touch detection device and a touch controller. Other input devices 10072 may include, but are not limited to, physical keyboards, function keys (such as volume control buttons, power buttons, etc.), trackballs, mice, and joysticks, which will not be described in detail here.

[1199] In this embodiment, after receiving downlink data from the network-side device, the radio frequency unit 1001 can transmit it to the processor 1010 for processing; in addition, the radio frequency unit 1001 can send uplink data to the network-side device. Typically, the radio frequency unit 1001 includes, but is not limited to, antennas, amplifiers, transceivers, couplers, low-noise amplifiers, duplexers, etc.

[1200] The memory 1009 can be used to store software programs or instructions, as well as various data. The memory 1009 may primarily include a first storage area for storing programs or instructions and a second storage area for storing data. The first storage area may store the operating system, application programs or instructions required for at least one function (such as sound playback, image playback, etc.). Furthermore, the memory 1009 may include volatile memory or non-volatile memory. The non-volatile memory may be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. Volatile memory can be random access memory (RAM), static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDRSDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM), and direct memory bus RAM (DRRAM). The memory 1009 in this embodiment includes, but is not limited to, these and any other suitable types of memory.

[1201] The processor 1010 may include one or more processing units; optionally, the processor 1010 integrates an application processor and a modem processor, wherein the application processor mainly handles operations involving the operating system, user interface, and applications, and the modem processor mainly handles wireless communication signals, such as a baseband processor. It is understood that the aforementioned modem processor may also not be integrated into the processor 1010.

[1202] The processor 1010 is used to determine the target result based on the target AI model.

[1203] The target AI model includes a first AI model or a second AI model, and the target result includes a first result determined based on the first AI model or a second result determined based on the second AI model.

[1204] The first result is used to indicate at least one of the following;

[1205] Activate or deactivate the first transmission;

[1206] Sending an activation signal or not sending an activation signal, the activation signal being used to activate or request activation of the first transmission;

[1207] The number of first transmissions that need to be activated;

[1208] The range of the first transmission to be activated;

[1209] The second result is used to indicate at least one of the following:

[1210] Deactivate or deactivate the first transmission;

[1211] Send a deactivation signal or not send a deactivation signal, the deactivation signal being used to deactivate or request deactivation of the first transmission;

[1212] The number of first transfers that need to be deactivated;

[1213] The range of the first transmission that needs to be deactivated;

[1214] or,

[1215] Processor 1010 is configured to perform a second operation, the second operation including at least one of the following:

[1216] At least a portion of the AI ​​model in the training target AI model;

[1217] Send at least a portion of the AI ​​model from the target AI model to the first device;

[1218] Send first input information to the first device, the first input information being used for prediction by the target AI model;

[1219] Send second input information to the first device, the second input information being used for training the target AI model;

[1220] Receive third input information from the first device, the third input information being used for training the target AI model;

[1221] Receive the target result sent by the first device, wherein the target result is the result determined according to the target AI model;

[1222] Receive the supervision results of the target AI model sent by the first device, or send the supervision results of the target AI model to the first device;

[1223] The target AI model is subjected to model supervision to obtain the supervision results of the target AI model;

[1224] Send an eleventh instruction message to the first device, the eleventh instruction message being used to trigger the first device to train the target AI model;

[1225] Send a twelfth instruction message to the first device, the twelfth instruction message being used to trigger the first device to make a prediction based on the target AI model;

[1226] The target AI model includes either a first AI model or a second AI model;

[1227] The first AI model is used to predict at least one of the following:

[1228] Activate or deactivate the target transfer;

[1229] Sending an activation signal or not sending an activation signal, the activation signal being used to activate or request activation of the target transmission;

[1230] The number of target transmissions that need to be activated;

[1231] The range of target transmissions that need to be activated;

[1232] The second AI model is used to predict at least one of the following;

[1233] Deactivate or deactivate the target transfer;

[1234] Send a deactivation signal or not send a deactivation signal, wherein the deactivation signal is used to deactivate or request deactivation of the target transmission;

[1235] The number of target transfers that need to be deactivated;

[1236] The range of the target transmission that needs to be deactivated.

[1237] It is understood that the implementation process of each implementation method mentioned in this embodiment can refer to the relevant description of the transmission control method in the method embodiment and achieve the same or corresponding technical effects. To avoid repetition, it will not be described again here.

[1238] This application embodiment also provides a network-side device, including a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is used to run programs or instructions to implement, for example... Figure 5 or Figure 6 The steps of the method embodiment shown are illustrated. This network-side device embodiment corresponds to the above-described network-side device method embodiment. All implementation processes and methods of the above-described method embodiments can be applied to this network-side device embodiment and can achieve the same technical effect.

[1239] Specifically, embodiments of this application also provide a network-side device, which can be... Figure 7 or Figure 8The transmission control device shown. (For example...) Figure 11 As shown, the network-side device 11000 includes: an antenna 1101, a radio frequency (RF) device 1102, a baseband device 1103, a processor 1104, and a memory 1105. The antenna 1101 is connected to the RF device 1102. In the uplink direction, the RF device 1102 receives information through the antenna 1101 and transmits the received information to the baseband device 1103 for processing. In the downlink direction, the baseband device 1103 processes the information to be transmitted and sends it to the RF device 1102. The RF device 1102 processes the received information and transmits it through the antenna 1101.

[1240] The method executed by the network-side device in the above embodiments can be implemented in the baseband device 1103, which includes a baseband processor.

[1241] The baseband device 1103 may include, for example, at least one baseband board on which multiple chips are disposed, such as... Figure 11 As shown, one of the chips is, for example, a baseband processor, which is connected to the memory 1105 via a bus interface to call the program in the memory 1105 and execute the network device operation shown in the above method embodiment.

[1242] The network-side device may also include a network interface 1106, such as a Common Public Radio Interface (CPRI).

[1243] Specifically, the network-side device 11000 in this application embodiment further includes: instructions or programs stored in memory 1105 and executable on processor 1104, wherein processor 1104 calls the instructions or programs in memory 1105 to execute. Figure 7 or Figure 8 The methods executed by each module shown achieve the same technical effect, and to avoid repetition, they will not be described in detail here.

[1244] This application also provides a readable storage medium storing a program or instructions. When the program or instructions are executed by a processor, they implement the various processes of the above-described transmission control method embodiments and achieve the same technical effects. To avoid repetition, they will not be described again here.

[1245] The processor mentioned above is the processor in the terminal described in the above embodiments. The readable storage medium includes computer-readable storage media, such as computer read-only memory (ROM), random access memory (RAM), magnetic disk, or optical disk. In some examples, the readable storage medium may be a non-transient readable storage medium.

[1246] This application embodiment also provides a chip, which includes a processor and a communication interface. The communication interface is coupled to the processor. The processor is used to run programs or instructions to implement the various processes of the above-described transmission control method embodiments and can achieve the same technical effect. To avoid repetition, it will not be described again here.

[1247] It should be understood that the chip mentioned in the embodiments of this application may also be referred to as a system-on-a-chip, system chip, chip system, or system-on-a-chip, etc.

[1248] This application also provides a computer program / program product, which is stored in a storage medium and executed by at least one processor to implement the various processes of the above-described transmission control method embodiments, and can achieve the same technical effect. To avoid repetition, it will not be described again here.

[1249] This application also provides a wireless communication system, including a first device and a second device, wherein the first device can be used to perform the steps of the transmission control method described above, and the second device can be used to perform the steps of the transmission control method described above.

[1250] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element. Furthermore, it should be noted that the scope of the methods and apparatuses in the embodiments of this application is not limited to performing functions in the order shown or discussed, but may also include performing functions substantially simultaneously or in the reverse order, depending on the functions involved. For example, the described methods may be performed in a different order than described, and various steps may be added, omitted, or combined. Additionally, features described with reference to certain examples may be combined in other examples.

[1251] From the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of computer software products plus necessary general-purpose hardware platforms, and of course, they can also be implemented by hardware. The computer software product is stored in a storage medium (such as ROM, RAM, magnetic disk, optical disk, etc.) and includes several instructions to cause the terminal or network-side device to execute the methods described in the various embodiments of this application.

[1252] The embodiments of this application have been described above with reference to the accompanying drawings. However, this application is not limited to the specific embodiments described above. The specific embodiments described above are merely illustrative and not restrictive. Those skilled in the art can make many other implementations under the guidance of this application without departing from the spirit and scope of the claims. All of these implementations are within the protection scope of this application.

Claims

1. A transmission control method, characterized in that, include: The first device determines the target result based on the target artificial intelligence (AI) model. The target AI model includes a first AI model or a second AI model, and the target result includes a first result determined based on the first AI model or a second result determined based on the second AI model. The first result is used to indicate at least one of the following; Activate or deactivate the first transmission; Sending an activation signal or not sending an activation signal, the activation signal being used to activate or request activation of the first transmission; The number of first transmissions that need to be activated; The range of the first transmission to be activated; The second result is used to indicate at least one of the following: Deactivate or deactivate the first transmission; Send a deactivation signal or not send a deactivation signal, the deactivation signal being used to deactivate or request deactivation of the first transmission; The number of first transfers that need to be deactivated; The range of the first transmission that needs to be deactivated.

2. The method according to claim 1, characterized in that, The first device determines the target result based on the target AI model, including: The first device determines the target result based on the first input information and the target AI model; The first input information includes at least one of the following: Time information; Terminal status information; Status information of network-side devices; Server status information; The signal strength and signal quality obtained by the terminal from measuring the reference signal associated with the second transmission, or the value determined based on the signal strength and signal quality obtained by the terminal from measuring the reference signal associated with the second transmission; The value determined by the terminal based on at least one of the signal strength and signal quality measured by the second transmission, or based on at least one of the signal strength and signal quality measured by the terminal based on the second transmission; The number of times the terminal failed to access the physical random access channel PRACH corresponding to the third transmission or the number of times it failed to receive the access response message. The number of PRACH retransmissions performed by the terminal on the PRACH resources associated with the third transport; The first indication information is used to indicate whether the terminal fails to access the PRACH resource associated with the third transmission after attempting two-step random access and then falling back to four-step random access. The second indication information is used to indicate whether the power of the terminal transmitting the PRACH signal on the third transmission associated PRACH resource is greater than or equal to the first threshold. The third indication information is used to indicate at least one of the following: whether the terminal receives a first random access response (RAR) message, the number of first RAR messages received within a first time period, and the number of first RAR messages received within the first time period being greater than or equal to a second threshold; wherein, the first RAR message is a RAR message whose included preamble identifier is not a preamble identifier sent by the terminal on the third transmission associated PRACH resource. The fourth indication information is used to indicate whether the number of times the terminal sends the activation signal is less than or equal to the first number, or the fourth indication information is used to indicate whether the number of times the terminal sends the deactivation signal is less than or equal to the second number; The fifth indication information is used to indicate whether the timing advance TA for activating signal transmission is valid, or the fifth indication information is used to indicate whether the timing advance TA for deactivating signal transmission is valid; The sixth indication information is used to indicate whether the interval between the current time and the time of the previous activation signal is greater than or equal to the first interval, or the sixth indication information is used to indicate whether the interval between the current time and the time of the previous deactivation signal is greater than or equal to the second interval; The seventh indication information is used to indicate whether the interval between the time of the previous activation or deactivation of the first transmission and the current time is greater than or equal to the third interval; The eighth indication information is used to indicate whether the terminal has sent an activation signal for the fourth transmission, or the eighth indication information is used to indicate whether the terminal has sent a deactivation signal for the fourth transmission. The ninth indication information is used to indicate whether the fifth transmission has been activated, or the ninth indication information is used to indicate whether the fifth transmission has been deactivated; The tenth indication information is used to indicate whether the terminal has detected the sixth transmission; Information on sudden events; The frequency domain characteristics of the first transmission; The temporal characteristics of the first transmission; The spatial characteristics of the first transmission; The second transmission is different from the first transmission, and the third transmission is a transmission associated with PRACH.

3. The method according to claim 2, characterized in that, The terminal's status information includes at least one of the following: the terminal's location information, the terminal's distribution information, the terminal's direction of movement, the terminal's speed of movement, the terminal's energy consumption status, the terminal's battery status, the terminal's network scene information, the terminal's environmental information, and the terminal's perception information. or, The status information of the network-side device includes at least one of the following: the energy consumption status of the network-side device, the power status of the network-side device, the environmental information of the network-side device, and the sensing information of the network-side device; or, The server's status information includes at least one of the following: the server's environmental information, and the server's perception information.

4. The method according to any one of claims 1 to 3, characterized in that, The triggering conditions for using the first AI model to make predictions include at least one of the following: Terminal power-on; The terminal performs an initial cell search; The terminal performs initial cell selection; The time taken for the terminal to perform the initial search using traditional methods reached the first duration; The terminal did not remain logged into the new cell during the second time period. The terminal performs cell reselection; The terminal performs cell handover; The timer used to trigger the prediction timed out; Before random access is triggered; Before the initial access is triggered; Beam failure detected; Wireless link failure detected; Based on at least one piece of information from the input information of the first AI model, it is determined that the first AI model needs to be used for prediction.

5. The method according to any one of claims 1 to 4, characterized in that, The triggering conditions for using the second AI model to make predictions include at least one of the following: Terminal power-on; The terminal performs an initial cell search; The terminal performs initial cell selection; The time taken for the terminal to perform the initial search using traditional methods exceeds the second search duration; The terminal did not remain logged into the new cell during the third time period; The terminal performs cell reselection; The terminal performs cell handover; The timer used to trigger the prediction timed out; Before random access is triggered; Before the initial access is triggered; Beam failure detected; Wireless link failure detected; The power consumption of network-side devices exceeds the first threshold; The terminal's energy consumption exceeds the second threshold; The terminal's battery level is below the third threshold; Based on at least one of the input information of the second AI model, it is determined that the second AI model needs to be used for prediction.

6. The method according to any one of claims 1 to 5, characterized in that, After the first device determines the target result based on the target artificial intelligence (AI) model, the method further includes: The first device performs a first operation, which includes at least one of the following: Send at least a portion of the input information of the target AI model and at least one of the target results; The process reverts to using a non-AI method to determine whether to activate or deactivate the first transmission. Trigger the switching of the target AI model; Trigger the retraining of the target AI model; This triggers the supervision of the target AI model.

7. The method according to claim 6, characterized in that, The fallback to using a non-AI method to determine whether to activate or deactivate the first transmission includes: If at least one of the following conditions is met, the process reverts to using a non-AI method to determine whether to activate or deactivate the first transmission; If the prediction is not successfully completed even after the first device has used the target AI model for a period of time exceeding the third time limit; The first device failed to make a prediction using the target AI model.

8. The method according to any one of claims 1 to 7, characterized in that, The method further includes at least one of the following: The first device acquires the metrics of the target AI model; The first device sends the metrics of the target AI model; The metrics of the target AI model include at least one of the following: The complexity of the target AI model; The latency predicted by the target AI model; The success rate of the target AI model's predictions; The reliability of the results output by the target AI model.

9. The method according to any one of claims 1 to 8, characterized in that, The method further includes: The first device trains at least a portion of the AI ​​model in the target AI model; or, The first device receives at least a portion of the AI ​​model from the target AI model.

10. The method according to claim 9, characterized in that, The triggering type for training the target AI model includes at least one of the following: conditional or event-triggered, periodic triggering, and semi-static triggering.

11. The method according to claim 9 or 10, characterized in that, The conditions or events that trigger the training of the target AI model include at least one of the following: The configuration information of the first transmission has changed; The configuration information for the second transmission has changed; The activation or deactivation method of the first transmission changes; The target AI model failed to predict; The target AI model fails to make predictions N times consecutively, where N is a positive integer; The number of times the target AI model failed to predict reached the fourth threshold; The target AI model was used for prediction; The terminal reselects to a new cell. The tracking area of ​​the terminal has changed; The environment in which the terminal is located has changed; The second transmission is different from the first transmission.

12. The method according to claim 11, characterized in that, The configuration information of the first transmission includes at least one of the following: the number of first transmissions, the range of the first transmission, the beam configuration corresponding to the first transmission, the transmission power of the first transmission, and the period of the first transmission; or, The configuration information of the second transmission includes at least one of the following: the number of second transmissions, the range of the second transmission, the beam configuration corresponding to the second transmission, the transmission power of the second transmission, and the period of the second transmission.

13. The method according to any one of claims 10 to 12, characterized in that, The configuration information for periodic triggering includes at least one of the following: the starting point of periodic model training, the interval of periodic model training, the number of model training sessions within a period, and the duration of model training within a period.

14. The method according to any one of claims 10 to 13, characterized in that, The semi-static triggering includes at least one of the following: The semi-static triggering configuration information is sent and / or activated based on specific conditions or events. The configuration information for the semi-static trigger is configured via Radio Resource Control (RRC), and / or the semi-static training of the model is activated or deactivated via Physical Control Information.

15. The method according to any one of claims 8 to 14, characterized in that, The method further includes: The first device receives second input information, which is used for training the target AI model; or, The first device sends third input information, which is used for training the target AI model.

16. The method according to claim 15, characterized in that, The first device is a terminal; The first device receives the second input information, including: The first device receives second input information sent by the network-side device through at least one of the following: Media Access Control Unit (MAC CE); RRC message; Non-Access Stratum (NAS) message; User plane data; System Information Block (SIB); Physical Layer Signaling; Physical Downlink Shared Channel; MSG 2; MSG 4; MSG B; or, The first device sends third input information, including at least one of the following: The first device sends the third input information to the network-side device through at least one of the following: MAC CE; RRC message; NAS message; user plane data; MSG 1; MSG A; MSG 3; physical uplink control channel; physical uplink shared channel; random access channel; uplink reference signal; The first device sends the third input information to the server through the first interface message.

17. The method according to claim 16, characterized in that, The first device is a network-side device; The first device receives the second input information, including: The first device receives second input information sent by the terminal via at least one of the following: MAC CE; RRC message; NAS message; user plane data; MSG 1; MSG A; MSG 3; physical uplink control channel; physical uplink shared channel; random access channel; uplink reference signal; or, The first device sends third input information, including at least one of the following: The first device sends the third input information to the terminal via at least one of the following: MAC CE; RRC message; Layer NAS message; User plane data; DCI information; SIB; Physical layer signaling; Physical downlink shared channel; MSG 2; MSG 4; MSG B; The first device sends the third input information to the server through the second interface message.

18. The method according to claim 15, characterized in that, The first device is a server; The first device receives third input information, including: The first device receives third input information from at least one of the terminal and the network-side device.

19. The method according to any one of claims 15 to 18, characterized in that, The triggering conditions for sending or receiving the second or third input information include at least one of the following: Terminal resides in the community; The terminal selects a cell for the first time; Terminal reselects cell; The terminal enters RRC connection state; The terminal has been in an inactive state for four consecutive hours.

20. The method according to any one of claims 1 to 19, characterized in that, The criteria for determining whether the first AI model has completed training include at least one of the following: The loss function used for training the first AI model satisfies the first preset condition; When the output of the first AI model indicates that the seventh transmission is activated, the measurement result obtained by the terminal based on the seventh transmission satisfies the second preset condition. If the output of the first AI model indicates that the seventh transmission is activated, the probability that the terminal successfully detects the seventh transmission after the seventh transmission is activated is greater than or equal to the third threshold. If the output of the first AI model indicates that the seventh transmission is activated, the terminal detects that the duration of the seventh transmission is less than or equal to the fourth threshold after the seventh transmission is activated. When the output of the first AI model indicates that the seventh transmission is activated, the probability that the terminal successfully accesses the network based on the seventh transmission is greater than or equal to the fifth threshold. If the output of the first AI model indicates that the seventh transmission is not activated, the probability that the terminal successfully accesses the network based on the eighth transmission is greater than or equal to the sixth threshold. When the output of the first AI model indicates that the seventh transmission is activated, the probability or frequency of the terminal selecting the seventh transmission for random access is greater than or equal to the seventh threshold. When the output of the first AI model indicates that the seventh transmission is activated, the probability or frequency of the terminal selecting the eighth transmission for random access is greater than or equal to the eighth threshold. The number of training iterations for the first AI model has reached a first preset value; The number of iterations for fine-tuning the first AI model reaches the second preset value.

21. The method according to any one of claims 1 to 20, characterized in that, The criteria for determining whether the training of the second AI model is complete include at least one of the following: The loss function used for training the second AI model satisfies the third preset condition; If the result output by the second AI model indicates that the ninth transmission should not be activated, the measurement result obtained by the terminal based on the ninth transmission satisfies the fourth preset condition. If the output of the second AI model indicates that the ninth transmission should not be activated, the probability that the terminal detects the ninth transmission is greater than or equal to the ninth threshold. If the result output by the second AI model indicates that the ninth transmission should not be activated, the terminal detects that the duration of the ninth transmission is less than or equal to the tenth threshold. If the output of the second AI model indicates that the ninth transmission should not be activated, the probability that the terminal successfully accesses the network based on the ninth transmission is greater than or equal to the eleventh threshold. When the output of the second AI model indicates that the ninth transmission should be activated, the probability that the terminal will successfully access the network based on the tenth transmission is greater than or equal to the twelfth threshold. If the output of the second AI model indicates that the ninth transmission should not be activated, the probability or frequency of the terminal selecting the ninth transmission for random access is greater than or equal to the thirteenth threshold. When the output of the second AI model indicates that the ninth transmission should be activated, the probability or frequency of the terminal selecting the tenth transmission for random access is greater than or equal to the fourteenth threshold. The second AI model has been trained a third preset number of times; The second AI model has reached the fourth preset number of iterations for fine-tuning.

22. The method according to any one of claims 1 to 21, characterized in that, When the target AI model is trained by the first device, the first information of the target AI model is determined according to the type of the first device; The first information includes at least one of the following: model information of the target AI model, input information for training the target AI model, label information for training the target AI model, and execution method for training the target AI model.

23. The method according to any one of claims 1 to 22, characterized in that, The triggering conditions for updating or retraining the target AI model include at least one of the following: The configuration information of the first transmission has changed; The configuration information for the second transmission has changed; The activation or deactivation method of the first transmission changes; The terminal moves to a new cell, a new tracking area, or a new geographical location; The change in the terminal's moving speed is greater than or equal to a fifth preset value, or the rate of change in the terminal's moving speed is greater than or equal to a sixth preset value. It has been five hours since the last model update or retraining. Timeout for a timer used to trigger model updates or retraining; M consecutive model supervisions have occurred or M model supervisions have been triggered, where M is a positive integer; The target AI model failed to predict; The target AI model fails to predict K times consecutively, where K is a positive integer; The number of times the target AI model failed to predict reached the fifth threshold; The target AI model was used for prediction; The environment in which the terminal is located has changed.

24. The method according to any one of claims 1 to 23, characterized in that, The method further includes: The first device acquires the model supervision results of the target AI model; or, The first device sends the model supervision results of the target AI model.

25. The method according to claim 24, characterized in that, The first device acquires the model supervision results of the target AI model, including: The first device performs model supervision on the target AI model to obtain the model supervision result of the target AI model; or, The first device receives the model supervision results of the target AI model.

26. The method according to any one of claims 1 to 25, characterized in that, The configuration information used for supervising the target AI model includes at least one of the following: Identification of AI models that require model supervision; The cycle of model supervision; The duration of model supervision; Information related to the detection window in model supervision; Triggering conditions for model supervision; Metrics for model supervision.

27. The method according to any one of claims 1 to 26, characterized in that, The triggering conditions for the supervision of the target AI model include at least one of the following: The target AI model does not meet the supervision index, or the target AI model does not meet the fifth preset condition, or the duration of the target AI model not meeting the supervision index reaches the sixth duration, or the duration of the target AI model not meeting the supervision index reaches the sixth duration. The target result of the target AI model does not meet the sixth preset condition, or the duration for which the target result of the target AI model does not meet the sixth preset condition reaches the seventh duration; The target AI model does not meet at least one of its metrics, or at least one of its metrics does not meet the seventh preset condition.

28. The method according to any one of claims 1 to 27, characterized in that, The metrics for supervising the target AI model include at least one of the following: Error information or accuracy information between the prediction results and actual results of the target AI model; Performance metrics of a communication system; The model-related information of the target AI model.

29. The method according to any one of claims 1 to 28, characterized in that, The method further includes at least one of the following: The first device sends information about its AI-related capabilities. The first device determines the AI-related capability information of the second device; The AI-related capability information is used to indicate at least one of the following: It may or may not have the ability to train an AI model for predicting the activation or deactivation of a target. It may or may not have the ability to predict the activation or deactivation of target transmission through AI models; It may or may not have the ability to send first auxiliary information, which is used to predict the activation or deactivation of the target transmission through an AI model; It may or may not have the ability to send second auxiliary information, which is used to train an AI model for predicting the activation or deactivation of the target transmission.

30. The method according to claim 29, characterized in that, The first device determines the AI-related capability information of the second device, including: The first device determines the AI-related capability information of the second device based on at least one of the following: The equipment type of the second device; AI-related capability information indicated by reference signals; The control information sent by the second device carries AI-related capability information; The AI-related capability information carried in the RRC signaling sent by the second device; The AI-related capability information carried in the interface messages between the first device and the second device.

31. The method according to any one of claims 1 to 30, characterized in that, The first device is a server, and the method further includes: The server sends the target result to the terminal or network-side device.

32. A transmission control method, characterized in that, include: The second device performs a second operation, the second operation including at least one of the following: At least a portion of the AI ​​model in the training target AI model; Send at least a portion of the AI ​​model from the target AI model to the first device; Send first input information to the first device, the first input information being used for prediction by the target AI model; Send second input information to the first device, the second input information being used for training the target AI model; Receive third input information from the first device, the third input information being used for training the target AI model; Receive the target result sent by the first device, wherein the target result is the result determined according to the target AI model; Receive the supervision results of the target AI model sent by the first device, or send the supervision results of the target AI model to the first device; The target AI model is subjected to model supervision to obtain the supervision results of the target AI model; Send an eleventh instruction message to the first device, the eleventh instruction message being used to trigger the first device to train the target AI model; Send a twelfth instruction message to the first device, the twelfth instruction message being used to trigger the first device to make a prediction based on the target AI model; The target AI model includes either a first AI model or a second AI model; The first AI model is used to predict at least one of the following: Activate or deactivate the target transfer; Sending an activation signal or not sending an activation signal, the activation signal being used to activate or request activation of the target transmission; The number of target transmissions that need to be activated; The range of target transmissions that need to be activated; The second AI model is used to predict at least one of the following; Deactivate or deactivate the target transfer; Send a deactivation signal or not send a deactivation signal, wherein the deactivation signal is used to deactivate or request deactivation of the target transmission; The number of target transfers that need to be deactivated; The range of the target transmission that needs to be deactivated.

33. The method according to claim 32, characterized in that, At least a portion of the AI ​​models in the training target AI model include: Train at least a portion of the AI ​​model in the target AI model based on the target input information; The target input information includes at least one of the following: Time information; Terminal status information; Status information of network-side devices; Server status information; The frequency domain characteristics of the eleventh transmission; The temporal characteristics of the eleventh transmission; The spatial characteristics of the eleventh transmission; The signal strength and signal quality obtained by the terminal measuring the reference signal of the twelfth transmission association, or the value determined based on the signal strength and signal quality obtained by the terminal measuring the reference signal of the twelfth transmission association; The value determined by the terminal based on at least one of the signal strength and signal quality measured by the twelfth transmission, or based on at least one of the signal strength and signal quality measured by the terminal based on the twelfth transmission; The number of times the terminal failed to access the physical random access channel PRACH corresponding to the thirteenth transmission or the number of times it failed to receive the access response message. The number of PRACH retransmissions performed by the terminal on the PRACH resource associated with the thirteenth transmission; The thirteenth instruction information is used to indicate whether the terminal fails to access the PRACH resource associated with the thirteenth transmission after attempting two steps of random access and then falling back to four steps of random access. The fourteenth indication information is used to indicate whether the power of the terminal transmitting the PRACH signal on the PRACH resource associated with the thirteenth transmission is greater than or equal to the first threshold. The fifteenth indication information is used to indicate at least one of the following: whether the terminal receives a second random access response (RAR) message, the number of second RAR messages received within a first time period, and the number of second RAR messages received within the first time period being greater than or equal to a second threshold; wherein the second RAR message is a RAR message whose included preamble identifier is not a preamble identifier sent by the terminal on the PRACH resource associated with the thirteenth transmission. The sixteenth indication information is used to indicate whether the number of times the terminal sends an activation signal is less than or equal to the first number, or the sixteenth indication information is used to indicate whether the number of times the terminal sends a deactivation signal is less than or equal to the second number; The seventeenth indication information is used to indicate whether the timing advance TA for activating signal transmission is valid, or the seventeenth indication information is used to indicate whether the timing advance TA for deactivating signal transmission is valid; The eighteenth indication information is used to indicate whether the interval between the current time and the time of the previous activation signal is greater than or equal to the first interval, or the eighteenth indication information is used to indicate whether the interval between the current time and the time of the previous deactivation signal is greater than or equal to the second interval. The nineteenth instruction information is used to indicate whether the interval between the time of the previous activation or deactivation of the eleventh transmission and the current time is greater than or equal to the third interval; The twentieth indication information is used to indicate whether the terminal has sent the fourteenth transmission activation signal, or whether the twentieth indication information is used to indicate whether the terminal has sent the fourteenth transmission deactivation signal. The 21st indication information is used to indicate whether the 15th transmission has been activated, or whether the 21st indication information has been deactivated. The twenty-second instruction message is used to indicate whether the terminal has detected the sixteenth transmission; Information on sudden events; The twelfth transmission is different from the eleventh transmission, and the thirteenth transmission is a transmission associated with PRACH.

34. The method according to claim 33, characterized in that, The terminal's status information includes at least one of the following: the terminal's location information, the terminal's distribution information, the terminal's direction of movement, the terminal's speed of movement, the terminal's energy consumption status, the terminal's battery status, the terminal's network scene information, the terminal's environmental information, and the terminal's perception information. or, The status information of the network-side device includes at least one of the following: the energy consumption status of the network-side device, the power status of the network-side device, the environmental information of the network-side device, and the sensing information of the network-side device; or, The server's status information includes at least one of the following: the server's environmental information, and the server's perception information.

35. The method according to any one of claims 32 to 34, characterized in that, The target AI model is the first AI model, and sending the eleventh instruction information to the first device includes: The eleventh indication message is sent to the first device if at least one of the following conditions is met: Terminal power-on; The terminal performs an initial cell search; The terminal performs initial cell selection; The time taken for the terminal to perform the initial search using traditional methods reached the first duration; The terminal did not remain logged into the new cell during the second time period. The terminal performs cell reselection; The terminal performs cell handover; The timer used to trigger the prediction timed out; Before random access is triggered; Before the initial access is triggered; Beam failure detected; Wireless link failure detected.

36. The method according to any one of claims 32 to 34, characterized in that, The target AI model is the second AI model, and sending the eleventh instruction information to the first device includes: The eleventh indication message is sent to the first device if at least one of the following conditions is met: Terminal power-on; The terminal performs an initial cell search; The terminal performs initial cell selection; The time taken for the terminal to perform the initial search using traditional methods exceeds the second search duration; The terminal did not remain logged into the new cell during the third time period; The terminal performs cell reselection; The terminal performs cell handover; The timer used to trigger the prediction timed out; Before random access is triggered; Before the initial access is triggered; Beam failure detected; Wireless link failure detected; The power consumption of network-side devices exceeds the first threshold; The terminal's energy consumption exceeds the second threshold; The terminal's battery level is below the third threshold.

37. The method according to any one of claims 32 to 36, characterized in that, The method further includes: The second device receives the metrics of the target AI model from the first device; or, The second device sends the metrics of the target AI model to the first device; The metrics of the target AI model include at least one of the following: The complexity of the target AI model; The latency predicted by the target AI model; The success rate of the target AI model's predictions; The reliability of the results output by the target AI model.

38. The method according to any one of claims 32 to 37, characterized in that, The triggering type for training the target AI model includes at least one of the following: conditional or event-triggered, periodic triggering, and semi-static triggering.

39. The method according to any one of claims 32 to 38, characterized in that, The conditions or events that trigger the training of the target AI model include at least one of the following: The configuration information for the first transmission has changed; The configuration information for the second transmission has changed; The activation or deactivation method of the first transmission changes; The target AI model failed to predict; The target AI model fails to make predictions N times consecutively, where N is a positive integer; The number of times the target AI model failed to predict reached the fourth threshold; The target AI model was used for prediction; The terminal reselects to a new cell. The tracking area of ​​the terminal has changed; The environment in which the terminal is located has changed; The second transmission is different from the first transmission.

40. The method according to any one of claims 32 to 39, characterized in that, The triggering conditions for sending or receiving the second or third input information include at least one of the following: Terminal resides in the community; The terminal selects a cell for the first time; Terminal reselects cell; The terminal enters RRC connection state; The terminal has been in an inactive state for four consecutive hours.

41. The method according to any one of claims 32 to 40, characterized in that, The criteria for determining whether the first AI model has completed training include at least one of the following: The loss function used for training the first AI model satisfies the first preset condition; When the output of the first AI model indicates that the seventh transmission is activated, the measurement result obtained by the terminal based on the seventh transmission satisfies the second preset condition. If the output of the first AI model indicates that the seventh transmission is activated, the probability that the terminal successfully detects the seventh transmission after the seventh transmission is activated is greater than or equal to the third threshold. If the output of the first AI model indicates that the seventh transmission is activated, the terminal detects that the duration of the seventh transmission is less than or equal to the fourth threshold after the seventh transmission is activated. When the output of the first AI model indicates that the seventh transmission is activated, the probability that the terminal successfully accesses the network based on the seventh transmission is greater than or equal to the fifth threshold. If the output of the first AI model indicates that the seventh transmission is not activated, the probability that the terminal successfully accesses the network based on the eighth transmission is greater than or equal to the sixth threshold. When the output of the first AI model indicates that the seventh transmission is activated, the probability or frequency of the terminal selecting the seventh transmission for random access is greater than or equal to the seventh threshold. When the output of the first AI model indicates that the seventh transmission is activated, the probability or frequency of the terminal selecting the eighth transmission for random access is greater than or equal to the eighth threshold. The number of training iterations for the first AI model has reached a first preset value; The number of iterations for fine-tuning the first AI model reaches the second preset value.

42. The method according to any one of claims 32 to 41, characterized in that, The criteria for determining whether the training of the second AI model is complete include at least one of the following: The loss function used for training the second AI model satisfies the third preset condition; If the result output by the second AI model indicates that the ninth transmission should not be activated, the measurement result obtained by the terminal based on the ninth transmission satisfies the fourth preset condition. If the output of the second AI model indicates that the ninth transmission should not be activated, the probability that the terminal detects the ninth transmission is greater than or equal to the ninth threshold. If the result output by the second AI model indicates that the ninth transmission should not be activated, the terminal detects that the duration of the ninth transmission is less than or equal to the tenth threshold. If the output of the second AI model indicates that the ninth transmission should not be activated, the probability that the terminal successfully accesses the network based on the ninth transmission is greater than or equal to the eleventh threshold. When the output of the second AI model indicates that the ninth transmission should be activated, the probability that the terminal will successfully access the network based on the tenth transmission is greater than or equal to the twelfth threshold. If the output of the second AI model indicates that the ninth transmission should not be activated, the probability or frequency of the terminal selecting the ninth transmission for random access is greater than or equal to the thirteenth threshold. When the output of the second AI model indicates that the ninth transmission should be activated, the probability or frequency of the terminal selecting the tenth transmission for random access is greater than or equal to the fourteenth threshold. The second AI model has been trained a third preset number of times; The second AI model has reached the fourth preset number of iterations for fine-tuning.

43. The method according to any one of claims 32 to 42, characterized in that, When the target AI model is trained by the second device, the first information of the target AI model is determined according to the type of the second device; The first information includes at least one of the following: model information of the target AI model, input information for training the target AI model, label information for training the target AI model, and execution method for training the target AI model.

44. The method according to any one of claims 32 to 43, characterized in that, The triggering conditions for updating or retraining the target AI model include at least one of the following: The configuration information for the first transmission has changed; The configuration information for the second transmission has changed; The activation or deactivation method of the first transmission changes; The terminal moves to a new cell, a new tracking area, or a new geographical location; The change in the terminal's moving speed is greater than or equal to a fifth preset value, or the rate of change in the terminal's moving speed is greater than or equal to a sixth preset value. It has been five hours since the last model update or retraining. Timeout for a timer used to trigger model updates or retraining; M consecutive model supervisions have occurred or M model supervisions have been triggered, where M is a positive integer; The target AI model failed to predict; The target AI model fails to predict K times consecutively, where K is a positive integer; The number of times the target AI model failed to predict reached the fifth threshold; The target AI model was used for prediction; The environment in which the terminal is located has changed.

45. The method according to any one of claims 32 to 44, characterized in that, The configuration information used for supervising the target AI model includes at least one of the following: Identification of AI models that require model supervision; The cycle of model supervision; The duration of model supervision; Information related to the detection window in model supervision; Triggering conditions for model supervision; Metrics for model supervision.

46. ​​The method according to any one of claims 32 to 45, characterized in that, The triggering conditions for the supervision of the target AI model include at least one of the following: The target AI model does not meet the supervision index, or the target AI model does not meet the fifth preset condition, or the duration of the target AI model not meeting the supervision index reaches the sixth duration, or the duration of the target AI model not meeting the supervision index reaches the sixth duration. The target result of the target AI model does not meet the sixth preset condition, or the duration for which the target result of the target AI model does not meet the sixth preset condition reaches the seventh duration; The target AI model does not meet at least one of its metrics, or at least one of its metrics does not meet the seventh preset condition.

47. The method according to any one of claims 32 to 46, characterized in that, The metrics for supervising the target AI model include at least one of the following: Error information or accuracy information between the prediction results and actual results of the target AI model; Performance metrics of a communication system; The model-related information of the target AI model.

48. The method according to any one of claims 32 to 47, characterized in that, The method further includes at least one of the following: The second device sends information about its AI-related capabilities. The second device determines the AI-related capability information of the first device; The AI-related capability information is used to indicate at least one of the following: It may or may not have the ability to train an AI model for predicting the activation or deactivation of a target. It may or may not have the ability to predict the activation or deactivation of target transmission through AI models; It may or may not have the ability to send first auxiliary information, which is used to predict the activation or deactivation of the target transmission through an AI model; It may or may not have the ability to send second auxiliary information, which is used to train an AI model for predicting the activation or deactivation of the target transmission.

49. A transmission control device, characterized in that, include: The processing module is used to determine the target result based on the target artificial intelligence (AI) model. The target AI model includes a first AI model or a second AI model, and the target result includes a first result determined based on the first AI model or a second result determined based on the second AI model. The first result is used to indicate at least one of the following; Activate or deactivate the first transmission; Sending an activation signal or not sending an activation signal, the activation signal being used to activate or request activation of the first transmission; The number of first transmissions that need to be activated; The range of the first transmission to be activated; The second result is used to indicate at least one of the following: Deactivate or deactivate the first transmission; Send a deactivation signal or not send a deactivation signal, the deactivation signal being used to deactivate or request deactivation of the first transmission; The number of first transfers that need to be deactivated; The range of the first transmission that needs to be deactivated.

50. The apparatus according to claim 49, characterized in that, The processing module is specifically used for: The target result is determined based on the first input information and the target AI model; The first input information includes at least one of the following: Time information; Terminal status information; Status information of network-side devices; Server status information; The signal strength and signal quality obtained by the terminal from measuring the reference signal associated with the second transmission, or the value determined based on the signal strength and signal quality obtained by the terminal from measuring the reference signal associated with the second transmission; The value determined by the terminal based on at least one of the signal strength and signal quality measured by the second transmission, or based on at least one of the signal strength and signal quality measured by the terminal based on the second transmission; The number of times the terminal failed to access the physical random access channel PRACH corresponding to the third transmission or the number of times it failed to receive the access response message. The number of PRACH retransmissions performed by the terminal on the PRACH resources associated with the third transport; The first indication information is used to indicate whether the terminal fails to access the PRACH resource associated with the third transmission after attempting two-step random access and then falling back to four-step random access. The second indication information is used to indicate whether the power of the terminal transmitting the PRACH signal on the third transmission associated PRACH resource is greater than or equal to the first threshold. The third indication information is used to indicate at least one of the following: whether the terminal receives a first random access response (RAR) message, the number of first RAR messages received within a first time period, and the number of first RAR messages received within the first time period being greater than or equal to a second threshold; wherein, the first RAR message is a RAR message whose included preamble identifier is not a preamble identifier sent by the terminal on the third transmission associated PRACH resource. The fourth indication information is used to indicate whether the number of times the terminal sends the activation signal is less than or equal to the first number, or the fourth indication information is used to indicate whether the number of times the terminal sends the deactivation signal is less than or equal to the second number; The fifth indication information is used to indicate whether the timing advance TA for activating signal transmission is valid, or the fifth indication information is used to indicate whether the timing advance TA for deactivating signal transmission is valid; The sixth indication information is used to indicate whether the interval between the current time and the time of the previous activation signal is greater than or equal to the first interval, or the sixth indication information is used to indicate whether the interval between the current time and the time of the previous deactivation signal is greater than or equal to the second interval; The seventh indication information is used to indicate whether the interval between the time of the previous activation or deactivation of the first transmission and the current time is greater than or equal to the third interval; The eighth indication information is used to indicate whether the terminal has sent an activation signal for the fourth transmission, or the eighth indication information is used to indicate whether the terminal has sent a deactivation signal for the fourth transmission. The ninth indication information is used to indicate whether the fifth transmission has been activated, or the ninth indication information is used to indicate whether the fifth transmission has been deactivated; The tenth indication information is used to indicate whether the terminal has detected the sixth transmission; Information on sudden events; The frequency domain characteristics of the first transmission; The temporal characteristics of the first transmission; The spatial characteristics of the first transmission; The second transmission is different from the first transmission, and the third transmission is a transmission associated with PRACH.

51. A transmission control device, characterized in that, include: A processing module is configured to perform a second operation, the second operation including at least one of the following: At least a portion of the AI ​​model in the training target AI model; Send at least a portion of the AI ​​model from the target AI model to the first device; Send first input information to the first device, the first input information being used for prediction by the target AI model; Send second input information to the first device, the second input information being used for training the target AI model; Receive third input information from the first device, the third input information being used for training the target AI model; Receive the target result sent by the first device, wherein the target result is the result determined according to the target AI model; Receive the supervision results of the target AI model sent by the first device, or send the supervision results of the target AI model to the first device; The target AI model is subjected to model supervision to obtain the supervision results of the target AI model; Send an eleventh instruction message to the first device, the eleventh instruction message being used to trigger the first device to train the target AI model; Send a twelfth instruction message to the first device, the twelfth instruction message being used to trigger the first device to make a prediction based on the target AI model; The target AI model includes either a first AI model or a second AI model; The first AI model is used to predict at least one of the following: Activate or deactivate the target transfer; Sending an activation signal or not sending an activation signal, the activation signal being used to activate or request activation of the target transmission; The number of target transmissions that need to be activated; The range of target transmissions that need to be activated; The second AI model is used to predict at least one of the following; Deactivate or deactivate the target transfer; Send a deactivation signal or not send a deactivation signal, wherein the deactivation signal is used to deactivate or request deactivation of the target transmission; The number of target transfers that need to be deactivated; The range of the target transmission that needs to be deactivated.

52. The apparatus according to claim 51, characterized in that, The processing module is specifically used for: Train at least a portion of the AI ​​model in the target AI model based on the target input information; The target input information includes at least one of the following: Time information; Terminal status information; Status information of network-side devices; Server status information; The frequency domain characteristics of the eleventh transmission; The temporal characteristics of the eleventh transmission; The spatial characteristics of the eleventh transmission; The signal strength and signal quality obtained by the terminal measuring the reference signal of the twelfth transmission association, or the value determined based on the signal strength and signal quality obtained by the terminal measuring the reference signal of the twelfth transmission association; The value determined by the terminal based on at least one of the signal strength and signal quality measured by the twelfth transmission, or based on at least one of the signal strength and signal quality measured by the terminal based on the twelfth transmission; The number of times the terminal failed to access the physical random access channel PRACH corresponding to the thirteenth transmission or the number of times it failed to receive the access response message. The number of PRACH retransmissions performed by the terminal on the PRACH resource associated with the thirteenth transmission; The thirteenth instruction information is used to indicate whether the terminal fails to access the PRACH resource associated with the thirteenth transmission after attempting two steps of random access and then falling back to four steps of random access. The fourteenth indication information is used to indicate whether the power of the terminal transmitting the PRACH signal on the PRACH resource associated with the thirteenth transmission is greater than or equal to the first threshold. The fifteenth indication information is used to indicate at least one of the following: whether the terminal receives a second random access response (RAR) message, the number of second RAR messages received within a first time period, and the number of second RAR messages received within the first time period being greater than or equal to a second threshold; wherein the second RAR message is a RAR message whose included preamble identifier is not a preamble identifier sent by the terminal on the PRACH resource associated with the thirteenth transmission. The sixteenth indication information is used to indicate whether the number of times the terminal sends an activation signal is less than or equal to the first number, or the sixteenth indication information is used to indicate whether the number of times the terminal sends a deactivation signal is less than or equal to the second number; The seventeenth indication information is used to indicate whether the timing advance TA for activating signal transmission is valid, or the seventeenth indication information is used to indicate whether the timing advance TA for deactivating signal transmission is valid; The eighteenth indication information is used to indicate whether the interval between the current time and the time of the previous activation signal is greater than or equal to the first interval, or the eighteenth indication information is used to indicate whether the interval between the current time and the time of the previous deactivation signal is greater than or equal to the second interval. The nineteenth instruction information is used to indicate whether the interval between the time of the previous activation or deactivation of the eleventh transmission and the current time is greater than or equal to the third interval; The twentieth indication information is used to indicate whether the terminal has sent the fourteenth transmission activation signal, or whether the twentieth indication information is used to indicate whether the terminal has sent the fourteenth transmission deactivation signal. The 21st indication information is used to indicate whether the 15th transmission has been activated, or whether the 21st indication information has been deactivated. The twenty-second instruction message is used to indicate whether the terminal has detected the sixteenth transmission; Information on sudden events; The twelfth transmission is different from the eleventh transmission, and the thirteenth transmission is a transmission associated with PRACH.

53. A first device, characterized in that, It includes a processor and a memory, the memory storing a program or instructions that can run on the processor, the program or instructions being executed by the processor to implement the steps of the transmission control method as described in any one of claims 1 to 31.

54. A second device, characterized in that, It includes a processor and a memory, the memory storing a program or instructions that can run on the processor, the program or instructions being executed by the processor to implement the steps of the transmission control method as described in any one of claims 32 to 48.

55. A readable storage medium, characterized in that, The readable storage medium stores a program or instructions that, when executed by a processor, implement the steps of the transmission control method as described in any one of claims 1 to 31, or implement the steps of the transmission control method as described in any one of claims 32 to 48.

56. A computer program product, characterized in that, The computer program product is executed by at least one processor to implement the steps of the transmission control method as claimed in any one of claims 1 to 31, or to implement the steps of the transmission control method as claimed in any one of claims 32 to 48.

Images