Transmission control method and apparatus, first device, and second device

Abstract

The present application relates to the technical field of communications, and discloses a transmission control method and apparatus, a first device, and a second device. The transmission control method in embodiments of the present application comprises: a first device determines a target result on the basis of a target AI model, wherein the target AI model comprises a first AI model or a second AI model, and the target result comprises a first result determined on the basis of the first AI model or a second result determined on the basis of the second AI model; the first result is used for indicating at least one of the following: activating or not activating a first transmission, sending or not sending an activation signal, the number of first transmissions that need to be activated, and the range of first transmissions that need to be activated; and the second result is used for indicating at least one of the following: deactivating or not deactivating a first transmission, sending or not sending a deactivation signal, the number of first transmissions that need to be deactivated, and the range of first transmissions that need to be deactivated.

Description

Transmission control method and device, first device and second device

[0001] Cross-reference to Related Applications

[0002] This application claims priority to Chinese Patent Application No. 202410717882.7, filed on June 04, 2024, the content of which is incorporated herein by reference in its entirety. TECHNICAL FIELD

[0003] The present application belongs to the technical field of communication, and specifically relates to a transmission control method and device, a first device and a second device. BACKGROUND

[0004] In order to control the complexity of transmission (e.g., downlink transmission) and reduce power consumption, some transmissions can be activated or deactivated according to needs, which can also be referred to as flexible transmission or on demand transmission, etc. However, in the related art, there is no corresponding solution for how to control the activation or deactivation of these transmissions, which results in poor accuracy of activation or deactivation of these transmissions. SUMMARY

[0005] Embodiments of the present application provide a transmission control method and device, a first device and a second device, which can improve the accuracy of activation or deactivation control of flexible transmission or on demand transmission, etc.

[0006] In a first aspect, a transmission control method is provided, the method comprising:

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

[0008] 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;

[0009] The first result is used to indicate at least one of:

[0010] activating or not activating a first transmission;

[0011] sending an activation signal or not sending an activation signal, the activation signal being used to activate or request to activate the first transmission;

[0012] a number of first transmissions that need to be activated;

[0013] a range of first transmissions that need to be activated;

[0014] The second result is used to indicate at least one of:

[0015] deactivating or not deactivating the first transmission;

[0016] sending or not sending a deactivation signal for deactivating or requesting to deactivate the first transmission;

[0017] a number of the first transmissions to be deactivated;

[0018] a range of the first transmissions to be deactivated.

[0019] In a second aspect, a transmission control apparatus is provided, and the apparatus comprises:

[0020] a processing module configured to determine a target result based on a target artificial intelligence (AI) model;

[0021] wherein 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;

[0022] the first result is configured to indicate at least one of:

[0023] activating or not activating the first transmission;

[0024] sending or not sending an activation signal for activating or requesting to activate the first transmission;

[0025] a number of the first transmissions to be activated;

[0026] a range of the first transmissions to be activated;

[0027] the second result is configured to indicate at least one of:

[0028] deactivating or not deactivating the first transmission;

[0029] sending or not sending a deactivation signal for deactivating or requesting to deactivate the first transmission;

[0030] a number of the first transmissions to be deactivated;

[0031] a range of the first transmissions to be deactivated.

[0032] In a third aspect, a transmission control method is provided, and the method comprises:

[0033] the second device performing a second operation, the second operation comprising at least one of:

[0034] training at least part of the target AI model;

[0035] sending at least part of the target AI model to the first device.

[0036] sending first input information to the first device, the first input information being used for prediction of the target AI model;

[0037] sending second input information to the first device, the second input information being used for training of the target AI model;

[0038] receiving third input information from the first device, the third input information being used for training of the target AI model;

[0039] receiving a target result sent by the first device, the target result being a result determined according to the target AI model;

[0040] receiving a supervision result of the target AI model sent by the first device, or sending a supervision result of the target AI model to the first device;

[0041] model supervision on the target AI model to obtain a supervision result of the target AI model;

[0042] sending eleventh indication information to the first device, the eleventh indication information being used for triggering the first device to perform training of the target AI model;

[0043] sending twelfth indication information to the first device, the twelfth indication information being used for triggering the first device to perform prediction based on the target AI model;

[0044] wherein the target AI model comprises a first AI model or a second AI model;

[0045] the first AI model is used for predicting at least one of the following;

[0046] activating or not activating a target transmission;

[0047] sending an activation signal or not sending the activation signal, the activation signal being used for activating or requesting to activate the target transmission;

[0048] a number of target transmissions that need to be activated;

[0049] a range of target transmissions that need to be activated;

[0050] the second AI model is used for predicting at least one of the following;

[0051] deactivating or not deactivating a target transmission;

[0052] sending a deactivation signal or not sending the deactivation signal, the deactivation signal being used for deactivating or requesting to deactivate the target transmission;

[0053] a number of target transmissions that need to be deactivated;

[0054] a range of target transmissions to be deactivated.

[0055] In a fourth aspect, there is provided a transmission control apparatus, comprising:

[0056] a processing module configured to perform a second operation, the second operation comprising at least one of:

[0057] training at least part of the target AI model;

[0058] sending at least part of the target AI model to the first device;

[0059] sending first input information to the first device, the first input information being used for prediction of the target AI model;

[0060] sending second input information to the first device, the second input information being used for training of the target AI model;

[0061] receiving third input information from the first device, the third input information being used for training of the target AI model;

[0062] receiving a target result sent by the first device, the target result being determined according to the target AI model;

[0063] receiving a supervision result of the target AI model sent by the first device, or sending a supervision result of the target AI model to the first device;

[0064] performing model supervision on the target AI model to obtain a supervision result of the target AI model;

[0065] sending eleventh indication information to the first device, the eleventh indication information being used to trigger the first device to perform training of the target AI model;

[0066] sending twelfth indication information to the first device, the twelfth indication information being used to trigger the first device to perform prediction based on the target AI model;

[0067] wherein the target AI model comprises a first AI model or a second AI model;

[0068] the first AI model is used to predict at least one of:

[0069] activating or not activating a target transmission;

[0070] sending an activation signal or not sending an activation signal, the activation signal being used to activate or request to activate a target transmission;

[0071] a number of target transmissions to be activated;

[0072] a range of target transmissions to be activated;

[0073] The second AI model is used to predict at least one of:

[0074] deactivating or not deactivating the target transmission;

[0075] sending or not sending a deactivation signal for deactivating or requesting to deactivate the target transmission;

[0076] a number of target transmissions that need to be deactivated;

[0077] a range of target transmissions that need to be deactivated.

[0078] In a fifth aspect, a device for transmission control is provided, which is configured to perform the steps of the method according to the first aspect, or implement the steps of the method according to the third aspect.

[0079] In a sixth aspect, a first device is provided, which comprises a processor and a memory storing programs or instructions executable on the processor, and the programs or instructions are executed by the processor to implement the steps of the method according to the first aspect.

[0080] In a seventh aspect, a first device is provided, which comprises a processor and a communication interface, wherein the processor is configured to determine a target result based on a target artificial intelligence (AI) model.

[0081] 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.

[0082] The first result is used to indicate at least one of:

[0083] activating or not activating the first transmission;

[0084] sending or not sending an activation signal for activating or requesting to activate the first transmission;

[0085] a number of first transmissions that need to be activated;

[0086] a range of first transmissions that need to be activated.

[0087] The second result is used to indicate at least one of:

[0088] deactivating or not deactivating the first transmission;

[0089] sending or not sending a deactivation signal for deactivating or requesting to deactivate the first transmission;

[0090] a number of first transmissions that need to be deactivated;

[0091] a range of first transmissions that need to be deactivated.

[0092] In an eighth aspect, a second device is provided, comprising a processor and a memory, the memory storing programs or instructions executable on the processor, the programs or instructions being executed by the processor to implement steps of the method according to the third aspect.

[0093] In a ninth aspect, a second device is provided, comprising a processor and a communication interface, wherein the processor is configured to perform second operations, the second operations comprising at least one of:

[0094] training at least part of the target AI model;

[0095] sending at least part of the target AI model to the first device;

[0096] sending first input information to the first device, the first input information being used for prediction of the target AI model;

[0097] sending second input information to the first device, the second input information being used for training of the target AI model;

[0098] receiving third input information from the first device, the third input information being used for training of the target AI model;

[0099] receiving a target result sent by the first device, the target result being a result determined according to the target AI model;

[0100] receiving a supervision result of the target AI model sent by the first device, or sending a supervision result of the target AI model to the first device;

[0101] performing model supervision on the target AI model to obtain a supervision result of the target AI model;

[0102] sending eleventh indication information to the first device, the eleventh indication information being used to trigger the first device to perform training of the target AI model;

[0103] sending twelfth indication information to the first device, the twelfth indication information being used to trigger the first device to perform prediction based on the target AI model;

[0104] wherein the target AI model comprises a first AI model or a second AI model;

[0105] the first AI model is used to predict at least one of:

[0106] activating or not activating the target transmission;

[0107] sending or not sending an activation signal for activating or requesting to activate the target transmission;

[0108] a number of target transmissions to be activated;

[0109] a range of target transmissions to be activated.

[0110] the second AI model is configured to predict at least one of:

[0111] deactivating or not deactivating the target transmission;

[0112] sending or not sending a deactivation signal for deactivating or requesting to deactivate the target transmission;

[0113] a number of target transmissions to be deactivated;

[0114] a range of target transmissions to be deactivated.

[0115] In a tenth aspect, a readable storage medium is provided, and the readable storage medium stores a program or instructions, and the program or instructions are executed by a processor to implement the steps of the method according to the first aspect or the steps of the method according to the third aspect.

[0116] In an eleventh aspect, a wireless communication system is provided, and the wireless communication system includes a first device and a second device, the first device is configured to implement the steps of the transmission control method according to the first aspect, and the second device is configured to implement the steps of the transmission control method according to the third aspect.

[0117] In a twelfth aspect, a chip is provided, and the chip includes a processor and a communication interface, the communication interface is coupled to the processor, and the processor is configured to run a program or instructions to implement the steps of the method according to the first aspect or the steps of the method according to the third aspect.

[0118] In a thirteenth aspect, a computer program / program product is provided, and the computer program / program product is stored in a storage medium, and the computer program / program product is executed by at least one processor to implement the steps of the method according to the first aspect or the steps of the method according to the third aspect.

[0119] In the embodiments of the present application, the first device determines a target result based on a target 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: activating or not activating the first transmission; sending an activation signal or not sending the activation signal, the activation signal being used to activate or request to activate the first transmission; the number of the first transmission to be activated; the range of the first transmission to be activated; and the second result is used to indicate at least one of the following: deactivating or not deactivating the first transmission; sending a deactivation signal or not sending the deactivation signal, the deactivation signal being used to deactivate or request to deactivate the first transmission; the number of the first transmission to be deactivated; and the range of the first transmission to be deactivated. That is, the embodiments of the present application control the activation or deactivation of the first transmission based on the AI model. Since the AI model has strong learning and computing capabilities, it is beneficial to ensure the accuracy of the activation or deactivation control of the first transmission, and thus it is beneficial to improve the resource utilization rate and reduce the energy consumption of the device. BRIEF DESCRIPTION OF DRAWINGS

[0120] FIG. 1 is a block diagram of a wireless communication system to which embodiments of the present application can be applied;

[0121] FIG. 2a is a schematic diagram of the association between an RO and an SSB according to an embodiment of the present application;

[0122] FIG. 2b is a schematic diagram of the association between an RO and an SSB according to another embodiment of the present application;

[0123] FIG. 3a is a schematic diagram of a neural network according to an embodiment of the present application;

[0124] FIG. 3b is a schematic diagram of a neuron according to an embodiment of the present application;

[0125] FIG. 4 is a schematic diagram of a framework of AI life cycle management according to an embodiment of the present application;

[0126] FIG. 5 is a flowchart of a transmission control method according to an embodiment of the present application;

[0127] FIG. 6 is a flowchart of another transmission control method according to an embodiment of the present application;

[0128] FIG. 7 is a structural diagram of a transmission control apparatus according to an embodiment of the present application;

[0129] FIG. 8 is a structural diagram of another transmission control apparatus according to an embodiment of the present application;

[0130] FIG. 9 is a structural diagram of a communication device according to an embodiment of the present application;

[0131] FIG. 10 is a structural diagram of a terminal according to an embodiment of the present application;

[0132] FIG. 11 is a structural diagram of a network-side device according to an embodiment of the present application. DETAILED DESCRIPTION

[0133] The technical solutions in the embodiments of the present application will be clearly described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some of the embodiments of the present application, but not all the embodiments of the present application. Based on the embodiments in the present application, all the other embodiments obtained by those of ordinary skill in the art belong to the scope of protection of the present application.

[0134] The terms "first", "second", and the like in the present application are used to distinguish similar objects, and are not used to describe a specific order or sequence. It should be understood that the terms used in this way can be interchanged under appropriate circumstances, so that the embodiments of the present application can be implemented in an order other than those illustrated or described herein, and the objects distinguished by "first", "second" are generally a category and do not limit the number of objects, for example, the first object can be one or more. In addition, "or" in the present application means at least one of the connected objects. For example, the protection scope of "A or B" at least covers three schemes, namely, scheme one: including A and not including B; scheme two: including B and not including A; scheme three: including A and including B. In addition, the terms "A and / or B", "at least one of A and B", "at least one of A or B" also at least cover the above three schemes, respectively. The character " / " generally represents that the objects before and after are in an "or" relationship.

[0135] The term "indication" in the present application can be a direct indication (or explicit indication) or an indirect indication (or implicit indication). The direct indication can be understood as that the sender explicitly informs the receiver of specific information, operations to be performed or requested results, etc. in the indication sent by the sender. The indirect indication can be understood as that the receiver determines the corresponding information according to the indication sent by the sender, or judges and determines the operations to be performed or the requested results according to the judgment result.

[0136] It is worth noting that the technology described in the embodiments of the present application is not limited to Long Term Evolution (LTE) / LTE-Advanced (LTE-A) systems, but can also be used in other wireless communication systems, such as Code Division Multiple Access (CDMA), Time Division Multiple Access (TDMA), Frequency Division Multiple Access (FDMA), Orthogonal Frequency Division Multiple Access (OFDMA), Single-carrier Frequency-Division Multiple Access (SC-FDMA) or other systems. The terms "system" and "network" in the embodiments of the present application are often used interchangeably, and the described technology can be used in the above-mentioned systems and radio technologies, as well as in other systems and radio technologies. The following description describes a New Radio (NR) system for example purposes, and NR terminology is used in most of the following description, but these technologies can also be applied to systems other than NR systems, such as 6th Generation (6G) communication systems. th

[0137] ​FIG. 1 shows a block diagram of a wireless communication system to which embodiments of the present application can be applied. The wireless communication system includes a terminal 11 and a network-side device 12. The terminal 11 can be a terminal-side device such as a mobile phone, a Tablet Personal Computer, a Laptop Computer, a notebook computer, a Personal Digital Assistant (PDA), a palmtop computer, a netbook, an Ultra-mobile Personal Computer (UMPC), a Mobile Internet Device (MID), an Augmented Reality (AR) device, a Virtual Reality (VR) device, a robot, a wearable device, a flight vehicle, a Vehicle User Equipment (VUE), a shipboard device, a Pedestrian User Equipment (PUE), a smart home (a home device with a wireless communication function such as a refrigerator, a television, a washing machine, or furniture), a game console, a Personal Computer (PC), a kiosk, or a self-service machine. The wearable device includes a smart watch, a smart bracelet, a smart earphone, smart glasses, smart jewelry (a smart bracelet, a smart necklace, a smart ring, a smart necklace, a smart anklet, a smart necklace, etc.), a smart wristband, smart clothes, etc. The vehicle-mounted device can also be referred to as a vehicle-mounted terminal, a vehicle-mounted controller, a vehicle-mounted module, a vehicle-mounted component, a vehicle-mounted chip, or a vehicle-mounted unit, etc. It should be noted that the specific type of the terminal 11 is not limited in the embodiments of the present application. The network-side device 12 can include an access network device or a core network device. The access network device can also be referred to as a Radio Access Network (RAN) device, a radio access network function, or a radio access network unit. The access network device can include a base station, a Wireless Local Area Network (WLAN) Access Point (AP), or a Wireless Fidelity (WiFi) node, etc.The base station can be referred to as a Node B (NB), an evolved Node B (eNB), a next generation Node B (gNB), a New Radio Node B (NR Node B), an access point, a relay station (RBS), a serving base station (SBS), a base transceiver station (BTS), a radio base station, a radio transceiver, a basic service set (BSS), an extended service set (ESS), a home Node B (HNB), a home evolved Node B, a transmit / receive point (TRP), or some other suitable terminology in the art, and is not limited to a particular technical terminology, provided that the same technical effect is achieved. It should be noted that in the embodiments of the present application, only the base station in the NR system is taken as an example for introduction, and the specific type of the base station is not limited.

[0138] The core network device can also be referred to as a core network node, a core network function, or a core network network element, etc., which includes but is not limited to at least one of the following: a mobility management entity (MME), an access and mobility management function (AMF), a session management function (SMF), a user plane function (UPF), a policy control function (PCF), a policy and charging rules function (PCRF), an edge application server discovery function (EASDF), a unified data management (UDM), a unified data repository (UDR), a home subscriber server (HSS), a centralized network configuration (CNC), a network repository function (NRF), a network exposure function (NEF), a local NEF (L-NEF), a binding support function (BSF), an application function (AF), a location management function (LMF), a gateway mobile location center (GMLC), a network data analytics function (NWDAF), etc. It should be noted that only the core network device in the NR system is taken as an example for introduction in the embodiments of the present application, and the specific type of the core network device is not limited. If the name of the core network device mentioned in the embodiments of the present application changes in the subsequent protocol version (for example, 6G), it is also within the protection scope of the present application.

[0139] Optionally, the core network device can be implemented by one or more function modules in one device, or can be implemented by multiple devices together, and the embodiments of the present application do not make a specific limitation. It can be understood that the above function modules can be network elements in a hardware device, can be software function modules running on a dedicated hardware, or can be virtualized function modules instantiated on a platform (for example, a cloud platform).

[0140] For the convenience of understanding, some contents related to the embodiments of the present application are described as follows:

[0141] I. Synchronization signal block (SSB) transmission method in 5G NR

[0142] For a primary cell (PCell) or a primary secondary cell (PScell), the base station must transmit a periodic SSB, and the SSB period needs to be less than or equal to 20 ms to be successfully searched by the initial search terminal.

[0143] For an intra-band secondary cell (SCell), the base station can transmit SSB, at this time, the SSB related parameters are configured when adding the Scell; or can not transmit SSB, at this time, the SSB related parameters are not configured when adding the Scell, and the terminal acquires timing through the SSB on the Pcell.

[0144] For an inter-band Scell, the base station must transmit SSB, and the SSB related parameters are configured when adding the Scell.

[0145] II. Mapping rule of SSB to physical random access opportunity (PRACH Occasion, RO) in 5G NR

[0146] The configuration parameters of PRACH resource and SSB-RO are configured in system information block (SIB) 1 (namely SIB1). In NR, a cell can configure multiple frequency division multiplexing (FDM) PRACH transmission opportunities (Transmission Occasion) or ROs on the time domain position of one transmission physical random access channel (PRACH). At one time, the number of FDM ROs can be {1, 2, 4, 8}, which is determined by the high layer parameter msg1-FDM.

[0147] A random access preamble (Preamble) can only be transmitted on the time domain resource configured by the parameter PRACHConfigurationIndex and the frequency domain resource configured by the parameter msg1-FDM. The PRACH frequency domain resource n RA ∈ {0, 1, …, M-1}, where M is equal to the higher layer parameter msg1-FDM. In the initial access, the PRACH frequency domain resource n RA The RO resource is numbered in ascending order from the lowest frequency in the initial active uplink bandwidth part, otherwise, the PRACH frequency domain resource n RA The RO resource is numbered in ascending order from the lowest frequency in the active uplink bandwidth part. For example, in FIG. 2a, the number of ROs for FDM at one time is 8 (msg1-FDM = 8), and the RO resources are numbered in order from low to high in frequency as RO#0 ~ RO#7.

[0148] In NR, there is an association relationship between RO and the actual transmitted synchronization signal / physical broadcast channel block (SS / PBCH block). The RO is associated with the SSB in the order of frequency domain (from low frequency to high frequency) and then time domain. One SSB can be associated with multiple consecutive ROs, and multiple SSBs can be associated with one RO, in which 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 that one SSB is associated with 8 consecutive ROs, eight represents that 8 SSBs are associated with one RO; {n4, n8, n12, …} represents the number of Preambles associated with each SSB on one RO, for example, n4 represents that the number of Preambles associated with each SSB on one RO is 4, and n8 represents that the number of Preambles associated with each SSB on one RO is 4.

[0149] All the SSBs associated with one round of ROs form a SSB-RO mapping cycle. One SSB-to-RO association period can contain one or more SSB-RO mapping cycles. One SSB-to-RO association pattern period can contain one or more SSB-to-RO association periods. The SSB-to-RO mapping repeats in the association pattern period, and the maximum association pattern period is 160 ms.

[0150] Generally, the base station can use different beams to transmit different SSBs, and the number of SSBs is configured by the ssb-PositionsInBurst parameter, and the maximum number of SSBs is 64 for Frequency Range (FR) 2. The UE selects the RO associated with the SSB with a good signal and the "RO and preamble combination" to transmit Msg1 according to the strength of the received downlink beam / SSB. In this way, the network can determine the SSB selected by the UE according to the received Preamble of the RO and the "RO and preamble combination". And send Msg2 on the downlink beam corresponding to the SSB to ensure the quality of the received downlink signal.

[0151] Taking FIG. 2a as an example, the number of FDM ROs at one time is 8, and the actual number of transmitted SSBs is 4, that is, 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, the UE selects one of RO#0 and RO#1 to send PRACH.

[0152] Taking FIG. 2b as an example, the number of FDM ROs at one time is 2, and the actual number of transmitted SSBs is 8, that is, SSB#0, SSB#1, …, SSB#7. Each 2 SSBs are associated with 1 RO. When multiple SSBs share one RO, the preamble set associated with the multiple SSBs is different, that is, the same preamble cannot belong to the preamble set associated with different SSBs at the same time: taking RO#0 in FIG. 2b as an example, RO#0 has 60 preambles, of which the preambles with indexes 0-29 are associated with SSB#0, and the preambles with indexes 30-59 are associated with SSB#1.

[0153] Before UE transmits PRACH, firstly, according to the received beam (such as SSB) reference signal received power (Reference Signal Received Power, RSRP), select the SSB whose RSRP is higher than the threshold; if there are multiple SSBs whose RSRP is higher than the threshold, the terminal can select any SSB whose RSRP is higher than the threshold; when there is no SSB whose RSRP is higher than the threshold, the UE selects a SSB based on implementation.

[0154] Based on network (Network, NW) configuration, the UE obtains the correspondence between SSB and RO. After selecting the 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 select one of them for PRACH / preamble / Msg1 transmission.

[0155] For example, in the example shown in FIG. 2a, assuming that the UE selects SSB#1, the UE can select one of RO#2 and RO#3 for PRACH / Msg1 transmission; in the example shown in FIG. 2b, assuming that the UE selects SSB#1, the UE can select the available RO closest to the current time among the ROs (RO#0 or 4) associated with SSB#1 for PRACH / Msg1 transmission. In the selected RO, the UE selects one preamble from the preamble set associated with the selected SSB for PRACH transmission. As shown in FIG. 2b, one RO is associated with two SSBs, so the available preamble set associated with the SSB in the RO is divided into two subsets, each corresponding to one SSB. The UE will select a preamble sequence in the preamble subset corresponding to the selected SSB for PRACH / Msg1 transmission.

[0156] Three, Artificial Intelligence (Artificial Intelligence, AI) / Machine Learning (Machine Learning, ML)

[0157] Artificial intelligence has been widely applied in various fields. Integrating artificial intelligence into wireless communication networks can significantly improve technical indicators such as throughput, latency, and user capacity, which is an important task for future wireless communication networks. AI modules have various implementation methods, such as neural networks, decision trees, support vector machines, and Bayesian classifiers. This application takes neural networks as an example for illustration, but does not limit the specific type of AI module.

[0158] Exemplarily, one neural network can be as shown in FIG. 3a, which is composed of neurons, each of which can be as shown in FIG. 3b. Wherein a1, a2, … aK are inputs, w is a weight (multiplicative coefficient), b is a bias (additive coefficient), and σ(.) is an activation function. Common activation functions include Sigmoid, tanh, Rectified Linear Unit (ReLU), etc.

[0159] The parameters of the neural network are optimized by a gradient optimization algorithm. Gradient optimization algorithm is a class of algorithms for minimizing or maximizing an objective function (also known as loss function), which is often a mathematical combination of model parameters and data. For example, given data X and its corresponding label Y, we construct a neural network model f(.). With the model, we can get the predicted output f(x) according to the input x, and can calculate the difference between the predicted value and the true value (f(x)-Y), which is the loss function. The goal is to find appropriate W and b to minimize the value of the above loss function, where the smaller the loss value, the closer the model is to the true situation.

[0160] The common optimization algorithm at present is basically based on error back propagation (BP) algorithm. The basic idea of BP algorithm is that the learning process consists of two processes of forward propagation of signals and backward propagation of errors. When forward propagating, the input sample is transmitted from the input layer, processed layer by layer through each hidden layer, and then transmitted to the output layer. If the actual output of the output layer does not match the expected output, the backward propagation of errors is entered. Error back propagation is to transmit the output error to the input layer through the hidden layer in a certain form, and allocate the error to all units of each layer, so as to obtain the error signal of each layer unit, which is used as the basis for correcting the weight of each unit. The process of adjusting the weight of each layer through forward propagation of signals and backward propagation of errors is repeated. The process of continuously adjusting the weight is the learning and training process of the network. This process continues until the error of the network output is reduced to an acceptable level, or until the preset number of learning times is reached.

[0161] Common optimization algorithms include Gradient Descent, Stochastic Gradient Descent (SGD), mini-batch gradient descent, Momentum, Nesterov (inventor's name, specifically Stochastic Gradient Descent with Momentum), Adaptive Gradient descent (Adagrad), Adadelta, Root Mean Square prop (RMSprop), Adaptive Moment Estimation (Adam), etc.

[0162] These optimization algorithms, when error backpropagation, are based on the error / loss obtained from the loss function, the derivative / partial derivative of the current neuron, the learning rate, the previous gradient / derivative / partial derivative, etc. to get the gradient, and pass the gradient to the previous layer.

[0163] Generally speaking, depending on the type of problem to be solved, the AI algorithm selected and the AI model used also differ. The main method of improving 5G network performance with AI is to enhance or replace the 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. With existing AI tools, neural network construction, training, and verification can be achieved.

[0164] Four, fine-tuning

[0165] In practice, due to insufficient real-time data sets, it is difficult to achieve convergence by directly training neural networks. A common approach is to pre-train the network based on a large amount of offline collected data to achieve convergence. Then use real-time collected data to fine-tune the pre-trained neural network parameters to adapt the neural network to the actual environment. Fine-tuning can be considered as a training process using pre-trained neural network parameters as initialization. In the fine-tuning stage, some layers can be frozen, generally the layers close to the input end are frozen, and the layers close to the output end are activated, which can ensure that the network can still converge. The less data in the fine-tuning stage, the more layers are recommended to be frozen, only a small number of layers close to the output end are fine-tuned.

[0166] Five, generalization of neural networks

[0167] Generalization refers to the ability of a neural network to produce reasonable outputs for data that it has not encountered during the training or learning process. To address the generalization problem caused by the variability of wireless transmission environments, there are two solutions for neural network-based wireless communication systems. The first solution is to train different neural networks under different transmission conditions, obtain multiple sets of neural network parameters, and switch the neural network parameters as the actual environment changes. The second solution is to train a common neural network based on mixed data, and the neural network parameters do not need to be switched as the environment changes. These two modes have their own advantages and disadvantages: the first solution performs well under different transmission conditions, but it requires storing multiple network parameters and switching them as needed, which can cause signaling overhead and frequent switching problems; the second solution only needs to store a set of neural network parameters and does not need to switch, but it cannot achieve optimal performance under each transmission condition. The way the mixed data set is constructed can affect the performance of the second solution.

[0168] Six, label

[0169] In machine learning and deep learning, a label typically refers to the identification or annotation of the true class or target value of a data sample. Labels are used to represent the information that the model should learn and predict. The following examples are used to illustrate this:

[0170] Labels in classification tasks: In classification tasks, labels represent which class a data sample belongs to. For example, in image classification, each image sample has a label representing the class of the object or scene contained in the image, such as "dog" or "cat".

[0171] Labels in object detection: In object detection tasks, labels usually include object location information (such as object bounding boxes) and class information. Each label identifies an object in the image, including its location and class. Labels in regression tasks:

[0172] In regression tasks, labels usually represent continuous or real-valued targets to be predicted. For example, in a house price prediction task, the label can be the actual sales price of a house.

[0173] Labels in sequence labeling: In natural language processing, labels in sequence labeling tasks are usually used for tasks such as part-of-speech tagging and named entity recognition, where labels are used to represent the properties or categories of each word or character in a text sequence.

[0174] Labels are a key component in supervised learning tasks and are used to train machine learning models. Models learn patterns and rules by comparing with real labels in order to make predictions or classifications on unseen data. The quality and accuracy of labels are crucial to the performance of the model.

[0175] Seven, AI Life Cycle Management (LCM)

[0176] The life cycle management of AI / ML models includes multiple AI functional modules: model training, model deployment, model inference, model monitoring, model update. Exemplarily, the specific framework of AI life cycle management can be as shown in FIG. 4.

[0177] (1) Model training

[0178] Performing AI model training, validation and testing, model performance indicators can be generated which can be used as part of the model testing process. If needed, this function is also responsible for data preparation based on the training data provided by the data collection function, such as data pre-processing and cleaning, formatting and conversion.

[0179] Training / Updating model: If there is a model storage function, it is used to transfer the AI model that has been trained, validated and tested to the model storage function, or to transfer the updated version of the model to the model storage function.

[0180] (2) Model management

[0181] Supervising the operation of AI models or AI functions, such as model selection / activation / deactivation / switching / fallback, and feeding back model monitoring performance. This module is also responsible for making decisions based on data received from the data collection module and the inference module to ensure correct inference operation.

[0182] Management instructions: information input by the model management function to the model inference function. Relevant information can include AI models or AI / ML-based functions to select / deactivate / activate / switch models / fallback to non-AI / ML operations (i.e. not dependent on inference process), etc.

[0183] Model transmission request: used to request a model from the model storage function.

[0184] Performance feedback / retraining request: information input by the model training function, such as for model (re)training or update purposes.

[0185] (3) Model inference

[0186] Using data provided by the data collection function (i.e. inference data) as input, providing the output of applying AI models. If needed, the inference function is also responsible for data preparation (e.g. data pre-processing and cleaning, formatting and conversion) based on the inference data provided by the data collection function.

[0187] Inference output: data used by the management function to monitor the performance of AI models or AI / ML functions.

[0188] Eight, AI model

[0189] The AI model of the embodiments of the present application can also be referred to as an AI unit, a machine learning (ML) model, an ML unit, an AI structure, an AI function, an AI feature, a machine learning model, a neural network, a neural network function, a neural network function, etc., or the above-mentioned AI unit can refer to a processing unit capable of implementing a specific algorithm, formula, processing flow, capability, etc. related to AI, or the AI unit can be a processing method, algorithm, function, module or unit for a specific data set, or the AI unit can be a processing method, algorithm, function, module or unit running on AI / ML related hardware such as a graphics processing unit (GPU), a neural processing unit (NPU), a tensor processing unit (TPU), an application-specific integrated circuit (ASIC), etc. The embodiments of the present application do not make specific limitations. Optionally, the specific data set includes at least one of the input and output of the AI unit.

[0190] Optionally, the identifier (i.e. ID) of the AI model can be an AI model identifier, an AI structure identifier, an AI algorithm identifier, or an identifier of a specific data set associated with the AI unit, or an identifier of a specific scene, environment, channel feature, device related to AI / ML, or an identifier of a function, feature, capability or module related to AI / ML. The embodiments of the present application do not make specific limitations.

[0191] Optionally, the index of the AI model can be described in various ways, such as functionality ID (functionality ID) and / or model ID (model ID), model physical ID, model logical ID, model global ID, and model local ID.

[0192] It should be further noted that AI in the embodiments of the present application can also represent machine learning, which has various implementation methods, such as neural networks, decision trees, support vector machines, Bayesian classifiers, etc. The embodiments of the present application do not make specific limitations.

[0193] The transmission control method provided by the embodiments of the present application will be described in detail below in combination with the accompanying drawings and some embodiments and their application scenarios.

[0194] Please refer to FIG. 5, which is a flowchart of a transmission control method provided by the embodiments of the present application. The method can be executed by a first device, as shown in FIG. 5, which includes the following steps:

[0195] Step 501, determining a target result based on a target AI model by the first device;

[0196] 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.

[0197] The first result is used to indicate at least one of the following:

[0198] activating or not activating the first transmission;

[0199] sending an activation signal or not sending the activation signal, the activation signal being used to activate or request to activate the first transmission;

[0200] a number of the first transmission to be activated;

[0201] a range of the first transmission to be activated.

[0202] The second result is used to indicate at least one of the following:

[0203] deactivating or not deactivating the first transmission;

[0204] sending a deactivation signal or not sending the deactivation signal, the deactivation signal being used to deactivate or request to deactivate the first transmission;

[0205] a number of the first transmission to be deactivated;

[0206] a range of the first transmission to be deactivated.

[0207] In the embodiment, the first device can be a terminal, a network-side device, or a server, etc. For example, the terminal can include, but is not limited to, the types of the terminal 11 listed above, the network-side device can include, but is not limited to, the types of the network-side device 12 listed above, the server can be a device for training or prediction or providing AI-related information, or can be a third server, or a device provided by an Over The Top (OTT) service provider, a third-party service provider, or the Internet, etc., and the embodiments of the present application do not make specific limitations thereon.

[0208] The first transmission can be a flexible transmission or an on demand transmission. The flexible transmission or the 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.

[0209] Exemplarily, the first transmission can include, but is not limited to, at least one of the following: a first signal of on demand transmission, a first channel of on demand transmission, a first resource of on demand transmission. Wherein, the first signal can include, but is not limited to, at least one of the following: an on demand synchronization signal, an on demand reference signal, an on demand broadcast signal, an on demand control signal, etc. For example, the on demand synchronization signal can include an on demand SSB, and the on demand reference signal can include, but is not limited to, at least one of the following: an on demand Sounding Reference Signal (SRS), an on demand Channel State Information Reference Signal (CSI-RS), an on demand Tracking Reference Signal (TRS), etc. The first channel can include, but is not limited to, at least one of the following: an on demand Physical Broadcast Channel (PBCH), an on demand Physical Random Access Channel (PRACH), an on demand MsgA Physical Uplink Sharing Channel (PUSCH), an on demand Configured Grant (CG) PUSCH, an on demand control channel, etc. The first resource can include, but is not limited to, at least one of the following: an on demand synchronization signal resource, an on demand reference signal resource, an on demand broadcast signal resource, and an on demand control signal resource, etc. The resource can include at least one of the following: a time-frequency resource, a Demodulation Reference Signal (DMRS) resource, and a sequence for on demand signal transmission. Wherein, the sequence for on demand signal transmission can include, but is not limited to, at least one of the following: a joining sequence, a code division multiplexing sequence, and a DMRS sequence, etc. For ease of description, the first transmission is taken as an on demand SSB for example in the embodiments of the present application.

[0210] The target AI model can include a first AI model or a second AI model, the first AI model is used for activation control of the first transmission, and the second AI model is used for deactivation control of the first transmission. The first result can be a result obtained by the first device performing inference or prediction or processing based on the first AI model, and the second result can be an inference result obtained by the first device performing inference or prediction or processing based on the second AI model.

[0211] The activation of the first transmission can be understood as allowing the first transmission to be sent. Taking the first transmission as an on demand SSB, the activation of the on demand SSB can be understood as allowing the network side device to send the on demand SSB on the corresponding on demand SSB resource.

[0212] The deactivation of the first transmission can be understood as not allowing the first transmission to be sent. Taking the first transmission as an on demand SSB, the deactivation of the on demand SSB can be understood as not allowing the network side device to send the on demand SSB on the corresponding on demand SSB resource.

[0213] It should be noted that the activation of the first transmission or the deactivation of the first transmission can be for all first transmissions, or only for part of the first transmissions. Taking the first transmission as an on demand SSB, the activation of the on demand SSB can be for part of the SSB indexes on the on demand SSB, or for all SSB indexes on the on demand SSB; and the deactivation of the on demand SSB can be for part of the SSB indexes on the on demand SSB, or for all SSB indexes on the on demand SSB.

[0214] The range of the first transmission can include a position range of the first transmission, an index range of the first transmission, and the like. The position range can include, but is not limited to, a cell range, a tracking area (TA) range, or a geographical position range, and the like. For the range of the first transmission to be activated, it can be understood as activating the first transmission in the position range or the first transmission in the index range. For the range of the first transmission to be deactivated, it can be understood as deactivating the first transmission in the position range or the first transmission in the index range. Taking the first transmission as an on demand SSB, the range of the first transmission can include an SSB index range of the on demand SSB.

[0215] The embodiment is described as follows.

[0216] Case one, the first device determines a first result based on a first AI model, the first result is used to indicate at least one of the following:

[0217] activating or not activating the first transmission;

[0218] sending or not sending an activation signal, the activation signal is used to activate or request to activate the first transmission;

[0219] a number of the first transmissions that need to be activated;

[0220] a range of the first transmissions that need to be activated.

[0221] The following is described by taking the first transmission as a downlink transmission as an example:

[0222] Scenario one: if the first device is a terminal, the above-mentioned first result is used to indicate at least one of the following: activating or not activating the first transmission; sending or not sending an activation signal, the activation signal is used to activate or request to activate the first transmission; a number of the first transmissions that need to be activated; a range of the first transmissions that need to be activated.

[0223] For example, if the above-mentioned first result is used to indicate activating the first transmission or sending the activation signal, the terminal sends the activation signal to the network side device, the activation signal is used to activate or request to activate the first transmission; if the above-mentioned first result is used to indicate not activating the first transmission or not sending the activation signal, the terminal can not send the activation signal, the activation signal is used to activate or request to activate the first transmission; if the first result indicates a number of the first transmissions that need to be activated or a range of the first transmissions that need to be activated, the terminal can send the activation signal to the network side device, the activation signal is used to activate or request to activate the first transmission, the activation signal can carry information such as the number of the first transmissions that need to be activated or the range of the first transmissions that need to be activated.

[0224] Scenario two: if the first device is a network side device, the above-mentioned first result is used to indicate at least one of the following: activating or not activating the first transmission; a number of the first transmissions that need to be activated; a range of the first transmissions that need to be activated.

[0225] For example, if the above-mentioned first result is used to indicate activating the first transmission, the network side device can activate the first transmission; if the above-mentioned first result is used to indicate not activating the first transmission, the network side device can not activate the first transmission; if the above-mentioned first result indicates a number of the first transmissions that need to be activated or a range of the first transmissions that need to be activated, the network side device can activate the first transmission based on the number of the first transmissions that need to be activated or the range of the first transmissions that need to be activated.

[0226] Scenario three: if the first device is a server, the server sends the first result to a terminal or a network-side device, wherein, in the case where the server sends the first result to the terminal, the first result is used to indicate at least one of the following: activating or not activating the first transmission; sending an activation signal or not sending the activation signal, the activation signal being used to activate or request to activate the first transmission; the number of the first transmission to be activated; the range of the first transmission to be activated. In the case 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 not activating the first transmission; the number of the first transmission to be activated; the range of the first transmission to be activated.

[0227] It should be noted that the behavior of the terminal or the network-side device after obtaining the first result sent by the server can refer to the related description of the aforementioned scenario one and scenario two, which will not be repeated here.

[0228] Case two: the first device determines a second result based on a second AI model, the second result being used to indicate at least one of the following:

[0229] deactivating or not deactivating the first transmission;

[0230] sending a deactivation signal or not sending the deactivation signal, the deactivation signal being used to deactivate or request to deactivate the first transmission;

[0231] the number of the first transmission to be deactivated;

[0232] the range of the first transmission to be deactivated.

[0233] The following takes the first transmission as a downlink transmission as an example for illustration:

[0234] Scenario four: if the first device is a terminal, the second result is used to indicate at least one of the following: deactivating or not deactivating the first transmission; sending a deactivation signal or not sending the deactivation signal, the deactivation signal being used to deactivate or request to deactivate the first transmission; the number of the first transmission to be deactivated; the range of the first transmission to be deactivated.

[0235] For example, if the second result is used to indicate deactivating the first transmission or sending the deactivation signal, the terminal sends the deactivation signal to the network-side device, the deactivation signal being used to deactivate or request to deactivate the first transmission; if the second result is used to indicate not deactivating the first transmission or not sending the deactivation signal, the terminal can not send the deactivation signal to deactivate or request to deactivate the first transmission; if the second result indicates the number of the first transmission to be deactivated or the range of the first transmission to be deactivated, the terminal can send the deactivation signal to the network-side device, the deactivation signal being used to deactivate or request to deactivate the first transmission, the deactivation signal carrying information such as the number of the first transmission to be deactivated or the range of the first transmission to be deactivated.

[0236] Scenario five: if the first device is a network side device, the second result is used to indicate at least one of the following: deactivation or non-deactivation of the first transmission; the number of the first transmission to be deactivated; the range of the first transmission to be deactivated.

[0237] For example, if the second result is used to indicate deactivation of the first transmission, the network side device can deactivate the first transmission; if the second result is used to indicate non-deactivation of the first transmission, the network side device can not deactivate the first transmission; if the second result indicates the number of the first transmission to be deactivated or the range of the first transmission to be deactivated, the network side device can deactivate the first transmission based on the number of the first transmission to be deactivated or the range of the first transmission to be deactivated.

[0238] Scenario six: if the first device is a server, the server sends the second result to a terminal or a network side device, wherein, in the case that the server sends the second result to the terminal, the second result is used to indicate at least one of the following: deactivation or non-deactivation of the first transmission; sending or not sending a deactivation signal used to deactivate or request to deactivate the first transmission; the number of the first transmission to be deactivated; the range of the first transmission to be deactivated. In the case that the server sends the second result to the network side device, the second result is used to indicate at least one of the following: deactivation or non-deactivation of the first transmission; the number of the first transmission to be deactivated; the range of the first transmission to be deactivated.

[0239] It should be noted that the behavior of the terminal or the network side device after obtaining the second result sent by the server can refer to the relevant description of the aforementioned scenario four and scenario five, which will not be repeated here.

[0240] In the embodiments of the present application, the first device determines a target result based on a target 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: activating or not activating the first transmission; sending an activation signal or not sending the activation signal, the activation signal being used to activate or request to activate the first transmission; the number of the first transmission to be activated; the range of the first transmission to be activated; and the second result is used to indicate at least one of the following: deactivating or not deactivating the first transmission; sending a deactivation signal or not sending the deactivation signal, the deactivation signal being used to deactivate or request to deactivate the first transmission; the number of the first transmission to be deactivated; and the range of the first transmission to be deactivated. That is, the embodiments of the present application control the activation or deactivation of the first transmission based on the AI model. Since the AI model has strong learning and computing capabilities, this is conducive to ensuring the accuracy of the activation or deactivation control of the first transmission, and thus is conducive to improving the resource utilization rate and reducing the energy consumption of the device.

[0241] Optionally, the first device determines the target result based on the target AI model, including:

[0242] The first device determines the target result based on the first input information and the target AI model;

[0243] The first input information includes at least one of the following:

[0244] Time information;

[0245] State information of the terminal;

[0246] State information of the network side device;

[0247] State information of the server;

[0248] At least one of the signal strength and the signal quality measured by the terminal based on the reference signal associated with the second transmission, or a value determined based on at least one of the signal strength and the signal quality measured by the terminal based on the reference signal associated with the second transmission;

[0249] At least one of the signal strength and the 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 the signal quality measured by the terminal based on the second transmission;

[0250] The number of random access failures or the number of access response message receiving failures of the terminal on a physical random access channel (PRACH) corresponding to the third transmission;

[0251] a number of PRACH repetition transmissions by the terminal on the PRACH resource associated with the third transmission;

[0252] first indication information indicating whether the terminal fails in the random access after falling back to the 4-step random access after failing in the 2-step random access on the PRACH resource associated with the third transmission;

[0253] second indication information indicating whether a power at which the terminal transmits the PRACH signal on the PRACH resource associated with the third transmission is greater than or equal to a first threshold value;

[0254] third indication information indicating at least one of whether the terminal receives a first random access response (RAR) message, a number of the first RAR messages received within a first time period, and whether the number of the first RAR messages received within the first time period is greater than or equal to a second threshold value, wherein the first RAR message is a RAR message including a preamble identifier that is not a preamble identifier of the preamble transmitted by the terminal on the PRACH resource associated with the third transmission;

[0255] fourth indication information indicating whether a number of times that the terminal transmits an activation signal is less than or equal to a first number of times, or indicating whether a number of times that the terminal transmits a deactivation signal is less than or equal to a second number of times;

[0256] fifth indication information indicating whether a timing advance (TA) for the activation signal transmission is valid, or indicating whether a TA for the deactivation signal transmission is valid;

[0257] sixth indication information indicating whether an interval between a current time and a time at which the activation signal was last transmitted is greater than or equal to a first interval, or indicating whether an interval between the current time and a time at which the deactivation signal was last transmitted is greater than or equal to a second interval;

[0258] seventh indication information indicating whether an interval between a time at which the first transmission was last activated or deactivated and a current time is greater than or equal to a third interval;

[0259] eighth indication information indicating whether the terminal transmits an activation signal of the fourth transmission, or indicating whether the terminal transmits a deactivation signal of the fourth transmission;

[0260] a ninth indication information, used for indicating whether the fifth transmission has been activated, or used for indicating whether the fifth transmission has been deactivated;

[0261] a tenth indication information, used for indicating whether the terminal detects the sixth transmission;

[0262] burst event information;

[0263] a frequency domain feature of the first transmission;

[0264] a time domain feature of the first transmission;

[0265] a spatial domain feature of the first transmission;

[0266] wherein the second transmission is different from the first transmission, and the third transmission is a transmission associated with a PRACH.

[0267] Exemplarily, the above-mentioned time information can be used for indicating a specific time, for example, 13:25:38, or can be used for indicating a time range, for example, 13:00-14:00, AM or PM, day or night, etc.

[0268] The above-mentioned time information can be timing information obtained through a first radio access technology (RAT), for example, the above-mentioned first RAT can include but is not limited to Bluetooth, Wi-Fi, 3rd generation mobile communication technology (3G), 4th generation mobile communication technology (4G) or 5th generation mobile communication technology (5G), etc.

[0269] The above-mentioned state information of the terminal can be used to reflect the relevant state of the terminal. Optionally, the state information of the terminal can include at least one of the following: position information of the terminal, distribution information of the terminal, moving direction of the terminal, moving speed of the terminal, energy consumption status of the terminal, power status of the terminal, network scenario information of the terminal, environment information of the terminal, perception information of the terminal.

[0270] The above-mentioned position information of the terminal can be a geographic position coordinate of the terminal, for example, a global positioning system (GPS) coordinate, or position range information of the terminal, for example, a street to which the terminal belongs, or position information of the terminal relative to a camping cell or an access cell or a certain TRP or a certain group of TRPs, for example, a direction of due east of the camping cell.

[0271] The distribution information of the terminal can include quantity information of terminals in different areas (e.g., a camping cell or an access cell or a certain TRP or a certain group of TRPs).

[0272] The moving direction of the terminal can be an absolute direction, for example, 40 degrees east of south, or a relative direction, for example, a direction relative to a certain base station.

[0273] The network scenario information of the terminal, for example, indoor hotspot (inH), urban macro (UMa) cell or rural macro (RMa) cell, or homogeneous / isotropic network, i.e., with or without overlapping coverage.

[0274] The environment information of the terminal, for example, weather information.

[0275] The perception information of the terminal, for example, whether there is an obstacle and / or how many obstacles under a beam corresponding to a second transmission (e.g., a normal SSB), or whether there is an obstacle and / or how many obstacles under a beam corresponding to a first transmission, or the quantity of terminals under beams corresponding to the first transmission and the second transmission, etc.

[0276] The state information of the network side device is used to reflect the relevant state of the network side device. Optionally, the state information of the network side device includes at least one of the following: energy consumption status of the network side device, power status of the network side device, environment information of the network side device, and perception information of the network side device.

[0277] The environment information of the network side device, for example, weather information. The perception information of the network side device, for example, whether there is an obstacle and / or how many obstacles under a beam corresponding to a second transmission, or whether there is an obstacle and / or how many obstacles under a beam corresponding to a first transmission, or the quantity of terminals under beams corresponding to the first transmission and the second transmission, etc.

[0278] The state information of the server is used to reflect the relevant state of the server. Optionally, the state information of the server includes at least one of the following: environment information of the server and perception information of the server.

[0279] The environment information of the server, for example, weather information. The perception information of the server, for example, whether there is an obstacle and / or how many obstacles under a beam corresponding to a second transmission, or whether there is an obstacle and / or how many obstacles under a beam corresponding to a first transmission, or the quantity of terminals under beams corresponding to the first transmission and the second transmission, etc.

[0280] The second transmission is different from the first transmission. The second transmission can be a normal transmission, a non-flexible transmission, a non-on-demand transmission, a transmission that does not support activation or deactivation, or the like. Illustratively, the second transmission can include at least one of a second signal, a second channel, and a second resource. The second signal can include, but is not limited to, at least one of a synchronization signal, a reference signal, a broadcast signal, and a control signal, or the like. For example, the synchronization signal can include a normal SSB, and the reference signal can include, but is not limited to, at least one of a normal SRS, a normal CSI-RS, and a normal TRS. The second channel can include, but is not limited to, at least one of a PBCH, a PRACH, a CG PUSCH, a MsgA PUSCH, a control channel, or the like. The second resource can 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, or the like.

[0281] The reference signal associated with the second transmission can include, but is not limited to, at least one of an SSB, a CSI-RS, a TRS, a MsgA, a MsgA PUSCH, a PRACH, and a CG PUSCH, or the like.

[0282] The reference signal can include a reference signal of one cell or a reference signal of multiple cells. The cells can have the same frequency carrier or different frequency carriers, and can be in-band or different bands. The different bands can be continuous or discontinuous. The association of the reference signal to the activated signal or the activated signal resource also includes, but is not limited to, an association between an SSB and an activated signal resource, an association between a CSI-RS and an activated signal resource, an association between a TRS and an activated signal resource, an association between a PRACH resource and an activated signal resource, an association between a MsgA resource and an activated signal resource, an association between a MsgA PUSCH resource and an activated signal resource, and an association between a CG PUSCH and an activated signal resource.

[0283] Illustratively, the signal strength can include a Reference Signal Received Power (RSRP), and the signal quality can include a Reference Signal Received Quality (RSRQ).

[0284] The third transmission is associated with PRACH, and the third transmission is different from the first transmission. The third transmission can be a normal transmission, a non-flexible transmission, a non-on-demand transmission, a transmission without support of activation or deactivation, and the like.

[0285] Exemplarily, the third transmission can include at least one of a third signal, a third channel, and a third resource. The third signal can include, but is not limited to, at least one of a synchronization signal, a reference signal, a broadcast signal, and a control signal, and the like. For example, the synchronization signal can include a normal SSB, and the reference signal can include, but is not limited to, at least one of a normal SRS, a normal CSI-RS, and a normal TRS. The third channel can include, but is not limited to, at least one of a PBCH, a PRACH, a CG PUSCH, a MsgA PUSCH, a control channel, and the like. The third resource can 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, and the like.

[0286] At least one of the first threshold, the second threshold, the first number, the second number, the first interval, and the second interval can be a protocol predefined value or a configured value, for example, a value configured by a network side device.

[0287] The first time period can be one RAR window length, or multiple RAR window lengths, or a window configured by a network, or a window specified by a protocol, for example, 10 ms.

[0288] The second threshold can be configured by a network or specified by a protocol, or related to a number of ROs associated with the second transmission (for example, a normal SSB) and / or a number of configured preambles. For example, the second threshold is the floor of a result of dividing a total number of preambles configured on the RO associated with the normal SSB by a number of ROs associated with the normal SSB.

[0289] Optionally, the fourth transmission can be a transmission associated with the first transmission. Illustratively, the fourth transmission can include at least one of a fourth on demand signal, a fourth on demand channel, and a fourth on demand resource. For example, the fourth transmission can 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), a CSI-RS, a Phase Tracking Reference Signal (PTRS), a MsgA signal / channel, etc.

[0290] Optionally, the fifth transmission can be a transmission associated with the first transmission. Illustratively, the fifth transmission can include at least one of a fifth on demand signal, a fifth on demand channel, and a fifth on demand resource. For example, the fifth transmission can include at least one of paging, a PDSCH, a PDCCH, a PRS, a TRS, a PRACH, a PUCCH, a PUSCH, a CSI-RS, a PTRS, a MsgA signal / channel, etc.

[0291] The fifth transmission can be a transmission associated with the first transmission. Illustratively, the fifth transmission can include at least one of a fifth on demand signal, a fifth on demand channel, and a fifth on demand resource. For example, the fifth transmission can include at least one of paging, a PDSCH, a PDCCH, a PRS, a TRS, a PRACH, a PUCCH, a PUSCH, a CSI-RS, a PTRS, a MsgA signal / channel, etc.

[0292] The sixth transmission can be a transmission associated with the first transmission. Illustratively, the sixth transmission can include at least one of a sixth on demand signal, a sixth on demand channel, and a sixth on demand resource. For example, the sixth transmission can include at least one of an SSB, paging, a PDSCH, a PDCCH, a PRS, a TRS, a PUSCH signal / channel, etc. For example, in a case where an on demand PDCCH has been activated, an on demand SSB can also need to be activated.

[0293] The burst event information is used to indicate a burst event, for example, a concert, an earthquake, etc.

[0294] Exemplarily, the frequency domain feature of the first transmission can include at least one of the following:

[0295] A synchronization raster or a Global Synchronization Channel Number (GSCN) frequency point position where a synchronization signal can exist, for example, a frequency domain position where a synchronization signal can exist defined in a protocol;

[0296] A number of Resource Blocks (RBs) or subcarriers of the synchronization signal.

[0297] Exemplarily, the time domain feature of the first transmission can include a number of time domain symbols of the synchronization signal, or a length of a time window of time domain correlation detection of the synchronization signal, etc.

[0298] It should be noted that, in the case where the target AI model is the first AI model, the fourth indication information is used to indicate whether the number of times of sending the activation signal by the terminal is less than or equal to the first number of times, the fifth indication information is used to indicate whether the TA used for sending the activation signal is valid, the sixth indication information is used to indicate whether the interval between the current time and the time of sending the activation signal last time is greater than or equal to the first interval, the seventh indication information is used to indicate whether the interval between the time of activating the first transmission last time 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. In the case where the target AI model is the second AI model, the fourth indication information is used to indicate whether the number of times of sending the deactivation signal by the terminal is less than or equal to the second number of times, the fifth indication information is used to indicate whether the TA used for sending the deactivation signal is valid, the sixth indication information is used to indicate whether the interval between the current time and the time of sending the deactivation signal last time is greater than or equal to the second interval, the seventh indication information is used to indicate whether the interval between the time of deactivating the first transmission last time 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.

[0299] Specifically, the first device can input the first input information into the target AI model for inference or prediction or processing to obtain a target result.

[0300] In this embodiment, the first device determines the target result based on the first input information and the target AI model, which is beneficial to further improve the accuracy of the activation or deactivation control of the first transmission, and further improve the utilization of resources and reduce the power consumption of the device.

[0301] In some optional embodiments, the first device can receive at least part of the first input information from at least one of the second device and the third device. For example, in the case that the first device is a terminal, the terminal can obtain the state information of the network side device from the network side device, and can obtain the state information of the server from the server; in the case that the first device is a network side device or a server, the network side device or the server can obtain at least one of the following from the terminal: the state information of the terminal; the signal strength and the signal quality measured by the terminal on the reference signal associated with the second transmission, or a value determined according to the signal strength and the signal quality measured by the terminal on the reference signal associated with the second transmission; at least one of the signal strength and the signal quality measured by the terminal based on the second transmission, or a value determined according to at least one of the signal strength and the signal quality measured by the terminal based on the second transmission; the number of random access failures or the number of access response message receiving failures of the terminal on the physical random access channel (PRACH) corresponding to the third transmission; the number of PRACH repeated transmissions of the terminal on the PRACH resource associated with the third transmission; the first indication information; the second indication information; the third indication information; the fourth indication information; the fifth indication information; the sixth indication information; the seventh indication information; the eighth indication information; the ninth indication information; and the tenth indication information.

[0302] Optionally, the trigger condition for using the first AI model for prediction includes at least one of the following:

[0303] The terminal is powered on;

[0304] The terminal performs initial cell search;

[0305] The terminal performs initial cell selection;

[0306] The terminal performs initial search in a legacy manner for a first time length;

[0307] The terminal does not camp on a new cell within a second time period;

[0308] The terminal performs cell reselection;

[0309] The terminal performs cell handover;

[0310] A timer for triggering prediction expires;

[0311] Before a random access trigger;

[0312] before initial access triggering;

[0313] detecting beam failure;

[0314] detecting radio link failure;

[0315] determining, based on at least one of the input information of the first AI model, that prediction using the first AI model is needed.

[0316] Exemplarily, the first time length can be predefined by a protocol or configured by a network side device.

[0317] The new cell can be understood as any cell different from the cell previously camped by the terminal. Exemplarily, the second time period can be within a preset time length from when the terminal attempts to camp on the new cell or within a preset time length from when the terminal performs cell switching.

[0318] The determination, based on at least one of the input information of the first AI model, that prediction using the first AI model is needed, 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 can be unavailable, and at this time, prediction whether the first transmission (e.g., on demand SSB) can be activated is needed.

[0319] Exemplarily, in the case where the first device is a terminal, in the case where the trigger condition for prediction using the first AI model is met, the terminal uses the first AI model to perform prediction and obtains a first result. In the case where the first device is a network side device or a server, the terminal can send twelfth indication information to the network side device or the server in the case where the trigger condition for prediction using the first AI model is met, to trigger the network side device or the server to perform prediction based on the first AI model. Correspondingly, the network side device or the server uses the first AI model to perform prediction and obtains a first result in the case where the twelfth indication information is received.

[0320] In the embodiment, in the case where the trigger condition is met, the first device uses the first AI model to perform prediction and obtains a first result, to perform activation control on the first transmission based on the first result, which can reduce unnecessary activation of the first transmission and is conducive to further reducing device power consumption.

[0321] Optionally, the trigger condition for prediction using the second AI model includes at least one of the following:

[0322] The terminal is powered on;

[0323] The terminal performs initial cell search;

[0324] the terminal performs initial cell selection;

[0325] a duration of initial search of the terminal in a conventional manner exceeds a second duration;

[0326] the terminal does not camp on a new cell within a third time period;

[0327] the terminal performs cell reselection;

[0328] the terminal performs cell handover;

[0329] a timer for triggering prediction expires;

[0330] before a random access is triggered;

[0331] before an initial access is triggered;

[0332] a beam failure is detected;

[0333] a radio link failure is detected;

[0334] an energy consumption of the network-side device exceeds a first threshold;

[0335] an energy consumption of the terminal exceeds a second threshold;

[0336] a power level of the terminal is less than a third threshold;

[0337] determining, based on at least one of input information of the second AI model, that prediction using the second AI model is needed.

[0338] Exemplarily, the second duration can be predefined by a protocol or configured by the network-side device.

[0339] The new cell can be understood as any cell different from a cell previously camped on by the terminal. Exemplarily, the third time period can be within a preset duration from when the terminal attempts to camp on the new cell or within a preset duration from when the terminal performs cell handover.

[0340] Exemplarily, at least one of the first threshold, the second threshold and the third threshold can be predefined by a protocol or configured by the network-side device.

[0341] The determination, based on at least one of input information of the second AI model, that prediction using the second AI model is needed, for example, if a signal strength or signal quality obtained by the terminal measuring a reference signal associated with a second transmission (e.g., normal SSB) is greater than a preset threshold, it indicates that the second transmission is available, at which time it is needed to predict whether the first transmission (e.g., on demand SSB) can be deactivated for power saving.

[0342] Exemplarily, in a case that the first device is a terminal, in a case that the trigger condition for using the second AI model to perform prediction is met, the terminal uses the second AI model to perform prediction to obtain a second result. In a case that the first device is a network-side device or a server, the terminal can send twelfth indication information to the network-side device or the server in a case that the trigger condition for using the second AI model to perform prediction is met, to trigger the network-side device or the server to perform prediction based on the second AI model. Correspondingly, in a case that the twelfth indication information is received, the network-side device or the server uses the second AI model to perform prediction to obtain the second result.

[0343] In the embodiment, in a case that the trigger condition is met, the first device uses the second AI model to perform prediction to obtain a first result, and performs deactivation control on the first transmission based on the second result, which is beneficial to further reduce the power consumption of the device.

[0344] Optionally, after the first device determines the target result based on the target artificial intelligence (AI) model, the method further includes:

[0345] The first device performs a first operation, and the first operation includes at least one of the following:

[0346] sending at least one of the following: at least part of the input information of the target AI model and the target result;

[0347] falling back to a non-AI manner to determine whether to activate or deactivate the first transmission;

[0348] triggering switching of the target AI model;

[0349] triggering retraining of the target AI model;

[0350] triggering supervision of the target AI model.

[0351] Exemplarily, the first device can send at least one of the following to a device used for training of the target AI model: at least part of the input information of the target AI model and the target result, so that the device used for training of the target AI model can fine-tune or update the target AI model based on at least one of the following: at least part of the input information of the target AI model and the target result.

[0352] The non-AI manner can also be referred to as a legacy manner, which means that the AI model is not used to determine the activation or deactivation of the first transmission. It can be understood that the non-AI manner is relative to the determination of the activation or deactivation of the first transmission based on the target AI model.

[0353] The switching of the target AI model is triggered, for example, by replacing input information of the target AI model or replacing the AI model used for the first transmission activation or deactivation control.

[0354] In some optional embodiments, the first device can perform a first operation based on a failure of the target AI model prediction, which is conducive to ensuring the accuracy of the first transmission activation or deactivation control. The target AI model prediction failure can include that the target result is not successfully obtained based on the target AI model, or the target result predicted based on the target AI model is inaccurate, for example, in the case where the target result indicates that the on demand SSB is activated, no terminal selects the on demand SSB beam or the measurement value of the on demand SSB beam is less than a preset value after the network side device activates the on demand SSB.

[0355] Optionally, the fallback to determine whether to activate or deactivate the first transmission in a non-AI manner includes:

[0356] In the case where at least one of the following conditions is met, the fallback to determine whether to activate or deactivate the first transmission in a non-AI manner includes:

[0357] The first device fails to successfully complete the prediction within a third time period.

[0358] The first device fails to successfully complete the prediction using the target AI model.

[0359] In the embodiment, the third time period can be predefined by a protocol, configured by a network side device, or determined by the first device.

[0360] Optionally, the method further includes at least one of the following:

[0361] The first device obtains an index of the target AI model.

[0362] The first device sends the index of the target AI model.

[0363] The index of the target AI model includes at least one of the following:

[0364] The complexity of the target AI model.

[0365] The latency of the target AI model prediction.

[0366] The success rate of the target AI model prediction.

[0367] The reliability of the result output by the target AI model.

[0368] The complexity of the target AI model is defined as different complexity index requirements of the AI model for different types / capabilities of network side devices or terminals or servers. For example, the complexity of the AI model used by a general terminal should not exceed a first value.

[0369] The latency of the prediction of the target AI model can be understood as the time length of the prediction or inference or processing using the target AI model. Specifically, the time length of the prediction or inference or processing using the target AI model should not exceed a first preset time length.

[0370] The success rate of the prediction of the target AI model can be understood as the success rate of the prediction or inference or processing using the target AI model within a certain time length. For example, the success rate of the prediction of the target AI model can be the ratio of the number of successful predictions using the target AI model within a certain time length to the total number of predictions within the certain time length, or the success rate of the prediction of the target AI model can be a value determined according to at least two success rates within at least two certain time lengths, for example, the average of the at least two success rates, and the success rate within each certain time length is the ratio of the number of successful predictions using the target AI model within the certain time length to the total number of predictions within the certain time length. The certain time length can be a protocol predefined time length or a network side device configured time length.

[0371] Specifically, the success rate of the prediction or inference or processing using the target AI model should not be less than a second value.

[0372] In the case of the target AI model being the first AI model, the reliability of the result output by the first AI model can be the probability that the activated first transmission is used and successfully completes a related function such as random access. In the case of the target AI model being the second AI model, the reliability of the result output by the second AI model can be the probability that the first transmission that is not deactivated is used and successfully completes a related 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.

[0373] The first device obtains the index of the target AI model, which includes that the first device determines the index of the target AI model, or the first device receives the index of the target AI model.

[0374] Optionally, the method further includes:

[0375] The first device trains at least part of the target AI model;

[0376] Or,

[0377] The first device receives at least part of the AI model in the target AI model.

[0378] In an embodiment, the first device trains the target AI model and performs inference using the target AI model.

[0379] In another embodiment, the second device trains the target AI model and sends it to the first device, which performs inference using the target AI model.

[0380] In yet another embodiment, the first device trains part of the target AI model, the second device trains another part of the target AI model, and sends the trained AI model parts to the first device, which performs inference using the target AI model.

[0381] In the above, the first device trains part of the target AI model, and the second device trains another part of the target AI model, which can include one of the following:

[0382] The terminal side reports the output of AI model training to the network side device, and the network side device takes the terminal side reported information (i.e. the output of terminal AI model training) as one of the input information of its own AI model training;

[0383] The network side device sends the output of AI model training to the terminal, and the terminal takes the information sent by the network side device (i.e. the output of network side AI model training) as one of the input information of its own AI model training;

[0384] The terminal side or the network side device performs offline AI model training, and the terminal side or the network side device performs fine tuning of the AI model in the actual network.

[0385] In the above, the second device can be a terminal, a network side device or a server.

[0386] Optionally, the trigger type of the target AI model training includes at least one of the following: conditional or event trigger, periodic trigger, and semi-static trigger.

[0387] Optionally, the condition or event triggering the target AI model training includes at least one of the following:

[0388] The configuration information of the first transmission changes;

[0389] The configuration information of the second transmission changes;

[0390] The activation or deactivation mode of the first transmission changes;

[0391] The target AI model fails to predict;

[0392] the target AI model fails to make a prediction for N consecutive times, N being a positive integer;

[0393] the number of times the target AI model fails to make a prediction reaches a fourth threshold;

[0394] a prediction is made using the target AI model;

[0395] the terminal reselects to a new cell;

[0396] a tracking area of the terminal changes;

[0397] an environment in which the terminal is located changes;

[0398] The second transmission is different from the first transmission.

[0399] The first transmission and the second transmission in this embodiment can refer to the related descriptions of the foregoing embodiments, which will not be described here.

[0400] For the first transmission, the activation manner changes, for example, from being activated by the network side device to being activated by sending an activation signal by the terminal. For the first transmission, the deactivation manner changes, for example, from being deactivated by the network side device to being deactivated by sending a deactivation signal by the terminal.

[0401] The target AI model failing to make a prediction can include that a target result is not successfully obtained based on the target AI model, or that the target result predicted based on the target AI model is inaccurate, for example, in the case where the target result indicates that the on demand SSB is activated, after the network side device activates the on demand SSB, no terminal selects the on demand SSB beam or the measurement value of the on demand SSB beam is less than a preset value.

[0402] The environment in which the terminal is located changes, for example, the terminal can obtain change information of the environment through sensing.

[0403] At least one of N, the fourth threshold, and the like can be predefined by a protocol or configured by the network side device.

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

[0405] Or,

[0406] The configuration information of the second transmission includes at least one of the following: the number of the second transmission, 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.

[0407] Taking the first transmission or the second transmission as an SSB, the configuration information can include at least one of the following: the number of SSBs, the index value of SSBs, the beam configuration corresponding to SSBs, the transmission power of SSBs, and the period of SSBs.

[0408] In the embodiment, when the condition or event for triggering the training of the target AI model is met, the first device can perform the training of the target AI model, which can ensure the accuracy of the prediction result based on the target AI model.

[0409] Optionally, the configuration information of the periodic triggering includes at least one of the following: the starting point of the periodic model training, the interval of the periodic model training, the number of model training in a period, and the duration of model training in a period.

[0410] The starting point of the periodic model training, for example, the model training is performed only after the terminal stays in a cell for a period of time.

[0411] The interval of the periodic model training, for example, at least one model training is triggered every interval T.

[0412] Optionally, the semi-static triggering includes at least one of the following:

[0413] The sending and / or activation of the configuration information of the semi-static triggering is triggered based on a specific condition or a specific event;

[0414] The configuration information of the semi-static triggering is configured through radio resource control (RRC), and / or the semi-static training of the model is activated or deactivated through physical control information.

[0415] The physical control information, for example, downlink control information (DCI).

[0416] In some optional embodiments, the target AI model is trained based on target input information, wherein the target input information includes at least one of the following:

[0417] Time information;

[0418] State information of the terminal;

[0419] State information of the network side device;

[0420] state information of the server;

[0421] frequency domain feature of the eleventh transmission;

[0422] time domain feature of the eleventh transmission;

[0423] spatial domain feature of the eleventh transmission;

[0424] at least one of the signal strength and the signal quality obtained by the terminal measuring the reference signal associated with the twelfth transmission, or a value determined according to at least one of the signal strength and the signal quality obtained by the terminal measuring the reference signal associated with the twelfth transmission;

[0425] at least one of the signal strength and the signal quality measured by the terminal based on the twelfth transmission, or a value determined according to at least one of the signal strength and the signal quality measured by the terminal based on the twelfth transmission;

[0426] the number of random access failures or the number of access response message receiving failures of the terminal on a physical random access channel (PRACH) corresponding to the thirteenth transmission;

[0427] the number of PRACH repeated transmissions of the terminal on the PRACH resource associated with the thirteenth transmission;

[0428] the thirteenth indication information, used for indicating whether the terminal fails in the 2-step random access after attempting the 2-step random access on the PRACH resource associated with the thirteenth transmission and then falling back to the 4-step random access;

[0429] the fourteenth indication information, used for indicating whether the power of the PRACH signal sent by the terminal on the PRACH resource associated with the thirteenth transmission is greater than or equal to a first threshold value;

[0430] the fifteenth indication information, used for indicating at least one of the following: whether the terminal receives a second random access response (RAR) message, the number of the second RAR messages received within a first time period, and whether the number of the second RARs received within the first time period is greater than or equal to a second threshold value; wherein the second RAR message is a RAR message including a preamble identifier that is not the preamble identifier sent by the terminal on the PRACH resource associated with the thirteenth transmission;

[0431] the sixteenth indication information, used for indicating whether the number of times of sending an activation signal by the terminal is less than or equal to a first number of times, or used for indicating whether the number of times of sending a deactivation signal by the terminal is less than or equal to a second number of times;

[0432] Seventeenth indication information, used for indicating whether a timing advance (TA) for activating signal transmission is valid, or used for indicating whether a TA for deactivating signal transmission is valid;

[0433] Eighteenth indication information, used for indicating whether an interval between a current time and a time of last time of sending an activating signal is greater than or equal to a first interval, or used for indicating whether an interval between a current time and a time of last time of sending a deactivating signal is greater than or equal to a second interval;

[0434] Nineteenth indication information, used for indicating whether an interval between a time of last time of activating or deactivating the eleventh transmission and a current time is greater than or equal to a third interval;

[0435] Twentieth indication information, used for indicating whether the terminal has sent an activating signal of the fourteenth transmission, or used for indicating whether the terminal has sent a deactivating signal of the fourteenth transmission;

[0436] Twenty-first indication information, used for indicating whether the fifteenth transmission has been activated, or used for indicating whether the fifteenth transmission has been deactivated;

[0437] Twenty-second indication information, used for indicating whether the terminal has detected the sixteenth transmission;

[0438] Burst event information;

[0439] Wherein, the twelfth transmission is different from the eleventh transmission, and the thirteenth transmission is a transmission associated with the PRACH.

[0440] It can be understood that the target input information corresponds to the first input information, and each parameter item of the target input information can refer to the related description of each parameter item of the first input information, which will not be repeated here. In addition, the parameter items included in the first input information can be the same as the parameter items included in the target input information, or the parameter items included in the first input information can be a subset of the parameter items included in the target input information.

[0441] Exemplarily, the target input information can include P times of input information used for determining whether to activate or deactivate the on-demand transmission in the recent P times, and P is a positive integer.

[0442] In some optional embodiments, the label used for training the first AI model includes at least one of the following:

[0443] Activating or not activating the eleventh transmission;

[0444] sending or not sending an activation signal for activating or requesting to activate the eleventh transmission;

[0445] a number of the eleventh transmissions that need to be activated;

[0446] a range of the eleventh transmissions that need to be activated.

[0447] The label for training the second AI model includes at least one of the following:

[0448] deactivating or not deactivating the eleventh transmission;

[0449] sending or not sending a deactivation signal for deactivating or requesting to deactivate the eleventh transmission;

[0450] a number of the eleventh transmissions that need to be deactivated;

[0451] a range of the eleventh transmissions that need to be deactivated.

[0452] Optionally, the method further comprises:

[0453] The first device receives second input information for training the target AI model;

[0454] Or,

[0455] The first device sends third input information for training the target AI model.

[0456] Illustratively, in the case of training the target AI model by the first device, the first device can receive second input information for training the target AI model from the second device. In the case of training the target AI model by the second device, the first device can send third input information to the second device. Wherein the second device can be a terminal, a server or a network side device.

[0457] The second input information can include part or all of the target input information. The third input information can include part or all of the target input information.

[0458] Optionally, the first device is a terminal;

[0459] The first device receives second input information, including:

[0460] The first device receives second input information sent by the network-side device through at least one of the following: a media access control (MAC) control element (CE); an RRC message; a non-access stratum (NAS) message; user plane data; a system information block (SIB); physical layer signaling; a physical downlink shared channel; MSG 2; MSG 4; MSG B;

[0461] Or,

[0462] The first device sends third input information, including at least one of the following:

[0463] The first device sends the third input information to the network-side device through at least one of the following: a MAC CE; an RRC message; a NAS message; user plane data; MSG 1; MSG A; MSG 3; a physical uplink control channel; a physical uplink shared channel; a random access channel; an uplink reference signal;

[0464] The first device sends the third input information to the server through a first interface message.

[0465] The physical layer signaling is, for example, layer 1 signaling of a PDCCH. The uplink reference signal is, for example, a sounding reference signal (SRS) or a wake-up signal (WUS).

[0466] The first interface message is an interface message between the terminal and the server, for example, an OTT interface message.

[0467] Optionally, the first device is a network-side device.

[0468] The first device receives second input information, including:

[0469] The first device receives second input information sent by the terminal through at least one of the following: a MAC CE; an RRC message; a NAS message; user plane data; MSG 1; MSG A; MSG 3; a physical uplink control channel; a physical uplink shared channel; a random access channel; an uplink reference signal;

[0470] Or,

[0471] The first device sends third input information, including at least one of the following:

[0472] The first device sends the third input information to the terminal by at least one of the following: a MAC CE; an RRC message; a layer NAS message; user plane data; DCI information; a SIB; physical layer signaling; a physical downlink shared channel; a MSG 2; a MSG 4; a MSG B.

[0473] The first device sends the third input information to the server through a second interface message.

[0474] The second interface message is an interface message between the network side device and the server.

[0475] Optionally, the first device is a server.

[0476] The first device receives third input information, including:

[0477] The first device receives the third input information from at least one of the terminal and the network side device.

[0478] It can be understood that the server can receive the third input information based on an interface message between the server and the terminal, and the server can receive the third input information based on an interface message between the server and the network side device.

[0479] It can be understood that the third input information received by the server from the terminal and the third input information received by the server from the network side device are different.

[0480] Optionally, the trigger condition for sending or obtaining the second input information or the third input information includes at least one of the following:

[0481] The terminal camps on a cell;

[0482] The terminal initially selects a cell;

[0483] The terminal reselects a cell;

[0484] The terminal enters an RRC connected state;

[0485] The terminal enters an inactive state for a duration reaching a fourth duration.

[0486] Exemplarily, in the case that the first device is a terminal, the first device can send the second input information to the network side device or the server, or can request the network side device or the server to obtain the third input information, when the trigger condition is met; in the case that the first device is a network side device or a server, the terminal can send the third input information to the first device, or the terminal can request the first device to obtain the second input information, when the trigger condition is met.

[0487] The fourth time length can be a protocol predefined time length, or can be a time length configured by a network side device.

[0488] Specifically, in a case where a trigger condition of sending or obtaining the second input information or the third input information is met, the sending or obtaining of the second input information or the third input information can be triggered at least once, for example, periodic or semi-static sending or obtaining of the second input information or the third input information can be triggered.

[0489] Optionally, the determination condition of completion of the first AI model training comprises at least one of the following:

[0490] A loss function used for the first AI model training satisfies a first preset condition;

[0491] In a case where the result output by the first AI model indicates that the seventh transmission is activated, a measurement result measured by the terminal based on the seventh transmission satisfies a second preset condition;

[0492] In a case where the result output by the first AI model indicates that the seventh transmission is activated, a probability that the terminal successfully detects the seventh transmission after the seventh transmission is activated is greater than or equal to a third threshold value;

[0493] In a case where the result output by the first AI model indicates that the seventh transmission is activated, a time length used by the terminal to detect the seventh transmission after the seventh transmission is activated is less than or equal to a fourth threshold value;

[0494] In a case where the result output by the first AI model indicates that the seventh transmission is activated, a probability that the terminal successfully accesses based on the seventh transmission is greater than or equal to a fifth threshold value;

[0495] In a case where the result output by the first AI model indicates that the seventh transmission is not activated, a probability that the terminal successfully accesses based on the eighth transmission is greater than or equal to a sixth threshold value;

[0496] In a case where the result output by the first AI model indicates that the seventh transmission is activated, a probability or frequency that the terminal selects the seventh transmission for random access is greater than or equal to a seventh threshold value;

[0497] In a case where the result output by the first AI model indicates that the seventh transmission is activated, a probability or frequency that the terminal selects the eighth transmission for random access is greater than or equal to an eighth threshold value;

[0498] A training number of the first AI model reaches a first preset value;

[0499] An iteration number of fine tuning of the first AI model reaches a second preset value.

[0500] The loss function for the first AI model training can be related to at least one of:

[0501] a mean square error or a normalized mean square error of the predicted result and the actual result;

[0502] a mean absolute error of the predicted result and the actual result.

[0503] The loss function for the first AI model training satisfies a first preset condition. For example, the loss function for the first AI model training satisfies a predefined index or a predefined value. For example, the error of the training (e.g., the mean square error or the normalized mean square error of the predicted result and the actual result, the mean absolute error of the predicted result and the actual result, etc.) is less than the predefined value.

[0504] The seventh transmission can include at least one of an on demand seventh signal, an on demand seventh channel, and an on demand seventh resource. The on demand seventh signal can include, but is not limited to, at least one of an on demand synchronization signal, an on demand reference signal, an on demand broadcast signal, and an on demand control signal. For example, the on demand synchronization signal can include an on demand SSB, and the on demand reference signal can include, but is not limited to, at least one of an on demand SRS, an on demand CSI-RS, and an on demand TRS. The on demand seventh channel can include, but is not limited to, at least one of an on demand PBCH, an on demand PRACH, an on demand MsgA PUSCH, an on demand CG PUSCH, and an on demand control channel. The on demand seventh resource can include, but is not limited to, at least one of an on demand synchronization signal resource, an on demand reference signal resource, an on demand broadcast signal resource, and an on demand control signal resource. For example, the seventh transmission can be the same as the eleventh transmission in the target input information.

[0505] The measurement result measured based on the seventh transmission can include, but is not limited to, at least one of an RSRP, an RSRQ, a received signal strength indication (RSSI), and a signal noise ratio (SNR). The measurement result satisfies a second preset condition. For example, the RSRP, the RSRQ, the RSSI, or the SNR is greater than or equal to a corresponding threshold.

[0506] At least one of the first preset condition, the second preset condition, the third threshold, the fourth threshold, the fifth threshold, the sixth threshold, the seventh threshold, the eighth threshold, the first preset value, and the second preset value is predefined by a protocol or configured by a network side device.

[0507] The eighth transmission is different from the seventh transmission. The eighth transmission can be a regular transmission or a non-flexible transmission or a non-on-demand transmission or a transmission that does not support activation or deactivation, etc. Illustratively, the eighth transmission can include at least one of an eighth signal, an eighth channel, and an eighth resource. The eighth signal can include, but is not limited to, at least one of a synchronization signal, a reference signal, a broadcast signal, and a control signal, etc. For example, the synchronization signal can include a normal SSB, and the reference signal can include, but is not limited to, at least one of a normal SRS, a normal CSI-RS, and a normal TRS. The eighth channel can include, but is not limited to, at least one of a PBCH, a PRACH, a CG PUSCH, a MsgA PUSCH, a control channel, etc. The eighth resource can 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, etc. Illustratively, the eighth transmission can be the same as the twelfth transmission in the target input information.

[0508] Optionally, the determination condition that the second AI model training is completed includes at least one of the following:

[0509] The loss function used for the second AI model training satisfies a third preset condition;

[0510] In a case where the result output by the second AI model indicates that the ninth transmission is not to be deactivated, the terminal satisfies a fourth preset condition based on a measurement result measured based on the ninth transmission;

[0511] In a case where the result output by the second AI model indicates that the ninth transmission is not to be deactivated, the terminal detects the ninth transmission with a probability greater than or equal to a ninth threshold;

[0512] In a case where the result output by the second AI model indicates that the ninth transmission is not to be deactivated, the terminal detects the ninth transmission for a duration less than or equal to a tenth threshold;

[0513] In a case where the result output by the second AI model indicates that the ninth transmission is not to be deactivated, the terminal has a probability of successful access based on the ninth transmission greater than or equal to an eleventh threshold;

[0514] In a case where the result output by the second AI model indicates that the ninth transmission is to be deactivated, the terminal has a probability of successful access based on the tenth transmission greater than or equal to a twelfth threshold;

[0515] In a case where the result output by the second AI model indicates not to deactivate the ninth transmission, a probability or frequency of the terminal selecting the ninth transmission for random access is greater than or equal to a thirteenth threshold value;

[0516] In a case where the result output by the second AI model indicates to deactivate the ninth transmission, a probability or frequency of the terminal selecting the tenth transmission for random access is greater than or equal to a fourteenth threshold value;

[0517] A number of times of training of the second AI model reaches a third preset value;

[0518] A number of iterations of fine-tuning of the second AI model reaches a fourth preset value.

[0519] The loss function used for training of the second AI model satisfies a third preset condition. For example, the loss function used for training of the second AI model satisfies a predefined index or a predefined value. For example, an error (for example, a mean square error or a normalized mean square error of a predicted result and an actual result, a mean absolute error of a predicted result and a true result, etc.) of training is less than a predefined value.

[0520] The ninth transmission can include at least one of a ninth on-demand signal, a ninth on-demand channel, and a ninth on-demand resource. For example, the ninth on-demand signal can include at least one of an on-demand synchronization signal, an on-demand reference signal, an on-demand broadcast signal, and an on-demand control signal. For example, the on-demand synchronization signal can include an on-demand SSB, and the on-demand reference signal can include at least one of an on-demand SRS, an on-demand CSI-RS, an on-demand TRS, etc. The ninth on-demand channel can include at least one of an on-demand PBCH, an on-demand PRACH, an on-demand MsgA PUSCH, an on-demand CG PUSCH, an on-demand control channel, etc. The ninth on-demand resource can include at least one of an on-demand synchronization signal resource, an on-demand reference signal resource, an on-demand broadcast signal resource, and an on-demand control signal resource, etc. For example, the ninth transmission can be the same as the eleventh transmission in the target input information.

[0521] The measurement result measured based on the ninth transmission can include, but is not limited to, at least one of RSRP, RSRQ, RSSI, SNR, and the like. The measurement result satisfies a fourth preset condition, for example, the RSRP, RSRQ, or RSSI or SNR is greater than or equal to a corresponding threshold.

[0522] At least one of the third preset condition, the fourth preset condition, the ninth threshold, the tenth threshold, the eleventh threshold, the twelfth threshold, the thirteenth threshold, the fourteenth threshold, the third preset value, and the fourth preset value is predefined by a protocol or configured by a network side device.

[0523] The tenth transmission is different from the ninth transmission. The tenth transmission can be a regular transmission, a non-flexible transmission, a non-on-demand transmission, or a transmission that does not support activation or deactivation, and the like. Illustratively, the tenth transmission can include at least one of a tenth signal, a tenth channel, and a tenth resource. The tenth signal can include, but is not limited to, at least one of a synchronization signal, a reference signal, a broadcast signal, a control signal, and the like. For example, the synchronization signal can include a normal SSB. The tenth channel can include, but is not limited to, at least one of a PBCH, a PRACH, a CG PUSCH, a MsgA PUSCH, a control channel, and the like. The tenth resource can 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, and the like. Illustratively, the tenth transmission can be the same as the twelfth transmission in the target input information.

[0524] Optionally, in a case where the target AI model is trained by the first device, the first information of the target AI model is determined according to a type of the first device.

[0525] The first information includes at least one of model information of the target AI model, input information for training of the target AI model, label information for training of the target AI model, and execution mode for training of the target AI model.

[0526] The model information of the target AI model can include a model structure or a model algorithm, and the like. Illustratively, for different types of first devices, the AI model used for AI model training can be different. For example, a first device with weaker capability can not be able to apply a too complex AI model.

[0527] Illustratively, for different types of first devices, the input or label information used for training of the target AI model can be different. For example, the input information used for model training by a first device with weaker capability can be less than the input information used for model training by a first device with stronger capability.

[0528] Exemplarily, the AI model training can be performed in different manners for different types of first devices. For example, for a first device with weak capability, only the second device can be considered to perform the model training, or the first device side only performs a small part of the joint model training. For example, in the case of a terminal as the first device, the model training of data related to user privacy can be performed on the terminal side.

[0529] Exemplarily, the AI model used for model training is different for different types of first devices.

[0530] In some optional embodiments, in the case where 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;

[0531] The first information includes at least one of the following: model information of the target AI model, input information for training of the target AI model, label information for training of the target AI model, and execution manner for training of the target AI model.

[0532] The embodiment determines the first information of the target AI model according to the type of the device used for training the target AI model, which is advantageous to ensure the probability of successful training of the target AI model.

[0533] Optionally, the trigger condition for updating or retraining the target AI model includes at least one of the following:

[0534] The configuration information of the first transmission changes;

[0535] The configuration information of the second transmission changes;

[0536] The activation or deactivation manner of the first transmission changes;

[0537] The terminal moves to a new cell, a new tracking area, or a new geographic location;

[0538] The change amount of the moving speed of the terminal is greater than or equal to a fifth preset value, or the change speed of the moving speed of the terminal is greater than or equal to a sixth preset value;

[0539] The time length from the last model update or retraining reaches a fifth time length;

[0540] The timer for triggering model update or retraining times out;

[0541] M consecutive model supervision occurs or M model supervision is triggered, M being a positive integer;

[0542] The target AI model fails to make a prediction;

[0543] The target AI model fails in prediction for K consecutive times, K being a positive integer;

[0544] The number of times that the target AI model fails in prediction reaches a fifth threshold;

[0545] The target AI model is used for prediction;

[0546] The environment in which the terminal is located changes.

[0547] The configuration information of the first transmission changes, the configuration information of the second transmission changes, the activation or deactivation manner of the first transmission changes, the target AI model fails in prediction, the environment in which the terminal is located changes, and the like in this embodiment can be referred to the related description of the foregoing embodiments, and will not be described here.

[0548] At least one of the fifth preset value, the sixth preset value, the fifth time length, M, K, and the third time length can be predefined by a protocol or configured by a network side device.

[0549] In this embodiment, the target AI model is updated or retrained when the trigger condition for updating or retraining the target AI model is met, which is conducive to ensuring the accuracy of the first transmission activation or deactivation control based on the target AI model.

[0550] In actual application, when the inference environment and the training environment differ greatly, the performance of the first transmission activation or deactivation based on the AI model will become poor, that is, mismatch will occur. Therefore, the actual inference performance of the first transmission activation or deactivation based on the AI model needs to be supervised, and adjustment measures can be triggered according to the model supervision result.

[0551] Optionally, the method further includes:

[0552] The first device obtains a model supervision result of the target AI model;

[0553] Or,

[0554] The first device sends the model supervision result of the target AI model.

[0555] Exemplarily, the model supervision result can include at least one of error information or accuracy information between a prediction result and an actual result of the target AI model, a performance indicator (for example, a cell search delay, a cell camping success rate, a timing error, and the like) of a communication system, model related information (for example, a running time length of the target AI model, or a memory space size occupied by the target AI model) of the target AI model, and the like.

[0556] In an embodiment, the first device can obtain a model supervision result of the target AI model, and then determine whether the target AI model needs to be updated or retrained, or whether the target AI model needs to be switched, based on the model supervision result of the target AI model.

[0557] In another embodiment, the first device can perform model supervision on the target AI model to obtain a model supervision result, and send the model supervision result to a second device, so that the second device determines whether the target AI model needs to be updated or retrained based on the model supervision result of the target AI model. The second device can be a device for training or managing the target AI model, for example, the second device can be a terminal, a network side device or a server.

[0558] Optionally, the first device obtains the model supervision result of the target AI model, including:

[0559] The first device performs model supervision on the target AI model to obtain a model supervision result of the target AI model.

[0560] Or,

[0561] The first device receives the model supervision result of the target AI model.

[0562] For example, the first device can receive the model supervision result of the target AI model from a second device, which can be a device for training or managing the target AI model, for example, the second device can be a terminal, a network side device or a server.

[0563] Optionally, the configuration information for the target AI model supervision includes at least one of the following:

[0564] An AI model identifier that needs to be supervised;

[0565] A model supervision period;

[0566] A model supervision duration;

[0567] Model supervision detection window related information;

[0568] A model supervision trigger condition;

[0569] A model supervision index.

[0570] The model supervision detection window related information can include at least one of the following: a detection window duration and a number of samples for detection.

[0571] The model supervision index, for example, error information or accuracy information between a prediction result and an actual result.

[0572] Optionally, the trigger condition of the target AI model supervision comprises at least one of the following:

[0573] The target AI model supervision index is not met, or the target AI model supervision index does not meet the fifth preset condition, or the duration that the target AI model supervision index is not met reaches the sixth duration, or the duration that the target AI model supervision index does not meet the fifth preset condition reaches the sixth duration.

[0574] The target result of the target AI model does not meet the sixth preset condition, or the duration that the target result of the target AI model does not meet the sixth preset condition reaches the seventh duration.

[0575] At least one of the target AI model indexes is not met, or at least one of the target AI model indexes does not meet the seventh preset condition.

[0576] The target result of the target AI model does not meet the sixth preset condition, for example, the first device uses the target AI model to infer for more than Q duration, and still does not complete a specific function (such as random access) dependent on the first transmission (such as on demand SSB) or the second transmission (such as normal SSB), Q is a duration predefined by a protocol or configured by a network side device; or the first device does not successfully complete AI inference using the target AI model.

[0577] The target AI model index can refer to the related description of the foregoing embodiments, which will not be repeated here.

[0578] At least one of the target AI model indexes is not met, for example, the first device determines to activate the first transmission (such as on demand SSB) or does not deactivate the first transmission based on the target AI model, but the RSRP measured based on the first transmission does not meet the requirement; or the predicted latency of the target AI model exceeds the preset duration.

[0579] Optionally, the target AI model supervision index comprises at least one of the following:

[0580] Error information or accuracy information between the prediction result and the actual result of the target AI model;

[0581] Performance index of a communication system;

[0582] Model related information of the target AI model.

[0583] In the embodiment, the performance index of the communication system is, for example, cell search latency, cell camping success rate, timing error, etc. It should be noted that the performance index of the communication system can be obtained within a monitoring window.

[0584] The model-related information of the target AI model, for example, a running time of the target AI model, or a memory space size occupied by the target AI model.

[0585] Optionally, the method further includes at least one of the following:

[0586] The first device sends AI-related capability information of the first device.

[0587] The first device determines AI-related capability information of a second device.

[0588] The AI-related capability information is used to indicate at least one of the following:

[0589] Possessing or not possessing the capability of training an AI model for predicting activation or deactivation of a target transmission;

[0590] Possessing or not possessing the capability of predicting activation or deactivation of a target transmission by an AI model;

[0591] Possessing or not possessing the capability of sending first auxiliary information for predicting activation or deactivation of a target transmission by an AI model.

[0592] Possessing or not possessing the capability of sending second auxiliary information for training an AI model for predicting activation or deactivation of a target transmission.

[0593] The target transmission can include, but is not limited to, at least one of the following: a signal of on-demand transmission, a channel of on-demand transmission, and a resource of on-demand transmission.

[0594] In an embodiment, the first device can send AI-related capability information of the first device to the second device. For example, in a case where the AI-related capability information of the first device indicates that the first device possesses the capability of training an AI model for predicting activation or deactivation of a target transmission, the second device can determine to train the AI model for predicting activation or deactivation of the target transmission by the first device; in a case where the AI-related capability information of the first device indicates that the first device does not possess the capability of training an AI model for predicting activation or deactivation of a target transmission, the second device can determine to train the AI model for predicting activation or deactivation of the target transmission.

[0595] In another embodiment, the first device can determine the AI-related capability information of the second device, and when the AI-related capability information of the second device indicates that the second device has the capability of training an AI model for predicting the activation or deactivation of the target transmission, the first device can determine to train the AI model for predicting the activation or deactivation of the target transmission by the second device; when the AI-related capability information of the second device indicates that the second device does not have the capability of training an AI model for predicting the activation or deactivation of the target transmission, the first device can determine to train the AI model for predicting the activation or deactivation of the target transmission.

[0596] Optionally, the first device determines the AI-related capability information of the second device, including:

[0597] The first device determines the AI-related capability information of the second device based on at least one of the following:

[0598] The device type of the second device;

[0599] The AI-related capability information indicated by the reference signal;

[0600] The AI-related capability information carried by the control information sent by the second device;

[0601] The AI-related capability information carried by the RRC signaling sent by the second device;

[0602] The AI-related capability information carried by the interface message between the first device and the second device.

[0603] 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 are 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.).

[0604] For the AI-related capability information indicated by the reference signal, for example, the capability of predicting the activation of the target transmission is indicated through the PRACH resource.

[0605] The above-mentioned control information can include uplink control information or physical layer control information, etc.

[0606] The interface message between the first device and the second device can be a specific interface message, which can be only for a specific AI model, or can be for all AI models. Illustratively, in the case that one of the first device and the second device is a terminal and the other is a network-side device, the interface message between the first device and the second device can be an interface message between the terminal and the network-side device. In the case that one of the first device and the second device is a terminal and the other is a server, the interface message between the first device and the second device can be an interface message between the terminal and the server. In the case that one of the first device and the second device is a network-side device and the other is a server, the interface message between the first device and the second device can be an interface message between the network-side device and the server.

[0607] It can be understood that the second device can determine the AI-related capability information of the first device based on at least one of the following:

[0608] a device type of the first device;

[0609] AI-related capability information indicated by a reference signal;

[0610] AI-related capability information carried by control information sent by the first device;

[0611] AI-related capability information carried by RRC signaling sent by the first device;

[0612] AI-related capability information carried by an interface message between the first device and the second device.

[0613] Optionally, the first device is a server, and the method further comprises:

[0614] The server sends the target result to a terminal or a network-side device.

[0615] In the case that the server sends the first result to the terminal, the first result is used to indicate at least one of the following: activation or non-activation of the first transmission; sending or not sending an activation signal, the activation signal being used to activate or request to activate the first transmission; a number of first transmissions to be activated; a range of first transmissions to be activated. In the case that the server sends the first result to the network-side device, the first result is used to indicate at least one of the following: activation or non-activation of the first transmission; a number of first transmissions to be activated; a range of first transmissions to be activated.

[0616] In the case that the server sends the second result to the terminal, the second result is used to indicate at least one of the following: deactivation or non-deactivation of the first transmission; sending or not sending a deactivation signal for deactivating or requesting to deactivate the first transmission; the number of the first transmissions to be deactivated; the range of the first transmissions to be deactivated. In the case that the server sends the second result to the network side device, the second result is used to indicate at least one of the following: deactivation or non-deactivation of the first transmission; the number of the first transmissions to be deactivated; the range of the first transmissions to be deactivated.

[0617] It should be noted that the behavior of the terminal or the network side device after obtaining the first result sent by the server can be referred to the related description of scenario one and scenario two, which will not be repeated here. The behavior of the terminal or the network side device after obtaining the second result sent by the server can be referred to the related description of scenario four and scenario five, which will not be repeated here.

[0618] Please refer to FIG. 6, which is a flow chart of a transmission control method provided by an embodiment of the present application. The method can be executed by a second device, as shown in FIG. 6, including the following steps:

[0619] Step 601, the second device executes a second operation, and the second operation includes at least one of the following:

[0620] Training at least part of the target AI model;

[0621] Sending at least part of the target AI model to the first device;

[0622] Sending first input information to the first device, the first input information being used for prediction of the target AI model;

[0623] Sending second input information to the first device, the second input information being used for training of the target AI model;

[0624] Receiving third input information from the first device, the third input information being used for training of the target AI model;

[0625] Receiving a target result sent by the first device, the target result being a result determined according to the target AI model;

[0626] Receiving a supervision result of the target AI model sent by the first device, or sending a supervision result of the target AI model to the first device;

[0627] Model supervision on the target AI model to obtain a supervision result of the target AI model;

[0628] The eleventh indication information is used to trigger the first device to perform target AI model training.

[0629] The twelfth indication information is used to trigger the first device to perform prediction based on the target AI model.

[0630] The target AI model includes the first AI model or the second AI model.

[0631] The first AI model is used to predict at least one of the following:

[0632] The target transmission is activated or not activated.

[0633] An activation signal is sent or not sent, and the activation signal is used to activate or request to activate the target transmission.

[0634] The number of target transmissions that need to be activated.

[0635] The range of target transmissions that need to be activated.

[0636] The second AI model is used to predict at least one of the following:

[0637] The target transmission is deactivated or not deactivated.

[0638] A deactivation signal is sent or not sent, and the deactivation signal is used to deactivate or request to deactivate the target transmission.

[0639] The number of target transmissions that need to be deactivated.

[0640] The range of target transmissions that need to be deactivated.

[0641] The target transmission can be any on-demand transmission or flexible transmission. Illustratively, the target transmission can include at least one of an on-demand transmitted signal, an on-demand transmitted channel, and an on-demand transmitted resource. The on-demand transmitted signal can include, but is not limited to, at least one of an on-demand synchronization signal, an on-demand reference signal, an on-demand broadcast signal, and an on-demand control signal. For example, the on-demand synchronization signal can include an on-demand SSB, and the on-demand reference signal can include, but is not limited to, at least one of an SRS, a CSI-RS, a TRS, and the like. The on-demand transmitted channel can include, but is not limited to, at least one of an on-demand PBCH, an on-demand PRACH, an on-demand MsgA PUSCH, an on-demand CG PUSCH, an on-demand control channel, and the like. The on-demand transmitted resource can include, but is not limited to, at least one of an on-demand synchronization signal resource, an on-demand reference signal resource, an on-demand broadcast signal resource, and an on-demand control signal resource, and the like.

[0642] Optionally, the at least part of the AI models in the target AI model includes:

[0643] training at least part of the AI models in the target AI model based on target input information;

[0644] The target input information includes at least one of:

[0645] time information;

[0646] state information of the terminal;

[0647] state information of the network-side device;

[0648] state information of the server;

[0649] frequency domain characteristics of the eleventh transmission;

[0650] time domain characteristics of the eleventh transmission;

[0651] spatial domain characteristics of the eleventh transmission;

[0652] at least one of signal strength and signal quality obtained by the terminal measuring a reference signal associated with the twelfth transmission, or a value determined according to at least one of signal strength and signal quality obtained by the terminal measuring a reference signal associated with the twelfth transmission;

[0653] at least one of the signal strength and the signal quality measured by the terminal based on the twelfth transmission, or a value determined by the terminal based on at least one of the signal strength and the signal quality measured by the terminal based on the twelfth transmission;

[0654] a number of random access failures of the terminal on a physical random access channel (PRACH) corresponding to the thirteenth transmission or a number of reception failures of an access response message;

[0655] a number of PRACH repeated transmissions of the terminal on the PRACH resource associated with the thirteenth transmission;

[0656] thirteenth indication information for indicating whether the terminal fails in the 2-step random access after attempting the 2-step random access on the PRACH resource associated with the thirteenth transmission and then falls back to the 4-step random access;

[0657] fourteenth indication information for indicating whether a power of a PRACH signal sent by the terminal on the PRACH resource associated with the thirteenth transmission is greater than or equal to a first threshold value;

[0658] fifteenth indication information for indicating at least one of the following: whether the terminal receives a second random access response (RAR) message, a number of the second RAR messages received within a first time period, and whether the number of the second RARs received within the first time period is greater than or equal to a second threshold value, wherein the second RAR message is a RAR message including a preamble identifier that is not the preamble identifier sent by the terminal on the PRACH resource associated with the thirteenth transmission;

[0659] sixteenth indication information for indicating whether a number of times of sending an activation signal by the terminal is less than or equal to a first number of times, or for indicating whether a number of times of sending a deactivation signal by the terminal is less than or equal to a second number of times;

[0660] seventeenth indication information for indicating whether a timing advance (TA) for sending the activation signal is valid, or for indicating whether a TA for sending the deactivation signal is valid;

[0661] eighteenth indication information for indicating whether an interval between a current time and a time of a previous sending of the activation signal is greater than or equal to a first interval, or for indicating whether an interval between the current time and a time of a previous sending of the deactivation signal is greater than or equal to a second interval;

[0662] nineteenth indication information for indicating whether an interval between a time of a previous activation or deactivation of the eleventh transmission and a current time is greater than or equal to a third interval;

[0663] The twentieth indication information is used for indicating whether the terminal has sent the activation signal of the fourteenth transmission, or is used for indicating whether the terminal has sent the deactivation signal of the fourteenth transmission.

[0664] The twenty-first indication information is used for indicating whether the fifteenth transmission has been activated, or is used for indicating whether the fifteenth transmission has been deactivated.

[0665] The twenty-second indication information is used for indicating whether the terminal has detected the sixteenth transmission.

[0666] The event information of the burst;

[0667] The twelfth transmission is different from the eleventh transmission, and the thirteenth transmission is a transmission associated with the PRACH.

[0668] The eleventh transmission can include at least one of an on demand eleventh signal, an on demand eleventh channel, and an on demand eleventh resource. The on demand eleventh signal can include, but is not limited to, at least one of an on demand synchronization signal, an on demand reference signal, an on demand broadcast signal, and an on demand control signal. For example, the on demand synchronization signal can include an on demand SSB, and the on demand reference signal can include, but is not limited to, at least one of an SRS, a CSI-RS, a TRS, and the like. The eleventh channel can include, but is not limited to, at least one of an on demand PBCH, an on demand PRACH, an on demand MsgA PUSCH, an on demand CG PUSCH, an on demand control channel, and the like. The eleventh resource can include, but is not limited to, at least one of an on demand synchronization signal resource, an on demand reference signal resource, an on demand broadcast signal resource, and an on demand control signal resource.

[0669] The twelfth transmission is different from the eleventh transmission. The twelfth transmission can be a normal transmission, a non-flexible transmission, a non-on-demand transmission, a transmission that does not support activation or deactivation, or the like. Illustratively, the twelfth transmission can include at least one of a twelfth signal, a twelfth channel, and a twelfth resource. The twelfth signal can include, but is not limited to, at least one of a synchronization signal, a reference signal, a broadcast signal, a control signal, or the like. For example, the synchronization signal can include a normal SSB. The twelfth channel can include, but is not limited to, at least one of a PBCH, a PRACH, a CG PUSCH, a MsgA PUSCH, a control channel, or the like. The twelfth resource can include, but is not limited to, at least one of a synchronization signal resource, a reference signal resource, a broadcast signal resource, a control signal resource, or the like.

[0670] The reference signal associated with the twelfth transmission can refer to the related description of the reference signal associated with the second transmission, which will not be repeated here.

[0671] The thirteenth transmission is a transmission associated with a PRACH, which can refer to the related description of the third transmission, which will not be repeated here.

[0672] The fourteenth transmission can refer to the related description of the fourth transmission, which will not be repeated here.

[0673] The fifteenth transmission can refer to the related description of the fifth transmission, which will not be repeated here.

[0674] The sixteenth transmission can refer to the related description of the sixth transmission, which will not be repeated here.

[0675] Optionally, the state information of the terminal includes at least one of the following: position information of the terminal, distribution information of the terminal, moving direction of the terminal, moving speed of the terminal, energy consumption status of the terminal, power status of the terminal, network scene information of the terminal, environment information of the terminal, and perception information of the terminal.

[0676] Alternatively,

[0677] The state information of the network side device includes at least one of the following: energy consumption status of the network side device, power status of the network side device, environment information of the network side device, and perception information of the network side device.

[0678] Alternatively,

[0679] The state information of the server includes at least one of the following: environment information of the server and perception information of the server.

[0680] Optionally, the target AI model is a first AI model, and the sending of the eleventh indication information to the first device comprises:

[0681] The eleventh indication information is sent to the first device in at least one of the following cases:

[0682] The terminal is powered on.

[0683] The terminal performs initial cell search.

[0684] The terminal performs initial cell selection.

[0685] The terminal performs initial search through a traditional method for a first time length.

[0686] The terminal does not camp on a new cell within a second time period.

[0687] The terminal performs cell reselection.

[0688] The terminal performs cell handover.

[0689] A timer for triggering prediction expires.

[0690] Before a random access trigger.

[0691] Before an initial access trigger.

[0692] A beam failure is detected.

[0693] A radio link failure is detected.

[0694] Optionally, the target AI model is a second AI model, and the sending of the eleventh indication information to the first device comprises:

[0695] The eleventh indication information is sent to the first device in at least one of the following cases:

[0696] The terminal is powered on.

[0697] The terminal performs initial cell search.

[0698] The terminal performs initial cell selection.

[0699] The terminal performs initial search through a traditional method for a second time length.

[0700] The terminal does not camp on a new cell within a third time period.

[0701] The terminal performs cell reselection.

[0702] The terminal performs cell handover.

[0703] A timer for triggering prediction expires.

[0704] Before a random access trigger;

[0705] Before an initial access trigger;

[0706] A beam failure is detected;

[0707] A radio link failure is detected;

[0708] Energy consumption of the network-side device exceeds a first threshold;

[0709] Energy consumption of the terminal exceeds a second threshold;

[0710] Battery level of the terminal is less than a third threshold.

[0711] Optionally, the method further comprises:

[0712] The second device receives the indicator of the target AI model from the first device;

[0713] Or,

[0714] The second device sends the indicator of the target AI model to the first device;

[0715] The indicator of the target AI model comprises at least one of the following:

[0716] Complexity of the target AI model;

[0717] Latency predicted by the target AI model;

[0718] Success rate predicted by the target AI model;

[0719] Reliability of the result output by the target AI model.

[0720] Optionally, the trigger type of the target AI model training comprises at least one of the following: conditional or event trigger, periodic trigger, and semi-static trigger.

[0721] Optionally, the condition or event triggering the target AI model training comprises at least one of the following:

[0722] Configuration information of the first transmission changes;

[0723] Configuration information of the second transmission changes;

[0724] Activation or deactivation mode of the first transmission changes;

[0725] The target AI model prediction fails;

[0726] The target AI model fails to predict for N consecutive times, N being a positive integer;

[0727] The number of times of prediction failure of the target AI model reaches a fourth threshold;

[0728] The target AI model is used for prediction;

[0729] The terminal reselects a new cell;

[0730] The tracking area of the terminal changes;

[0731] The environment in which the terminal is located changes;

[0732] The second transmission is different from the first transmission.

[0733] Optionally, the trigger condition for sending or obtaining the second input information or the third input information comprises at least one of the following:

[0734] The terminal camps on a cell;

[0735] The terminal initially selects a cell;

[0736] The terminal reselects a cell;

[0737] The terminal enters an RRC connected state;

[0738] The duration for which the terminal enters an inactive state reaches a fourth duration.

[0739] Optionally, the determination condition for completing the training of the first AI model comprises at least one of the following:

[0740] A loss function used for the training of the first AI model satisfies a first preset condition;

[0741] In a case where the result output by the first AI model indicates activating a seventh transmission, a measurement result measured by the terminal based on the seventh transmission satisfies a second preset condition;

[0742] In a case where the result output by the first AI model indicates activating a seventh transmission, a probability that the terminal successfully detects the seventh transmission after activating the seventh transmission is greater than or equal to a third threshold;

[0743] In a case where the result output by the first AI model indicates activating a seventh transmission, a duration for which the terminal detects the seventh transmission after activating the seventh transmission is less than or equal to a fourth threshold;

[0744] In a case where the result output by the first AI model indicates activating a seventh transmission, a probability that the terminal accesses successfully based on the seventh transmission is greater than or equal to a fifth threshold;

[0745] In a case where the result output by the first AI model indicates not activating a seventh transmission, a probability that the terminal accesses successfully based on an eighth transmission is greater than or equal to a sixth threshold;

[0746] In a case where the result output by the first AI model indicates to activate the seventh transmission, the probability or frequency of the terminal selecting the seventh transmission for random access is greater than or equal to a seventh threshold value;

[0747] In a case where the result output by the first AI model indicates to activate the seventh transmission, the probability or frequency of the terminal selecting the eighth transmission for random access is greater than or equal to an eighth threshold value;

[0748] The number of training times of the first AI model reaches a first preset value;

[0749] The number of iterations of fine-tuning of the first AI model reaches a second preset value.

[0750] Optionally, the determination condition of the completion of the training of the second AI model comprises at least one of the following:

[0751] The loss function used for the training of the second AI model satisfies a third preset condition;

[0752] In a case where the result output by the second AI model indicates not to deactivate the ninth transmission, the measurement result measured by the terminal based on the ninth transmission satisfies a fourth preset condition;

[0753] In a case where the result output by the second AI model indicates not to deactivate the ninth transmission, the probability of the terminal detecting the ninth transmission is greater than or equal to a ninth threshold value;

[0754] In a case where the result output by the second AI model indicates not to deactivate the ninth transmission, the duration for which the terminal detects the ninth transmission is less than or equal to a tenth threshold value;

[0755] In a case where the result output by the second AI model indicates not to deactivate the ninth transmission, the probability of the terminal accessing successfully based on the ninth transmission is greater than or equal to an eleventh threshold value;

[0756] In a case where the result output by the second AI model indicates to deactivate the ninth transmission, the probability of the terminal accessing successfully based on the tenth transmission is greater than or equal to a twelfth threshold value;

[0757] In a case where the result output by the second AI model indicates not to deactivate the ninth transmission, the probability or frequency of the terminal selecting the ninth transmission for random access is greater than or equal to a thirteenth threshold value;

[0758] In a case where the result output by the second AI model indicates to deactivate the ninth transmission, the probability or frequency of the terminal selecting the tenth transmission for random access is greater than or equal to a fourteenth threshold value;

[0759] The number of training times of the second AI model reaches a third preset value;

[0760] The number of iterations of the fine-tuning of the second AI model reaches a fourth preset value.

[0761] Optionally, in a case where the target AI model is trained by the second device, the first information of the target AI model is determined according to a type of the second device.

[0762] The first information includes at least one of the following: model information of the target AI model, input information for training of the target AI model, label information for training of the target AI model, and execution mode for training of the target AI model.

[0763] Optionally, the trigger condition for updating or retraining the target AI model includes at least one of the following:

[0764] The configuration information of the first transmission changes;

[0765] The configuration information of the second transmission changes;

[0766] The activation or deactivation mode of the first transmission changes;

[0767] The terminal moves to a new cell, a new tracking area, or a new geographic location;

[0768] A change amount of a moving speed of the terminal is greater than or equal to a fifth preset value, or a change speed of the moving speed of the terminal is greater than or equal to a sixth preset value;

[0769] A time length from a last model update or retraining reaches a fifth time length;

[0770] A timer for triggering model update or retraining times out;

[0771] M consecutive model supervisions occur or M model supervisions are triggered, M being a positive integer;

[0772] The target AI model fails in prediction;

[0773] The target AI model fails in prediction for K consecutive times, K being a positive integer;

[0774] A number of times that the target AI model fails in prediction reaches a fifth threshold;

[0775] The target AI model is used for prediction;

[0776] An environment in which the terminal is located changes.

[0777] Optionally, the configuration information for the target AI model supervision includes at least one of the following:

[0778] An AI model requiring model supervision is identified;

[0779] A period of model supervision;

[0780] A duration of model supervision;

[0781] Detection window related information of model supervision;

[0782] Trigger conditions of model supervision;

[0783] Indicators of model supervision.

[0784] Optionally, the trigger conditions of the target AI model supervision include at least one of the following:

[0785] The indicators of the target AI model supervision are not met, or the indicators of the target AI model supervision do not meet a fifth preset condition, or a duration in which the indicators of the target AI model supervision are not met reaches a sixth duration, or a duration in which the indicators of the target AI model supervision do not meet the fifth preset condition reaches the sixth duration;

[0786] The target result of the target AI model does not meet a sixth preset condition, or a duration in which the target result of the target AI model does not meet the sixth preset condition reaches a seventh duration;

[0787] At least one of the indicators of the target AI model is not met, or at least one of the indicators of the target AI model does not meet a seventh preset condition.

[0788] Optionally, the indicators of the target AI model supervision include at least one of the following:

[0789] Error information or accuracy information between a prediction result and an actual result of the target AI model;

[0790] Performance indicators of a communication system;

[0791] Model related information of the target AI model.

[0792] Optionally, the method further includes at least one of the following:

[0793] The second device sends AI related capability information of the second device;

[0794] The second device determines AI related capability information of the first device;

[0795] The AI related capability information is used to indicate at least one of the following:

[0796] Possessing or not possessing the capability of training an AI model for predicting target transmission activation or deactivation;

[0797] with or without the capability of predicting the activation or deactivation of the target transmission by the AI model;

[0798] with or without the capability of sending the first assistance information for predicting the activation or deactivation of the target transmission by the AI model;

[0799] with or without the capability of sending the second assistance information for training the AI model for predicting the activation or deactivation of the target transmission.

[0800] It should be noted that the implementation manner of the embodiment can refer to the related description of the embodiment shown in FIG. 5, which will not be repeated here.

[0801] It should be noted that the execution subject of the transmission control method provided by the embodiment of the present application can be a transmission control device. In the embodiment of the present application, the transmission control device is taken as an example to illustrate the transmission control device provided by the embodiment of the present application.

[0802] The embodiment of the present application provides a transmission control device. As an example, the transmission control device can be a communication device or a component in the communication device, such as a chip. The communication device can be a terminal, a network side device, a server, etc. For example, the terminal can include but is not limited to the types of the terminal 11 listed above, the network side device can include but is not limited to the types of the network side device 12 listed above, and the embodiment of the present application is not limited specifically.

[0803] The transmission control apparatus includes a receiving module, a sending module and a processing module. The receiving module, the sending module and the processing module can be implemented by software or by hardware. When implemented by hardware, the processing module can be implemented by a processor. The processor can include a general-purpose processor, a special-purpose processor, etc., such as a central processing unit (CPU), a microprocessor, a digital signal processor (DSP), an artificial intelligent (AI) processor, a graphics processing unit (GPU), an application specific integrated circuit (ASIC), a network processor (NP), a field programmable gate array (FPGA) or other programmable logic devices, a gate circuit, a transistor, a discrete hardware component, etc. The receiving module and the sending module can be implemented by a communication interface, which can include one or more of a transceiver, a pin, a circuit, a bus, a radio frequency unit, etc.

[0804] Specifically, referring to FIG. 7, when the transmission control apparatus is a first device or a component in the first device, the transmission control apparatus 700 includes a processing module 701 configured to determine a target result based on a target artificial intelligent (AI) model.

[0805] 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.

[0806] The first result is used to indicate at least one of the following:

[0807] activating or not activating a first transmission;

[0808] sending or not sending an activation signal, the activation signal being used to activate or request to activate the first transmission;

[0809] a number of the first transmissions that need to be activated;

[0810] a range of the first transmissions that need to be activated;

[0811] The second result is used to indicate at least one of the following:

[0812] deactivating or not deactivating the first transmission;

[0813] sending or not sending a deactivation signal for deactivating or requesting to deactivate the first transmission;

[0814] a number of the first transmissions that need to be deactivated;

[0815] a range of the first transmissions that need to be deactivated.

[0816] Optionally, the processing module is specifically configured to:

[0817] determine a target result based on the first input information and the target AI model;

[0818] The first input information includes at least one of the following:

[0819] time information;

[0820] state information of the terminal;

[0821] state information of the network-side device;

[0822] state information of the server;

[0823] at least one of signal strength and signal quality obtained by the terminal measuring a reference signal associated with the second transmission, or a value determined according to at least one of signal strength and signal quality obtained by the terminal measuring a reference signal associated with the second transmission;

[0824] at least one of signal strength and signal quality measured by the terminal based on the second transmission, or a value determined according to at least one of signal strength and signal quality measured by the terminal based on the second transmission;

[0825] a number of random access failures or a number of access response message receiving failures of the terminal on a physical random access channel (PRACH) corresponding to the third transmission;

[0826] a number of PRACH repeated transmissions of the terminal on a PRACH resource associated with the third transmission;

[0827] first indication information for indicating whether the terminal fails to perform 2-step random access after attempting 2-step random access on the PRACH resource associated with the third transmission and then falls back to 4-step random access;

[0828] second indication information for indicating whether a power of a PRACH signal sent by the terminal on the PRACH resource associated with the third transmission is greater than or equal to a first threshold value;

[0829] a third indication information, the third indication information being used for indicating at least one of the following: whether the terminal receives a first random access response (RAR) message, a number of the first RAR messages received in a first time period, whether the number of the first RAR messages received in the first time period is greater than or equal to a second threshold value, wherein the first RAR message is a RAR message comprising a preamble identifier which is not the preamble identifier sent by the terminal on a PRACH resource of a third transmission association;

[0830] a fourth indication information, the fourth indication information being used for indicating whether a number of times of sending an activation signal by the terminal is less than or equal to a first number of times, or the fourth indication information being used for indicating whether a number of times of sending a deactivation signal by the terminal is less than or equal to a second number of times;

[0831] a fifth indication information, the fifth indication information being used for indicating whether a timing advance (TA) used for sending the activation signal is valid, or the fifth indication information being used for indicating whether a TA used for sending the deactivation signal is valid;

[0832] a sixth indication information, the sixth indication information being used for indicating whether an interval between a current time and a time of sending the activation signal last time is greater than or equal to a first interval, or the sixth indication information being used for indicating whether an interval between the current time and a time of sending the deactivation signal last time is greater than or equal to a second interval;

[0833] a seventh indication information, the seventh indication information being used for indicating whether an interval between a time of activating or deactivating the first transmission last time and a current time is greater than or equal to a third interval;

[0834] an eighth indication information, the eighth indication information being used for indicating whether the terminal sends an activation signal of a fourth transmission, or the eighth indication information being used for indicating whether the terminal sends a deactivation signal of the fourth transmission;

[0835] a ninth indication information, the ninth indication information being used for indicating whether a fifth transmission is activated, or the ninth indication information being used for indicating whether the fifth transmission is deactivated;

[0836] a tenth indication information, the tenth indication information being used for indicating whether the terminal detects a sixth transmission;

[0837] event information of a burst;

[0838] a frequency domain feature of the first transmission;

[0839] a time domain feature of the first transmission;

[0840] a spatial domain feature of the first transmission;

[0841] The second transmission is different from the first transmission, and the third transmission is a transmission associated with a PRACH.

[0842] Optionally, the state information of the terminal includes at least one of the following: position information of the terminal, distribution information of the terminal, moving direction of the terminal, moving speed of the terminal, energy consumption status of the terminal, power status of the terminal, network scenario information of the terminal, environment information of the terminal, and perception information of the terminal.

[0843] Optionally, the state information of the terminal includes at least one of the following: position information of the terminal, distribution information of the terminal, moving direction of the terminal, moving speed of the terminal, energy consumption status of the terminal, power status of the terminal, network scenario information of the terminal, environment information of the terminal, and perception information of the terminal.

[0844] Optionally, the state information of the network side device includes at least one of the following: energy consumption status of the network side device, power status of the network side device, environment information of the network side device, and perception information of the network side device.

[0845] Optionally, the state information of the network side device includes at least one of the following: energy consumption status of the network side device, power status of the network side device, environment information of the network side device, and perception information of the network side device.

[0846] Optionally, the state information of the server includes at least one of the following: environment information of the server and perception information of the server.

[0847] Optionally, the trigger condition for using the first AI model for prediction includes at least one of the following:

[0848] Terminal booting up;

[0849] Terminal performing initial cell search;

[0850] Terminal performing initial cell selection;

[0851] Terminal performing initial search through a traditional way for a time length reaching a first time length;

[0852] Terminal not camping on a new cell in a second time period;

[0853] Terminal performing cell reselection;

[0854] Terminal performing cell handover;

[0855] Timer for triggering prediction expires;

[0856] Before random access triggering;

[0857] Before initial access triggering;

[0858] Beam failure is detected;

[0859] Radio link failure is detected;

[0860] Determining, based on at least one of the input information of the first AI model, that the first AI model needs to be used for prediction.

[0861] Optionally, the triggering condition for using the second AI model for prediction comprises at least one of the following:

[0862] Terminal is powered on;

[0863] Terminal performs initial cell search;

[0864] Terminal performs initial cell selection;

[0865] Terminal performs initial search through a traditional way for a time period exceeding a second time period;

[0866] Terminal does not camp on a new cell for a third time period;

[0867] Terminal performs cell reselection;

[0868] Terminal performs cell handover;

[0869] A timer for triggering prediction expires;

[0870] Before a random access is triggered;

[0871] Before an initial access is triggered;

[0872] Beam failure is detected;

[0873] Radio link failure is detected;

[0874] Energy consumption of a network-side device exceeds a first threshold;

[0875] Energy consumption of the terminal exceeds a second threshold;

[0876] Battery level of the terminal is less than a third threshold;

[0877] At least one of the input information of the second AI model is determined to need to use the second AI model for prediction.

[0878] Optionally, the processing module is further configured to:

[0879] After the target result is determined based on the target artificial intelligence (AI) model, a first operation is performed, and the first operation comprises at least one of the following:

[0880] At least one of the following is sent: at least part of the input information of the target AI model and at least one of the target result;

[0881] Fall back to a non-AI way to determine whether to activate or deactivate the first transmission;

[0882] Trigger switching of the target AI model;

[0883] Trigger retraining of the target AI model;

[0884] triggering supervision of the target AI model.

[0885] Optionally, the fallback to the non-AI manner to determine whether to activate or deactivate the first transmission comprises:

[0886] fallback to the non-AI manner to determine whether to activate or deactivate the first transmission in a case that at least one of the following conditions is met:

[0887] a time length for prediction using the target AI model exceeds a third time length, and the prediction is still not successfully completed;

[0888] the prediction using the target AI model is not successfully completed.

[0889] Optionally, the apparatus further comprises at least one of:

[0890] a receiving module configured to obtain the index of the target AI model;

[0891] a sending module configured to send the index of the target AI model;

[0892] wherein the index of the target AI model comprises at least one of:

[0893] complexity of the target AI model;

[0894] time delay of prediction of the target AI model;

[0895] success rate of prediction of the target AI model;

[0896] reliability of a result output by the target AI model.

[0897] Optionally, the processing module is further configured to train at least part of the target AI models.

[0898] or,

[0899] the apparatus further comprises a receiving module configured to receive at least part of the target AI models.

[0900] Optionally, the trigger type of the training of the target AI model comprises at least one of: conditional or event trigger, periodic trigger, and semi-static trigger.

[0901] Optionally, the condition or event triggering the training of the target AI model comprises at least one of:

[0902] configuration information of the first transmission is changed;

[0903] configuration information of a second transmission is changed;

[0904] The activation or deactivation mode of the first transmission is changed;

[0905] The target AI model fails to make a prediction;

[0906] The target AI model fails to make a prediction for N consecutive times, N being a positive integer;

[0907] The number of times that the target AI model fails to make a prediction reaches a fourth threshold;

[0908] The target AI model is used to make a prediction;

[0909] The terminal reselects to a new cell;

[0910] The tracking area of the terminal changes;

[0911] The environment in which the terminal is located changes;

[0912] The second transmission is different from the first transmission.

[0913] Optionally, the configuration information of the first transmission includes at least one of the following: the number of the first transmission, 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.

[0914] Or,

[0915] The configuration information of the second transmission includes at least one of the following: the number of the second transmission, 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.

[0916] Optionally, the configuration information of the periodic triggering includes at least one of the following: the starting point of the periodic model training, the interval of the periodic model training, the number of model training in a period, and the duration of model training in a period.

[0917] Optionally, the semi-static triggering includes at least one of the following:

[0918] The sending and / or activation of the configuration information of the semi-static triggering is triggered based on a specific condition or a specific event;

[0919] The configuration information of the semi-static triggering is configured through radio resource control (RRC), and / or the semi-static training of the model is activated or deactivated through physical control information.

[0920] Optionally, the apparatus further includes:

[0921] The receiving module is configured to receive second input information, the second input information being used for training of the target AI model.

[0922] Or,

[0923] The sending module is configured to send third input information, where the third input information is used for training of the target AI model.

[0924] Optionally, the receiving module is specifically configured to:

[0925] The receiving module is configured to receive second input information sent by the network-side device through at least one of the following: a medium access control control element (MAC CE), a radio resource control (RRC) message, a non-access stratum (NAS) message, user plane data, a system information block (SIB), physical layer signaling, a physical downlink shared channel (PDSCH), MSG 2, MSG 4, and MSG B.

[0926] Or,

[0927] The sending module is specifically configured to at least one of the following:

[0928] The sending module is configured to send the third input information to the network-side device through at least one of the following: a MAC CE, an RRC message, a NAS message, user plane data, MSG 1, MSG A, MSG 3, a physical uplink control channel (PUCCH), a physical uplink shared channel (PUSCH), a random access channel (RACH), and an uplink reference signal (UL RS).

[0929] The sending module is configured to send the third input information to the server through a first interface message.

[0930] Optionally, the receiving module is specifically configured to:

[0931] The first device receives second input information sent by the terminal through at least one of the following: a MAC CE, an RRC message, a NAS message, user plane data, MSG 1, MSG A, MSG 3, a PUCCH, a PUSCH, a RACH, and an UL RS.

[0932] Or,

[0933] The sending module is specifically configured to at least one of the following:

[0934] The sending module is configured to send the third input information to the terminal through at least one of the following: a MAC CE, an RRC message, a NAS message, user plane data, DCI information, a SIB, physical layer signaling, a PDSCH, MSG 2, MSG 4, and MSG B.

[0935] The first device sends the third input information to the server through a second interface message.

[0936] Optionally, the receiving module is specifically configured to:

[0937] The receiving module is configured to receive third input information from at least one of the terminal and the network-side device.

[0938] Optionally, the trigger condition for sending or obtaining the second input information or the third input information comprises at least one of the following:

[0939] The terminal camps on a cell;

[0940] The terminal initially selects a cell;

[0941] The terminal reselects a cell;

[0942] The terminal enters an RRC connected state;

[0943] The duration that the terminal enters an inactive state reaches a fourth duration.

[0944] Optionally, the determination condition that the first AI model training is completed comprises at least one of the following:

[0945] A loss function used for the first AI model training satisfies a first preset condition;

[0946] In a case where the result output by the first AI model indicates activating a seventh transmission, a measurement result measured by the terminal based on the seventh transmission satisfies a second preset condition;

[0947] In a case where the result output by the first AI model indicates activating a seventh transmission, a probability that the terminal successfully detects the seventh transmission after activating the seventh transmission is greater than or equal to a third threshold value;

[0948] In a case where the result output by the first AI model indicates activating a seventh transmission, a duration that the terminal detects the seventh transmission after activating the seventh transmission is less than or equal to a fourth threshold value;

[0949] In a case where the result output by the first AI model indicates activating a seventh transmission, a probability that the terminal accesses successfully based on the seventh transmission is greater than or equal to a fifth threshold value;

[0950] In a case where the result output by the first AI model indicates not activating a seventh transmission, a probability that the terminal accesses successfully based on an eighth transmission is greater than or equal to a sixth threshold value;

[0951] In a case where the result output by the first AI model indicates activating a seventh transmission, a probability or frequency that the terminal selects the seventh transmission for random access is greater than or equal to a seventh threshold value;

[0952] In a case where the result output by the first AI model indicates activating a seventh transmission, a probability or frequency that the terminal selects an eighth transmission for random access is greater than or equal to an eighth threshold value;

[0953] The number of times of training of the first AI model reaches a first preset value;

[0954] The iteration number of the fine-tuning of the first AI model reaches a second preset value.

[0955] Optionally, the determination condition that the second AI model training is completed comprises at least one of the following:

[0956] The loss function for the second AI model training satisfies a third preset condition;

[0957] In a case where the result output by the second AI model indicates not to deactivate the ninth transmission, the terminal detects that the probability that the ninth transmission is detected is greater than or equal to a ninth threshold value;

[0958] In a case where the result output by the second AI model indicates not to deactivate the ninth transmission, the terminal detects that the duration for which the ninth transmission is detected is less than or equal to a tenth threshold value;

[0959] In a case where the result output by the second AI model indicates not to deactivate the ninth transmission, the terminal detects that the probability that the ninth transmission is accessed successfully is greater than or equal to an eleventh threshold value;

[0960] In a case where the result output by the second AI model indicates to deactivate the ninth transmission, the terminal detects that the probability that the tenth transmission is accessed successfully is greater than or equal to a twelfth threshold value;

[0961] In a case where the result output by the second AI model indicates not to deactivate the ninth transmission, the probability or frequency that the terminal selects the ninth transmission for random access is greater than or equal to a thirteenth threshold value;

[0962] In a case where the result output by the second AI model indicates to deactivate the ninth transmission, the probability or frequency that the terminal selects the tenth transmission for random access is greater than or equal to a fourteenth threshold value;

[0963] The training number of the second AI model reaches a third preset value;

[0964] The iteration number of the fine-tuning of the second AI model reaches a fourth preset value.

[0965] Optionally, in a case where the target AI model is trained by a first device, the first information of the target AI model is determined according to the type of the first device;

[0966]

[0967] ​The first information includes at least one of the following: model information of the target AI model, input information for training of the target AI model, label information for training of the target AI model, and execution mode for training of the target AI model.

[0968] Optionally, the trigger condition for updating or retraining the target AI model includes at least one of the following:

[0969] The configuration information of the first transmission changes;

[0970] The configuration information of the second transmission changes;

[0971] The activation or deactivation mode of the first transmission changes;

[0972] The terminal moves to a new cell, a new tracking area, or a new geographic location;

[0973] The change amount of the moving speed of the terminal is greater than or equal to a fifth preset value, or the change speed of the moving speed of the terminal is greater than or equal to a sixth preset value;

[0974] The time length from the last model update or retraining reaches a fifth time length;

[0975] A timer for triggering model update or retraining expires;

[0976] M consecutive model supervisions occur or M model supervisions are triggered, where M is a positive integer;

[0977] The target AI model fails in prediction;

[0978] The target AI model fails in prediction for K consecutive times, where K is a positive integer;

[0979] The number of times that the target AI model fails in prediction reaches a fifth threshold;

[0980] The target AI model is used for prediction;

[0981] The environment in which the terminal is located changes.

[0982] Optionally, the processing module is further configured to obtain a model supervision result of the target AI model.

[0983] Or,

[0984] The apparatus further includes a sending module configured to send the model supervision result of the target AI model.

[0985] Optionally, the processing module is specifically configured to:

[0986] The target AI model is subjected to model supervision to obtain a model supervision result of the target AI model.

[0987] Or,

[0988] The model supervision result of the target AI model is received.

[0989] Optionally, the configuration information for the target AI model supervision comprises at least one of the following:

[0990] An AI model identifier that needs to be subjected to model supervision;

[0991] A model supervision period;

[0992] A model supervision duration;

[0993] Model supervision detection window related information;

[0994] A model supervision trigger condition;

[0995] A model supervision index.

[0996] Optionally, the trigger condition of the target AI model supervision comprises at least one of the following:

[0997] The target AI model supervision index is not met, or the target AI model supervision index does not meet a fifth preset condition, or a duration in which the target AI model supervision index is not met reaches a sixth duration, or a duration in which the target AI model supervision index does not meet the fifth preset condition reaches the sixth duration;

[0998] The target result of the target AI model does not meet a sixth preset condition, or a duration in which the target result of the target AI model does not meet the sixth preset condition reaches a seventh duration;

[0999] At least one of the target AI model indexes is not met, or at least one of the target AI model indexes does not meet a seventh preset condition.

[1000] Optionally, the target AI model supervision index comprises at least one of the following:

[1001] Error information or accuracy information between a prediction result and an actual result of the target AI model;

[1002] A performance index of a communication system;

[1003] Model related information of the target AI model.

[1004] Optionally, the apparatus further comprises a sending module configured to send AI related capability information of the first device.

[1005] or,

[1006] The processing module is further configured to determine AI-related capability information of the second device.

[1007] The AI-related capability information is used to indicate at least one of the following:

[1008] Possessing or not possessing the capability of training an AI model for predicting activation or deactivation of the target transmission;

[1009] Possessing or not possessing the capability of predicting activation or deactivation of the target transmission by the AI model;

[1010] Possessing or not possessing the capability of sending first assistance information, the first assistance information being used to predict activation or deactivation of the target transmission by the AI model;

[1011] Possessing or not possessing the capability of sending second assistance information, the second assistance information being used to train the AI model for predicting activation or deactivation of the target transmission.

[1012] Optionally, the processing module is specifically configured to:

[1013] Determine the AI-related capability information of the second device based on at least one of the following:

[1014] The device type of the second device;

[1015] AI-related capability information indicated by a reference signal;

[1016] AI-related capability information carried by control information sent by the second device;

[1017] AI-related capability information carried by RRC signaling sent by the second device;

[1018] AI-related capability information carried by an interface message between the first device and the second device.

[1019] Optionally, the apparatus further includes:

[1020] A sending module configured to send the target result to a terminal or a network-side device.

[1021] The transmission control apparatus provided by the embodiments of the present application can implement each process implemented by the method embodiment of FIG. 5 and achieve the same technical effects. To avoid repetition, details are not described herein.

[1022] Referring to FIG. 8, when the transmission control apparatus is a second device or a component in the second device, the transmission control apparatus 800 includes a processing module 801 configured to perform a second operation, the second operation including at least one of the following:

[1023] training at least part of the AI model in the target AI model;

[1024] sending at least part of the AI model in the target AI model to the first device;

[1025] sending first input information to the first device, the first input information being used for prediction of the target AI model;

[1026] sending second input information to the first device, the second input information being used for training of the target AI model;

[1027] receiving third input information from the first device, the third input information being used for training of the target AI model;

[1028] receiving a target result sent by the first device, the target result being a result determined according to the target AI model;

[1029] receiving a supervision result of the target AI model sent by the first device, or sending a supervision result of the target AI model to the first device;

[1030] model supervising the target AI model to obtain a supervision result of the target AI model;

[1031] sending eleventh indication information to the first device, the eleventh indication information being used for triggering the first device to train the target AI model;

[1032] sending twelfth indication information to the first device, the twelfth indication information being used for triggering the first device to make prediction based on the target AI model;

[1033] wherein the target AI model comprises a first AI model or a second AI model;

[1034] the first AI model is used for predicting at least one of the following;

[1035] activating or not activating a target transmission;

[1036] sending an activation signal or not sending an activation signal, the activation signal being used for activating or requesting to activate a target transmission;

[1037] a number of target transmissions that need to be activated;

[1038] a range of target transmissions that need to be activated;

[1039] the second AI model is used for predicting at least one of the following;

[1040] deactivating or not deactivating a target transmission;

[1041] sending or not sending a deactivation signal for deactivating or requesting to deactivate the target transmission;

[1042] a number of target transmissions to be deactivated;

[1043] a range of target transmissions to be deactivated.

[1044] Optionally, the processing module is specifically configured to:

[1045] training at least part of the AI models in the target AI model based on target input information;

[1046] The target input information includes at least one of the following:

[1047] time information;

[1048] state information of the terminal;

[1049] state information of the network side device;

[1050] state information of the server;

[1051] frequency domain feature of the eleventh transmission;

[1052] time domain feature of the eleventh transmission;

[1053] spatial domain feature of the eleventh transmission;

[1054] at least one of signal strength and signal quality obtained by the terminal measuring a reference signal associated with the twelfth transmission, or a value determined according to at least one of signal strength and signal quality obtained by the terminal measuring a reference signal associated with the twelfth transmission;

[1055] at least one of signal strength and signal quality measured by the terminal based on the twelfth transmission, or a value determined according to at least one of signal strength and signal quality measured by the terminal based on the twelfth transmission;

[1056] number of random access failures or number of access response message receiving failures of the terminal on a physical random access channel (PRACH) corresponding to the thirteenth transmission;

[1057] number of PRACH repeated transmissions of the terminal on a PRACH resource associated with the thirteenth transmission;

[1058] thirteenth indication information for indicating whether the terminal fails to perform random access after falling back to 4-step random access after failing to attempt 2-step random access on the PRACH resource associated with the thirteenth transmission;

[1059] fourteenth indication information, used for indicating whether a power of the terminal sending the PRACH signal on the PRACH resource associated with the thirteenth transmission is greater than or equal to a first threshold value;

[1060] fifteenth indication information, used for indicating at least one of the following: whether the terminal receives a second random access response (RAR) message, a number of the second RAR messages received within a first time period, whether the number of the second RARs received within the first time period is greater than or equal to a second threshold value; wherein the second RAR message is a RAR message including a preamble identifier which is not the preamble identifier sent by the terminal on the PRACH resource associated with the thirteenth transmission;

[1061] sixteenth indication information, used for indicating whether a number of times of sending the activation signal by the terminal is less than or equal to a first number of times, or used for indicating whether a number of times of sending the deactivation signal by the terminal is less than or equal to a second number of times;

[1062] seventeenth indication information, used for indicating whether a timing advance (TA) used for sending the activation signal is valid, or used for indicating whether a TA used for sending the deactivation signal is valid;

[1063] eighteenth indication information, used for indicating whether an interval between a current time and a time of sending the activation signal last time is greater than or equal to a first interval, or used for indicating whether an interval between the current time and a time of sending the deactivation signal last time is greater than or equal to a second interval;

[1064] nineteenth indication information, used for indicating whether an interval between a time of activating or deactivating the eleventh transmission last time and a current time is greater than or equal to a third interval;

[1065] twentieth indication information, used for indicating whether the terminal sends the activation signal of the fourteenth transmission, or used for indicating whether the terminal sends the deactivation signal of the fourteenth transmission;

[1066] twenty-first indication information, used for indicating whether the fifteenth transmission is activated, or used for indicating whether the fifteenth transmission is deactivated;

[1067] twenty-second indication information, used for indicating whether the terminal detects the sixteenth transmission;

[1068] burst event information;

[1069] The twelfth transmission is different from the eleventh transmission, and the thirteenth transmission is a transmission associated with a PRACH.

[1070] Optionally, the state information of the terminal comprises at least one of the following: position information of the terminal, distribution information of the terminal, moving direction of the terminal, moving speed of the terminal, energy consumption status of the terminal, power status of the terminal, network scenario information of the terminal, environment information of the terminal, and perception information of the terminal.

[1071] Optionally, the state information of the terminal comprises at least one of the following: position information of the terminal, distribution information of the terminal, moving direction of the terminal, moving speed of the terminal, energy consumption status of the terminal, power status of the terminal, network scenario information of the terminal, environment information of the terminal, and perception information of the terminal.

[1072] Optionally, the state information of the terminal comprises at least one of the following: position information of the terminal, distribution information of the terminal, moving direction of the terminal, moving speed of the terminal, energy consumption status of the terminal, power status of the terminal, network scenario information of the terminal, environment information of the terminal, and perception information of the terminal.

[1073] Optionally, the state information of the terminal comprises at least one of the following: position information of the terminal, distribution information of the terminal, moving direction of the terminal, moving speed of the terminal, energy consumption status of the terminal, power status of the terminal, network scenario information of the terminal, environment information of the terminal, and perception information of the terminal.

[1074] Optionally, the state information of the terminal comprises at least one of the following: position information of the terminal, distribution information of the terminal, moving direction of the terminal, moving speed of the terminal, energy consumption status of the terminal, power status of the terminal, network scenario information of the terminal, environment information of the terminal, and perception information of the terminal.

[1075] Optionally, the target AI model is a first AI model, and the sending of the eleventh indication information to the first device comprises:

[1076] The eleventh indication information is sent to the first device in at least one of the following cases:

[1077] The terminal is powered on;

[1078] The terminal performs initial cell search;

[1079] The terminal performs initial cell selection;

[1080] The terminal performs initial search through a traditional method for a first time length;

[1081] The terminal does not camp on a new cell within a second time period;

[1082] The terminal performs cell reselection;

[1083] The terminal performs cell handover;

[1084] A timer for triggering prediction expires;

[1085] Before a random access trigger;

[1086] Before an initial access trigger;

[1087] A beam failure is detected;

[1088] A radio link failure is detected.

[1089] Optionally, the target AI model is a second AI model, and the sending of the eleventh indication information to the first device comprises:

[1090] The eleventh indication information is sent to the first device in at least one of the following cases:

[1091] The terminal is powered on.

[1092] The terminal performs initial cell search.

[1093] The terminal performs initial cell selection.

[1094] The terminal performs initial search through a traditional method for a time period longer than a second time period.

[1095] The terminal does not camp on a new cell within a third time period.

[1096] The terminal performs cell reselection.

[1097] The terminal performs cell handover.

[1098] A timer for triggering prediction expires.

[1099] Before a random access trigger.

[1100] Before an initial access trigger.

[1101] Beam failure is detected.

[1102] Radio link failure is detected.

[1103] Energy consumption of the network side device exceeds a first threshold.

[1104] Energy consumption of the terminal exceeds a second threshold.

[1105] The terminal has an amount of power less than a third threshold.

[1106] Optionally, the apparatus further comprises:

[1107] A receiving module configured to receive an index of the target AI model from the first device.

[1108] Or,

[1109] A sending module configured to send the index of the target AI model to the first device.

[1110] The index of the target AI model comprises at least one of the following:

[1111] Complexity of the target AI model.

[1112] Latency of prediction of the target AI model.

[1113] A success rate of the target AI model prediction;

[1114] A reliability of a result output by the target AI model.

[1115] Optionally, the trigger type of the target AI model training includes at least one of the following: conditional or event trigger, periodic trigger, and semi-static trigger.

[1116] Optionally, the condition or event triggering the target AI model training includes at least one of the following:

[1117] The configuration information of the first transmission changes;

[1118] The configuration information of the second transmission changes;

[1119] The activation or deactivation mode of the first transmission changes;

[1120] The target AI model prediction fails;

[1121] The target AI model fails to predict for N consecutive times, N being a positive integer;

[1122] The number of times of the target AI model prediction failure reaches a fourth threshold;

[1123] The target AI model is used for prediction;

[1124] The terminal reselects a new cell;

[1125] The tracking area of the terminal changes;

[1126] The environment in which the terminal is located changes;

[1127] The second transmission is different from the first transmission.

[1128] Optionally, the trigger condition of the second input information or the third input information sending or obtaining includes at least one of the following:

[1129] The terminal camps on a cell;

[1130] The terminal initially selects a cell;

[1131] The terminal reselects a cell;

[1132] The terminal enters an RRC connected state;

[1133] The terminal enters an inactive state for a fourth time length.

[1134] Optionally, the determination condition of the first AI model training completion includes at least one of the following:

[1135] The loss function used for the first AI model training satisfies a first preset condition.

[1136] In a case where the result output by the first AI model indicates activating the seventh transmission, the terminal succeeds in detecting the seventh transmission after activating the seventh transmission with a probability greater than or equal to a third threshold value;

[1137] In a case where the result output by the first AI model indicates activating the seventh transmission, the terminal succeeds in detecting the seventh transmission after activating the seventh transmission with a probability greater than or equal to a third threshold value;

[1138] In a case where the result output by the first AI model indicates activating the seventh transmission, the terminal succeeds in detecting the seventh transmission after activating the seventh transmission with a probability greater than or equal to a third threshold value;

[1139] In a case where the result output by the first AI model indicates activating the seventh transmission, the terminal succeeds in detecting the seventh transmission after activating the seventh transmission with a probability greater than or equal to a third threshold value;

[1140] In a case where the result output by the first AI model indicates not activating the seventh transmission, the terminal succeeds in accessing based on the eighth transmission with a probability greater than or equal to a sixth threshold value;

[1141] In a case where the result output by the first AI model indicates activating the seventh transmission, the terminal selects the seventh transmission for random access with a probability or frequency greater than or equal to a seventh threshold value;

[1142] In a case where the result output by the first AI model indicates activating the seventh transmission, the terminal selects the eighth transmission for random access with a probability or frequency greater than or equal to an eighth threshold value;

[1143] The number of times of training of the first AI model reaches a first preset value;

[1144] The number of iterations of fine-tuning of the first AI model reaches a second preset value.

[1145] Optionally, the determination condition of completion of the second AI model training includes at least one of the following:

[1146] The loss function used for the second AI model training satisfies a third preset condition;

[1147] In a case where the result output by the second AI model indicates not deactivating the ninth transmission, the terminal succeeds in detecting the ninth transmission with a probability greater than or equal to a ninth threshold value;

[1148] In a case where the result output by the second AI model indicates not deactivating the ninth transmission, the terminal succeeds in detecting the ninth transmission with a probability greater than or equal to a ninth threshold value;

[1149] In a case where the result output by the second AI model indicates not to deactivate the ninth transmission, the terminal detects that a duration for the ninth transmission is less than or equal to a tenth threshold value;

[1150] In a case where the result output by the second AI model indicates not to deactivate the ninth transmission, the terminal detects that a probability of success of access based on the ninth transmission is greater than or equal to an eleventh threshold value;

[1151] In a case where the result output by the second AI model indicates to deactivate the ninth transmission, the terminal detects that a probability of success of access based on the tenth transmission is greater than or equal to a twelfth threshold value;

[1152] In a case where the result output by the second AI model indicates not to deactivate the ninth transmission, the terminal detects that a probability or frequency of selecting the ninth transmission for random access is greater than or equal to a thirteenth threshold value;

[1153] In a case where the result output by the second AI model indicates to deactivate the ninth transmission, the terminal detects that a probability or frequency of selecting the tenth transmission for random access is greater than or equal to a fourteenth threshold value;

[1154] A number of training of the second AI model reaches a third preset value;

[1155] A number of iterations of fine-tuning of the second AI model reaches a fourth preset value.

[1156] Optionally, in a case where the target AI model is trained by a second device, the first information of the target AI model is determined according to a type of the second device;

[1157] The first information includes at least one of the following: model information of the target AI model, input information for training of the target AI model, label information for training of the target AI model, and execution mode for training of the target AI model.

[1158] Optionally, the trigger condition for updating or retraining the target AI model includes at least one of the following:

[1159] Configuration information of the first transmission is changed;

[1160] Configuration information of the second transmission is changed;

[1161] Activation or deactivation mode of the first transmission is changed;

[1162] The terminal moves to a new cell, a new tracking area, or a new geographic location;

[1163] A change in the moving speed of the terminal is greater than or equal to a fifth preset value, or a change speed of the moving speed of the terminal is greater than or equal to a sixth preset value;

[1164] A time length from a last model update or retraining reaches a fifth time length;

[1165] A timer for triggering the model update or retraining expires;

[1166] M consecutive model supervisions occur or M model supervisions are triggered, M being a positive integer;

[1167] The target AI model fails in prediction;

[1168] The target AI model fails in prediction for K consecutive times, K being a positive integer;

[1169] A number of times that the target AI model fails in prediction reaches a fifth threshold;

[1170] The target AI model is used for prediction;

[1171] An environment in which the terminal is located changes.

[1172] Optionally, the configuration information for the target AI model supervision includes at least one of the following:

[1173] An AI model identifier that needs to be supervised;

[1174] A period of model supervision;

[1175] A time length of model supervision;

[1176] Detection window related information of model supervision;

[1177] A triggering condition of model supervision;

[1178] An index of model supervision.

[1179] Optionally, the triggering condition of the target AI model supervision includes at least one of the following:

[1180] The index of the target AI model supervision is not met, or the index of the target AI model supervision does not meet a fifth preset condition, or a time length for which the index of the target AI model supervision is not met or the index of the target AI model supervision does not meet the fifth preset condition reaches a sixth time length;

[1181] A target result of the target AI model does not meet a sixth preset condition, or a time length for which the target result of the target AI model does not meet the sixth preset condition reaches a seventh time length;

[1182] at least one of the indicators of the target AI model is not satisfied, or at least one of the indicators of the target AI model does not satisfy a seventh preset condition.

[1183] Optionally, the indicators supervised by the target AI model include at least one of the following:

[1184] error information or accuracy information between a prediction result and an actual result of the target AI model;

[1185] a performance indicator of a communication system;

[1186] model-related information of the target AI model.

[1187] Optionally, the apparatus further includes a sending module configured to send the AI-related capability information of the second device.

[1188] or

[1189] The processing module is further configured to determine the AI-related capability information of the first device.

[1190] The AI-related capability information is used to indicate at least one of the following:

[1191] possessing or not possessing the capability of training an AI model for predicting activation or deactivation of target transmission;

[1192] possessing or not possessing the capability of predicting activation or deactivation of target transmission by an AI model;

[1193] possessing or not possessing the capability of sending first auxiliary information for predicting activation or deactivation of target transmission by an AI model;

[1194] possessing or not possessing the capability of sending second auxiliary information for training an AI model for predicting activation or deactivation of target transmission.

[1195] The transmission control apparatus provided by the embodiments of the present application can implement each process implemented by the method embodiment of FIG. 6 and achieve the same technical effects. To avoid repetition, details are not described herein.

[1196] As shown in FIG. 9, the embodiments of the present application further provide a communication device 900, comprising a processor 901 and a memory 902, wherein the memory 902 stores programs or instructions executable on the processor 901. For example, when the communication device 900 is a first device, the programs or instructions are executed by the processor 901 to implement each step of the above-mentioned first device side transmission control method embodiments and achieve the same technical effects. When the communication device 900 is a second device, the programs or instructions are executed by the processor 901 to implement each step of the above-mentioned second device side transmission control method embodiments and achieve the same technical effects. To avoid repetition, details are not described herein.

[1197] The embodiments of the present application further provide a terminal, comprising a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is configured to run programs or instructions to implement the steps in the method embodiments shown in FIG. 5 or FIG. 6. The terminal embodiments correspond to the above-mentioned terminal side method embodiments, and each implementation process and implementation manner of the above-mentioned method embodiments can be applied to the terminal embodiments and achieve the same technical effects. The terminal can be the transmission control apparatus shown in FIG. 7 or FIG. 8. Specifically, FIG. 10 is a schematic diagram of a hardware structure of a terminal for implementing the embodiments of the present application.

[1198] The terminal 1000 includes, but is not limited to, at least part of the components such as a radio frequency unit 1001, a network module 1002, an audio output unit 1003, an input unit 1004, a sensor 1005, a display unit 1006, a user input unit 1007, an interface unit 1008, a memory 1009, and a processor 1010.

[1199] Those skilled in the art can understand that the terminal 1000 can further include a power supply (such as a battery) for supplying power to each component, and the power supply can be logically connected to the processor 1010 through a power management system, so as to realize functions such as power management, discharge management, and power consumption management through the power management system. The terminal structure shown in FIG. 10 does not constitute a limitation on the terminal, and the terminal can include more or fewer components than those shown, or combine certain components, or different component arrangements, which are not described herein.

[1200] It should be understood that in the embodiments of the present application, the input unit 1004 can include a graphics processor 10041 and a microphone 10042, and the graphics processor 10041 processes image data of a still picture or a video obtained by an image capture device (such as a camera) in a video capture mode or an image capture mode. The display unit 1006 can include a display panel 10061, which can be configured in the form of a liquid crystal display, an organic light-emitting diode, etc. The user input unit 1007 includes at least one of a touch panel 10071 and other input devices 10072. The touch panel 10071 is also called a touch screen. The touch panel 10071 can include two parts of a touch detection device and a touch controller. The other input devices 10072 can include, but are not limited to, a physical keyboard, function keys (such as volume control keys, on-off keys, etc.), a trackball, a mouse, a joystick, and the like, which will not be described here.

[1201] In the embodiments of the present application, after the radio frequency unit 1001 receives the downlink data from the network side device, it can be transmitted to the processor 1010 for processing. In addition, the radio frequency unit 1001 can send uplink data to the network side device. Generally, the radio frequency unit 1001 includes, but is not limited to, an antenna, an amplifier, a transceiver, a coupler, a low noise amplifier, a duplexer, etc.

[1202] The memory 1009 can be used to store software programs or instructions and various data. The memory 1009 can mainly include a first storage area storing programs or instructions and a second storage area storing data, wherein the first storage area can store an operating system, application programs or instructions required by at least one function (such as a sound playing function, an image playing function, etc.), and the like. In addition, the memory 1009 can include a volatile memory or a non-volatile memory. The non-volatile memory can be a Read-Only Memory (ROM), a Programmable ROM (PROM), an Erasable PROM (EPROM), an Electrically EPROM (EEPROM), or a flash memory. The volatile memory can be a Random Access Memory (RAM), a Static RAM (SRAM), a Dynamic RAM (DRAM), a Synchronous DRAM (SDRAM), a Double Data Rate SDRAM (DDR SDRAM), an Enhanced SDRAM (ESDRAM), a Synch link DRAM (SLDRAM), and a Direct Rambus RAM (DRRAM). The memory 1009 in the embodiments of the present application includes but is not limited to these and any other suitable types of memory.

[1203] The processor 1010 can include one or more processing units; optionally, the processor 1010 integrates an application processor and a modem processor, wherein the application processor mainly processes operations related to an operating system, a user interface, and an application program, and the modem processor mainly processes wireless communication signals, such as a baseband processor. It can be understood that the above-mentioned modem processor can also not be integrated into the processor 1010.

[1204] The processor 1010 is configured to determine a target result based on a target AI model.

[1205] 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.

[1206] The first result is used to indicate at least one of the following;

[1207] activating or not activating the first transmission;

[1208] sending or not sending an activation signal for activating or requesting to activate the first transmission;

[1209] a number of the first transmissions to be activated;

[1210] a range of the first transmissions to be activated;

[1211] the second result is used to indicate at least one of:

[1212] deactivating or not deactivating the first transmission;

[1213] sending or not sending a deactivation signal for deactivating or requesting to deactivate the first transmission;

[1214] a number of the first transmissions to be deactivated;

[1215] a range of the first transmissions to be deactivated;

[1216] or,

[1217] the processor 1010 is configured to perform a second operation, the second operation comprising at least one of:

[1218] training at least part of the target AI model;

[1219] sending at least part of the target AI model to the first device;

[1220] sending first input information to the first device, the first input information being used for prediction of the target AI model;

[1221] sending second input information to the first device, the second input information being used for training of the target AI model;

[1222] receiving third input information from the first device, the third input information being used for training of the target AI model;

[1223] receiving a target result sent by the first device, the target result being a result determined according to the target AI model;

[1224] receiving a supervision result of the target AI model sent by the first device, or sending a supervision result of the target AI model to the first device;

[1225] performing model supervision on the target AI model to obtain a supervision result of the target AI model;

[1226] The eleventh indication information is used to trigger the first device to perform target AI model training.

[1227] The twelfth indication information is used to trigger the first device to perform prediction based on the target AI model.

[1228] The target AI model includes the first AI model or the second AI model.

[1229] The first AI model is used to predict at least one of the following:

[1230] The target transmission is activated or not activated.

[1231] An activation signal is sent or not sent, and the activation signal is used to activate or request to activate the target transmission.

[1232] The number of target transmissions that need to be activated.

[1233] The range of target transmissions that need to be activated.

[1234] The second AI model is used to predict at least one of the following:

[1235] The target transmission is deactivated or not deactivated.

[1236] A deactivation signal is sent or not sent, and the deactivation signal is used to deactivate or request to deactivate the target transmission.

[1237] The number of target transmissions that need to be deactivated.

[1238] The range of target transmissions that need to be deactivated.

[1239] It can be understood that the implementation process of each implementation mode mentioned in the embodiment can refer to the related description of the method embodiment of the transmission control method, and achieve the same or corresponding technical effects. To avoid repetition, it will not be repeated here.

[1240] The embodiment of the application also provides a network side device, which includes a processor and a communication interface, the communication interface and the processor are coupled, and the processor is used to run programs or instructions to realize the steps of the method embodiment as shown in FIG. 5 or FIG. 6. The network side device embodiment corresponds to the above-mentioned network side device method embodiment, and each implementation process and implementation mode of the above-mentioned method embodiment can be applied to the network side device embodiment, and the same technical effects can be achieved.

[1241] Specifically, the embodiment of the present application further provides a network side device, which can be the transmission control apparatus shown in FIG. 7 or FIG. 8. As shown in FIG. 11, the network side device 11000 includes an antenna 1101, a radio frequency device 1102, a baseband device 1103, a processor 1104 and a memory 1105. The antenna 1101 is connected with the radio frequency device 1102. In the uplink direction, the radio frequency device 1102 receives information through the antenna 1101, and sends the received information to the baseband device 1103 for processing. In the downlink direction, the baseband device 1103 processes information to be sent, and sends the processed information to the radio frequency device 1102, which processes the received information and sends it out through the antenna 1101.

[1242] The method performed by the network side device in the above embodiment can be implemented in the baseband device 1103, which includes a baseband processor.

[1243] The baseband device 1103 may, for example, include at least one baseband board on which a plurality of chips are arranged, as shown in FIG. 11, one of which is a baseband processor, for example, which is connected with the memory 1105 through a bus interface to call programs in the memory 1105 and perform the operations of the network device shown in the above method embodiments.

[1244] The network side device can further include a network interface 1106, which is a Common Public Radio Interface (CPRI), for example.

[1245] Specifically, the network side device 11000 of the embodiment of the present application further includes instructions or programs stored in the memory 1105 and executable on the processor 1104, and the processor 1104 calls the instructions or programs in the memory 1105 to perform the method performed by each module shown in FIG. 7 or FIG. 8 and achieve the same technical effects. To avoid repetition, details are not described here.

[1246] The embodiment of the present application further provides a readable storage medium, which stores programs or instructions, and the programs or instructions are executed by a processor to implement each process of the above transmission control method embodiments and achieve the same technical effects. To avoid repetition, details are not described here.

[1247] The processor is the processor in the terminal described in the above embodiments. The readable storage medium includes a computer readable storage medium, such as a computer readable only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc. In some examples, the readable storage medium can be a non-transitory readable storage medium.

[1248] The embodiment of the present application further provides a chip, which comprises a processor and a communication interface, wherein the communication interface is coupled with the processor, and the processor is used to run programs or instructions, so as to realize the processes of the transmission control method and achieve the same technical effects. To avoid repetition, details are not described herein.

[1249] It should be understood that the chip mentioned in the embodiment of the present application can also be referred to as a system chip, a system-on-chip, a chip system or a system-on-chip, etc.

[1250] The embodiment of the present application further provides a computer program / product, which is stored in a storage medium and is executed by at least one processor to realize the processes of the transmission control method and achieve the same technical effects. To avoid repetition, details are not described herein.

[1251] The embodiment of the present application further provides a wireless communication system, which comprises a first device and a second device, wherein the first device is used to execute the steps of the transmission control method, and the second device is used to execute the steps of the transmission control method.

[1252] It should be noted that in this document, the terms "comprising", "containing" or any other variant thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements not only includes those elements, but also includes other elements not explicitly listed or inherent to such a process, method, article or device. Without more limitations, the element defined by the statement "comprising a" does not exclude the presence of additional identical elements in the process, method, article or device including the element. In addition, it should be pointed out that the scope of the methods and devices in the embodiments of the present application is not limited to the order of performing the functions shown or discussed, and can also include performing the functions in a substantially simultaneous manner or in a reverse order, for example, the described method can be performed in an order different from that described, and various steps can also be added, omitted or combined. In addition, the features described with reference to certain examples can be combined in other examples.

[1253] From the above description of the embodiments, those skilled in the art can clearly understand that the above-mentioned embodiment method can be realized by means of computer software product and general hardware platform, of course, it can also be realized by hardware. The computer software product is stored in a storage medium (such as ROM, RAM, magnetic disc, optical disc, etc.), which includes a plurality of instructions for making the terminal or network side device execute the method described in each embodiment of the present application.

[1254] The embodiments of the present application are described above with reference to the accompanying drawings, but the present application is not limited to the above-described specific embodiments, and the above-described specific embodiments are merely illustrative, but not restrictive, and a person of ordinary skill in the art can make many forms of embodiments under the inspiration of the present application without departing from the purpose of the present application and the scope protected by the claims, and these embodiments all belong to the protection of the present application.

Claims

1. A transmission control method, comprising: determining, by a first device, a target result based on a target artificial intelligence (AI) model; wherein 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 to indicate at least one of: activating or not activating a first transmission; sending an activation signal or not sending the activation signal, the activation signal being used to activate or request to activate the first transmission; a number of the first transmissions that need to be activated; a range of the first transmissions that need to be activated; the second result is used to indicate at least one of: deactivating or not deactivating the first transmission; sending a deactivation signal or not sending the deactivation signal, the deactivation signal being used to deactivate or request to deactivate the first transmission; a number of the first transmissions that need to be deactivated; a range of the first transmissions that need to be deactivated.

2. The method of claim 1, wherein, determining, by the first device, the target result based on the target AI model, comprises: determining, by the first device, the target result based on first input information and the target AI model; wherein the first input information comprises at least one of: time information; state information of a terminal; state information of a network-side device; state information of a server; at least one of signal strength and signal quality measured by the terminal on a reference signal associated with a second transmission, or a value determined based on at least one of signal strength and signal quality measured by the terminal on the reference signal associated with the second transmission; at least one of signal strength and signal quality measured by the terminal based on a third transmission, or a value determined based on at least one of signal strength and signal quality measured by the terminal based on the third transmission; a number of random access failures or a number of reception failures of an access response message on a physical random access channel (PRACH) corresponding to the third transmission; a number of PRACH repeated transmissions on a PRACH resource associated with the third transmission by the terminal; first indication information indicating whether the terminal fails to perform a 2-step random access after attempting the 2-step random access on the PRACH resource associated with the third transmission and then falls back to a 4-step random access; second indication information indicating whether a power of a PRACH signal sent by the terminal on the PRACH resource associated with the third transmission is greater than or equal to a first threshold value; third indication information indicating at least one of: whether the terminal receives a first random access response (RAR) message, a number of the first RAR messages received within a first time period, and whether the number of the first RAR messages received within the first time period is greater than or equal to a second threshold value, wherein the first RAR message is a RAR message including a preamble identifier that is not a preamble identifier sent by the terminal on the PRACH resource associated with the third transmission; fourth indication information indicating whether a number of activation signals sent by the terminal is less than or equal to a first number, or indicating whether a number of deactivation signals sent by the terminal is less than or equal to a second number. fifth indication information used for indicating whether a timing advance (TA) for activating signal transmission is valid, or used for indicating whether a TA for deactivating signal transmission is valid; sixth indication information used for indicating whether an interval between a current time and a time of last time of sending an activating signal is greater than or equal to a first interval, or used for indicating whether an interval between a current time and a time of last time of sending a deactivating signal is greater than or equal to a second interval; seventh indication information used for indicating whether an interval between a time of last time of activating or deactivating the first transmission and a current time is greater than or equal to a third interval; eighth indication information used for indicating whether the terminal has sent an activating signal of the fourth transmission, or used for indicating whether the terminal has sent a deactivating signal of the fourth transmission; ninth indication information used for indicating whether the fifth transmission has been activated, or used for indicating whether the fifth transmission has been deactivated; tenth indication information used for indicating whether the terminal has detected the sixth transmission; event information of the burst; a frequency domain feature of the first transmission; a time domain feature of the first transmission; a spatial domain feature of the first transmission; wherein the second transmission is different from the first transmission, and the third transmission is a transmission associated with a PRACH.

3. The method of claim 2, wherein, the state information of the terminal comprises at least one of the following: position information of the terminal, distribution information of the terminal, moving direction of the terminal, moving speed of the terminal, energy consumption status of the terminal, power status of the terminal, network scenario information of the terminal, environment information of the terminal, and perception information of the terminal; or, the state information of the network side device comprises at least one of the following: energy consumption status of the network side device, power status of the network side device, environment information of the network side device, and perception information of the network side device; or, the state information of the server comprises at least one of the following: environment information of the server and perception information of the server.

4. The method of any one of claims 1 to 3, wherein, the trigger condition for using the first AI model to perform prediction comprises at least one of the following: terminal power-on; terminal performing initial cell search; terminal performing initial cell selection; terminal performing initial search through a traditional way for a time duration reaching a first time duration; terminal not camping on a new cell in a second time period; terminal performing cell reselection; terminal performing cell handover; a timer for triggering prediction expires; before a random access trigger; before an initial access trigger; detecting beam failure; detecting radio link failure; determining, based on at least one of input information of the first AI model, that the first AI model needs to be used to perform prediction.

5. The method of any one of claims 1 to 4, wherein, the trigger condition for using the second AI model to perform prediction comprises at least one of the following: terminal power-on; terminal performing initial cell search; terminal performing initial cell selection; terminal performing initial search through a traditional way for a time duration exceeding a second time duration; the terminal does not camp on the new cell in a third time period; the terminal performs cell reselection; the terminal performs cell handover; a timer for triggering prediction expires; before a random access is triggered; before an initial access is triggered; a beam failure is detected; a radio link failure is detected; energy consumption of the network-side device exceeds a first threshold; energy consumption of the terminal exceeds a second threshold; power of the terminal is less than a third threshold; determining, based on at least one of the input information of the second AI model, that the second AI model needs to be used for prediction.

6. The method of any one of claims 1 to 5, wherein, 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, and the first operation includes at least one of the following: sending at least one of the target AI model input information and the target result; falling back to determining whether to activate or deactivate the first transmission in a non-AI manner; triggering switching of the target AI model; triggering retraining of the target AI model; triggering supervision of the target AI model.

7. The method of claim 6, wherein, The falling back to determining whether to activate or deactivate the first transmission in a non-AI manner includes: falling back to determining whether to activate or deactivate the first transmission in a non-AI manner in at least one of the following cases: the first device fails to successfully complete prediction within a third time period after using the target AI model for prediction; the first device fails to successfully complete prediction using the target AI model.

8. The method of any one of claims 1 to 7, further including at least one of the following: the first device obtains an indicator of the target AI model; the first device sends the indicator of the target AI model; wherein, the indicator of the target AI model includes at least one of the following: complexity of the target AI model; latency of prediction of the target AI model; success rate of prediction of the target AI model; reliability of the result output by the target AI model.

9. The method of any one of claims 1 to 8, further including: the first device trains at least part of the target AI models; or, the first device receives at least part of the target AI models.

10. The method of claim 9, wherein, The trigger type of the target AI model training includes at least one of the following: conditional or event trigger, periodic trigger, and semi-static trigger.

11. The method of claim 9 or 10, wherein, The condition or event triggering the target AI model training includes at least one of the following: configuration information of the first transmission changes; configuration information of a second transmission changes; activation or deactivation mode of the first transmission changes; the target AI model fails to predict; the target AI model fails to predict for N consecutive times, N being a positive integer; the target AI model fails to predict for a fourth threshold number of times; the target AI model is used for prediction; the terminal reselects to a new cell; tracking area of the terminal changes; environment in which the terminal is located changes. The second transmission is different from the first transmission.

12. The method of claim 11, wherein, The configuration information of the first transmission comprises at least one of the following: the number of the first transmission, 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 comprises at least one of the following: the number of the second transmission, 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 of any one of claims 10 to 12, wherein, The configuration information of the periodic triggering comprises at least one of the following: the starting point of the periodic model training, the interval of the periodic model training, the number of model training in a period, and the duration of model training in a period.

14. The method of any one of claims 10 to 13, wherein, The semi-static triggering comprises at least one of the following: The sending and / or activation of the configuration information of the semi-static triggering is triggered based on a specific condition or a specific event; The configuration information of the semi-static triggering is configured by a radio resource control (RRC) and / or activated or deactivated by physical control information.

15. The method of any one of claims 8-14, further comprising: The first device receives second input information, which is used for training of the target AI model; Or, The first device sends third input information, which is used for training of the target AI model.

16. The method of claim 15, wherein, The first device is a terminal; The first device receives second input information, comprising: The first device receives the second input information sent by a network-side device through at least one of the following: a medium access control control element (MAC CE), an RRC message, a non-access stratum (NAS) message, user plane data, a system information block (SIB), physical layer signaling, a physical downlink shared channel (PDSCH), MSG 2, MSG 4, and MSG B; Or, The first device sends third input information, comprising at least one of the following: The first device sends the third input information to a network-side device through at least one of the following: a MAC CE, an RRC message, a NAS message, user plane data, MSG 1, MSG A, MSG 3, a physical uplink control channel (PUCCH), a physical uplink shared channel (PUSCH), a random access channel (RACH), and an uplink reference signal (UL RS); The first device sends the third input information to a server through a first interface message.

17. The method of claim 16, wherein, The first device is a network-side device; The first device receives second input information, comprising: The first device receives the second input information sent by a terminal through at least one of the following: a MAC CE, an RRC message, a NAS message, user plane data, MSG 1, MSG A, MSG 3, a PUCCH, a PUSCH, a RACH, and an UL RS; Or, The first device sends third input information, comprising at least one of the following: The first device sends the third input information to a terminal through at least one of the following: a MAC CE, an RRC message, a NAS message, user plane data, DCI information, a SIB, physical layer signaling, a PDSCH, MSG 2, MSG 4, and MSG B; The first device sends the third input information to the server through a second interface message.

18. The method of claim 15, wherein, 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 a terminal and a network side device.

19. The method of any one of claims 15 to 18, wherein, The trigger condition for sending or obtaining the second input information or the third input information includes at least one of the following: The terminal camps on a cell; The terminal initially selects a cell; The terminal reselects a cell; The terminal enters an RRC connected state; The terminal enters an inactive state for a duration reaching a fourth duration.

20. The method of any one of claims 1 to 19, wherein, The determination condition for the first AI model training completion includes at least one of the following: The loss function for the first AI model training satisfies a first preset condition; In a case where the result output by the first AI model indicates activating a seventh transmission, a measurement result measured by the terminal based on the seventh transmission satisfies a second preset condition; In a case where the result output by the first AI model indicates activating a seventh transmission, a probability that the terminal successfully detects the seventh transmission after activating the seventh transmission is greater than or equal to a third threshold value; In a case where the result output by the first AI model indicates activating a seventh transmission, a duration for the terminal to detect the seventh transmission after activating the seventh transmission is less than or equal to a fourth threshold value; In a case where the result output by the first AI model indicates activating a seventh transmission, a probability that the terminal accesses successfully based on the seventh transmission is greater than or equal to a fifth threshold value; In a case where the result output by the first AI model indicates not activating a seventh transmission, a probability that the terminal accesses successfully based on an eighth transmission is greater than or equal to a sixth threshold value; In a case where the result output by the first AI model indicates activating a seventh transmission, a probability or frequency that the terminal selects the seventh transmission for random access is greater than or equal to a seventh threshold value; In a case where the result output by the first AI model indicates activating a seventh transmission, a probability or frequency that the terminal selects an eighth transmission for random access is greater than or equal to an eighth threshold value; The number of times of training of the first AI model reaches a first preset value; The number of iterations of fine-tuning of the first AI model reaches a second preset value.

21. The method of any one of claims 1 to 20, wherein, The determination condition for the second AI model training completion includes at least one of the following: The loss function for the second AI model training satisfies a third preset condition; In a case where the result output by the second AI model indicates not deactivating a ninth transmission, a measurement result measured by the terminal based on the ninth transmission satisfies a fourth preset condition; In a case where the result output by the second AI model indicates not deactivating a ninth transmission, a probability that the terminal detects the ninth transmission is greater than or equal to a ninth threshold value; In a case where the result output by the second AI model indicates not deactivating a ninth transmission, a duration for the terminal to detect the ninth transmission is less than or equal to a tenth threshold value; In a case where the result output by the second AI model indicates not deactivating a ninth transmission, a probability that the terminal accesses successfully based on the ninth transmission is greater than or equal to an eleventh threshold value; In a case where the result output by the second AI model indicates deactivation of the ninth transmission, the terminal has a probability or frequency of selecting the tenth transmission for random access greater than or equal to a twelfth threshold value; In a case where the result output by the second AI model indicates not deactivating the ninth transmission, the terminal has a probability or frequency of selecting the ninth transmission for random access greater than or equal to a thirteenth threshold value; In a case where the result output by the second AI model indicates deactivation of the ninth transmission, the terminal has a probability or frequency of selecting the tenth transmission for random access greater than or equal to a fourteenth threshold value; The second AI model has a training number reaching a third preset value; The second AI model has an iteration number of fine-tuning reaching a fourth preset value.

22. The method of any one of claims 1 to 21, wherein, In a case where the target AI model is trained by the first device, first information of the target AI model is determined according to a 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 of the target AI model, label information for training of the target AI model, and execution mode for training of the target AI model.

23. The method of any one of claims 1 to 22, wherein, The trigger condition for updating or retraining the target AI model includes at least one of the following: Configuration information of the first transmission changes; Configuration information of a second transmission changes; Activation or deactivation mode of the first transmission changes; The terminal moves to a new cell, a new tracking area or a new geographic location; A change amount of a moving speed of the terminal is greater than or equal to a fifth preset value, or a change speed of the moving speed of the terminal is greater than or equal to a sixth preset value; A time length from a last model update or retraining reaches a fifth time length; A timer for triggering model update or retraining times out; M consecutive model supervisions occur or M model supervisions are triggered, M being a positive integer; The target AI model fails to make a prediction; The target AI model fails to make a prediction for K consecutive times, K being a positive integer; A number of times that the target AI model fails to make a prediction reaches a fifth threshold; The target AI model is used to make a prediction; An environment in which the terminal is located changes.

24. The method of any of claims 1-23, further comprising: the first device obtaining a model supervision result of the target AI model; or, the first device sending the model supervision result of the target AI model.

25. The method of claim 24, wherein, the first device obtaining the model supervision result of the target AI model, comprising: the first device performing model supervision on the target AI model to obtain the model supervision result of the target AI model; or, the first device receiving the model supervision result of the target AI model.

26. The method of any one of claims 1 to 25, wherein, The configuration information for the target AI model supervision includes at least one of the following: an AI model identifier that needs to be supervised; a model supervision period; a model supervision time length; model supervision detection window related information; a model supervision trigger condition; a model supervision index.

27. The method of any one of claims 1 to 26, wherein, The trigger condition for the target AI model supervision includes at least one of the following: the target AI model supervision index does not meet a fifth preset condition, or a time length that the target AI model supervision index does not meet a fifth preset condition reaches a sixth time length; a target result of the target AI model does not meet a sixth preset condition, or a time length that the target result of the target AI model does not meet a sixth preset condition reaches a seventh time length; at least one of the target AI model indexes does not meet a seventh preset condition.

28. The method of any one of claims 1 to 27, wherein, The target AI model supervision index includes at least one of the following: error information or accuracy information between a prediction result and an actual result of the target AI model; a performance index of a communication system; model-related information of the target AI model.

29. The method of any one of claims 1-28, further comprising at least one of the following: the first device sending AI-related capability information of the first device; the first device determining AI-related capability information of a second device; wherein, the AI-related capability information indicating at least one of the following: having or not having the capability to train an AI model for predicting activation or deactivation of a target transmission; having or not having the capability to predict activation or deactivation of a target transmission by an AI model; having or not having the capability to send first assistance information for predicting activation or deactivation of a target transmission by an AI model; having or not having the capability to send second assistance information for training an AI model for predicting activation or deactivation of a target transmission.

30. The method of claim 29, wherein, The first device determines AI-related capability information of a second device, comprising: the first device determining the AI-related capability information of the second device based on at least one of the following: a device type of the second device; AI-related capability information indicated by a reference signal; AI-related capability information carried by control information sent by the second device; AI-related capability information carried by RRC signaling sent by the second device; AI-related capability information carried by an interface message between the first device and the second device.

31. The method of any one of claims 1 to 30, wherein, The first device is a server, and the method further comprises: the server sending the target result to a terminal or a network-side device.

32. A transmission control method, comprising: a second device performing a second operation, the second operation comprising at least one of the following: training at least part of target AI models; sending at least part of the target AI models to a first device; sending first input information to the first device, the first input information being used for prediction of the target AI models; sending second input information to the first device, the second input information being used for training of the target AI models; receiving third input information from the first device, the third input information being used for training of the target AI models; receiving a target result sent by the first device, the target result being a result determined according to the target AI models; receive a supervision result of the target AI model sent by the first device, or send the supervision result of the target AI model to the first device; perform model supervision on the target AI model to obtain a supervision result of the target AI model; send eleventh indication information to the first device, the eleventh indication information being used to trigger the first device to perform target AI model training; send twelfth indication information to the first device, the twelfth indication information being used to trigger the first device to perform prediction based on the target AI model; the target AI model comprises a first AI model or a second AI model; the first AI model is used to predict at least one of the following; activation or non-activation of target transmission; sending or not sending an activation signal, the activation signal being used to activate or request activation of target transmission; a number of target transmissions that need to be activated; a range of target transmissions that need to be activated; the second AI model is used to predict at least one of the following; deactivation or non-deactivation of target transmission; sending or not sending a deactivation signal, the deactivation signal being used to deactivate or request deactivation of target transmission; a number of target transmissions that need to be deactivated; a range of target transmissions that need to be deactivated.

33. The method of claim 32, wherein, the training of at least part of the AI models in the target AI model comprises: training at least part of the AI models in the target AI model based on target input information; the target input information comprises at least one of the following: time information; state information of the terminal; state information of the network side device; state information of the server; frequency domain characteristics of the eleventh transmission; time domain characteristics of the eleventh transmission; spatial domain characteristics of the eleventh transmission; at least one of signal strength and signal quality obtained by the terminal measuring a reference signal associated with the twelfth transmission, or a value determined according to at least one of signal strength and signal quality obtained by the terminal measuring the reference signal associated with the twelfth transmission; at least one of signal strength and signal quality measured by the terminal based on the twelfth transmission, or a value determined according to at least one of signal strength and signal quality measured by the terminal based on the twelfth transmission; a number of random access failures or a number of access response message receiving failures of the terminal on a physical random access channel (PRACH) corresponding to the thirteenth transmission; a number of PRACH repeated transmissions of the terminal on a PRACH resource associated with the thirteenth transmission; thirteenth indication information used to indicate whether the terminal fails to perform random access after falling back to 4-step random access after failing to perform 2-step random access on the PRACH resource associated with the thirteenth transmission; fourteenth indication information used to indicate whether the power of the PRACH signal sent by the terminal on the PRACH resource associated with the thirteenth transmission is greater than or equal to a first threshold value; fifteenth indication information, used for indicating at least one of the following: whether the terminal receives a second random access response (RAR) message, a number of the second RAR messages received in a first time period, whether the number of the second RAR messages received in the first time period is greater than or equal to a second threshold value, wherein the second RAR message is a RAR message including a preamble identifier that is not the preamble identifier sent by the terminal on the PRACH resource associated with the thirteenth transmission; sixteenth indication information, used for indicating whether a number of times of sending an activation signal by the terminal is less than or equal to a first number of times, or used for indicating whether a number of times of sending a deactivation signal by the terminal is less than or equal to a second number of times; seventeenth indication information, used for indicating whether a timing advance (TA) for sending the activation signal is valid, or used for indicating whether a TA for sending the deactivation signal is valid; eighteenth indication information, used for indicating whether an interval between a current time and a time of sending the activation signal last time is greater than or equal to a first interval, or used for indicating whether an interval between the current time and a time of sending the deactivation signal last time is greater than or equal to a second interval; nineteenth indication information, used for indicating whether an interval between a time of activating or deactivating the eleventh transmission last time and a current time is greater than or equal to a third interval; twentieth indication information, used for indicating whether the terminal sends the activation signal of the fourteenth transmission, or used for indicating whether the terminal sends the deactivation signal of the fourteenth transmission; twenty-first indication information, used for indicating whether the fifteenth transmission is activated, or used for indicating whether the fifteenth transmission is deactivated; twenty-second indication information, used for indicating whether the terminal detects the sixteenth transmission; event information of the burst; wherein the twelfth transmission is different from the eleventh transmission, and the thirteenth transmission is a transmission associated with the PRACH.

34. The method of claim 33, wherein, the state information of the terminal includes at least one of the following: position information of the terminal, distribution information of the terminal, moving direction of the terminal, moving speed of the terminal, energy consumption status of the terminal, power status of the terminal, network scenario information of the terminal, environment information of the terminal, and perception information of the terminal; or, the state information of the network side device includes at least one of the following: energy consumption status of the network side device, power status of the network side device, environment information of the network side device, and perception information of the network side device; or, the state information of the server includes at least one of the following: environment information of the server and perception information of the server.

35. The method of any one of claims 32 to 34, wherein, the target AI model is a first AI model, and the sending, to the first device, of the eleventh indication information includes: The eleventh indication information is sent to the first device in at least one of the following cases: The terminal is powered on; The terminal performs initial cell search; The terminal performs initial cell selection; The terminal performs initial search through a traditional manner for a first time length; The terminal does not camp on a new cell within a second time period; The terminal performs cell reselection; The terminal performs cell switching; A timer for triggering prediction times out; Before a random access trigger; Before an initial access trigger; A beam failure is detected; A radio link failure is detected.

36. The method of any one of claims 32 to 34, wherein, The target AI model is a second AI model, and the sending of the eleventh indication information to the first device comprises: The eleventh indication information is sent to the first device in at least one of the following cases: The terminal is powered on; The terminal performs initial cell search; The terminal performs initial cell selection; The terminal performs initial search through a traditional manner for a second time length; The terminal does not camp on a new cell within a third time period; The terminal performs cell reselection; The terminal performs cell switching; A timer for triggering prediction times out; Before a random access trigger; Before an initial access trigger; A beam failure is detected; A radio link failure is detected; Energy consumption of the network side device exceeds a first threshold; Energy consumption of the terminal exceeds a second threshold; The terminal has less than a third threshold of power.

37. The method of any one of claims 32 to 36, further comprising: The second device receives an indicator of the target AI model from the first device; Or, The second device sends an indicator of the target AI model to the first device; The indicator of the target AI model comprises at least one of the following: Complexity of the target AI model; Latency of prediction by the target AI model; Success rate of prediction by the target AI model; Reliability of results output by the target AI model.

38. The method of any one of claims 32 to 37, wherein, The trigger type of training of the target AI model comprises at least one of the following: conditional or event trigger, periodic trigger, and semi-static trigger.

39. The method of any one of claims 32 to 38, wherein, The condition or event triggering the training of the target AI model comprises at least one of the following: Configuration information of the first transmission changes; Configuration information of the second transmission changes; Activation or deactivation mode of the first transmission changes; The target AI model fails to predict; The target AI model fails to predict for N consecutive times, N being a positive integer; The target AI model fails to predict for a fourth threshold number of times; The target AI model is used for prediction; The terminal reselects to a new cell; Tracking area of the terminal changes; Environment in which the terminal is located changes. The second transmission is different from the first transmission.

40. The method of any one of claims 32 to 39, wherein, The trigger condition for sending or obtaining the second input information or the third input information comprises at least one of the following: The terminal camps on a cell; The terminal initially selects a cell; The terminal reselects a cell; The terminal enters an RRC connected state; The terminal enters a non-active state for a fourth time length.

41. The method of any one of claims 32 to 40, wherein, The determination condition for completion of training of the first AI model comprises at least one of the following: A loss function for training of the first AI model satisfies a first preset condition; In a case where the result output by the first AI model indicates activating the seventh transmission, the terminal satisfies a second preset condition based on a measurement result measured by the terminal from the seventh transmission; In a case where the result output by the first AI model indicates activating the seventh transmission, a probability that the terminal successfully detects the seventh transmission after activating the seventh transmission is greater than or equal to a third threshold value; In a case where the result output by the first AI model indicates activating the seventh transmission, a time length that the terminal detects the seventh transmission after activating the seventh transmission is less than or equal to a fourth threshold value; In a case where the result output by the first AI model indicates activating the seventh transmission, a probability that the terminal successfully accesses based on the seventh transmission is greater than or equal to a fifth threshold value; In a case where the result output by the first AI model indicates not activating the seventh transmission, a probability that the terminal successfully accesses based on the eighth transmission is greater than or equal to a sixth threshold value; In a case where the result output by the first AI model indicates activating the seventh transmission, a probability or frequency that the terminal selects the seventh transmission for random access is greater than or equal to a seventh threshold value; In a case where the result output by the first AI model indicates activating the seventh transmission, a probability or frequency that the terminal selects the eighth transmission for random access is greater than or equal to an eighth threshold value; A number of times of training of the first AI model reaches a first preset value; A number of iterations of fine-tuning of the first AI model reaches a second preset value.

42. The method of any one of claims 32 to 41, wherein, The determination condition that the second AI model training is completed includes at least one of the following: A loss function used for training of the second AI model satisfies a third preset condition; In a case where the result output by the second AI model indicates not deactivating the ninth transmission, the terminal satisfies a fourth preset condition based on a measurement result measured by the terminal from the ninth transmission; In a case where the result output by the second AI model indicates not deactivating the ninth transmission, a probability that the terminal detects the ninth transmission is greater than or equal to a ninth threshold value; In a case where the result output by the second AI model indicates not deactivating the ninth transmission, a time length that the terminal detects the ninth transmission is less than or equal to a tenth threshold value; In a case where the result output by the second AI model indicates not deactivating the ninth transmission, a probability that the terminal successfully accesses based on the ninth transmission is greater than or equal to an eleventh threshold value; In a case where the result output by the second AI model indicates deactivating the ninth transmission, a probability that the terminal successfully accesses based on the tenth transmission is greater than or equal to a twelfth threshold value; In a case where the result output by the second AI model indicates not deactivating the ninth transmission, a probability or frequency that the terminal selects the ninth transmission for random access is greater than or equal to a thirteenth threshold value; In a case where the result output by the second AI model indicates deactivating the ninth transmission, a probability or frequency that the terminal selects the tenth transmission for random access is greater than or equal to a fourteenth threshold value; A number of times of training of the second AI model reaches a third preset value; A number of iterations of fine-tuning of the second AI model reaches a fourth preset value.

43. The method of any one of claims 32 to 42, wherein, In a case where the target AI model is trained by the second device, the first information of the target AI model is determined according to a 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 of the target AI model, label information for training of the target AI model, and execution mode for training of the target AI model.

44. The method of any one of claims 32 to 43, wherein, The trigger condition for updating or retraining the target AI model includes at least one of the following: The configuration information of the first transmission changes; The configuration information of the second transmission changes; The activation or deactivation mode of the first transmission changes; The terminal moves to a new cell or a new tracking area or a new geographical location; A change amount of a moving speed of the terminal is greater than or equal to a fifth preset value, or a change speed of the moving speed of the terminal is greater than or equal to a sixth preset value; A time length from a last model update or retraining reaches a fifth time length; A timer for triggering model update or retraining times out; M consecutive model supervision occurs or M model supervision is triggered, M being a positive integer; The target AI model fails to make a prediction; The target AI model fails to make a prediction for K consecutive times, K being a positive integer; A number of times that the target AI model fails to make a prediction reaches a fifth threshold; The target AI model is used to make a prediction; An environment in which the terminal is located changes.

45. The method of any one of claims 32 to 44, wherein, The configuration information for the target AI model supervision includes at least one of the following: An AI model identification that needs to be supervised; A period of model supervision; A time length of model supervision; Detection window related information of model supervision; A trigger condition of model supervision; An index of model supervision.

46. The method of any one of claims 32 to 45, wherein, The trigger condition of the target AI model supervision includes at least one of the following: The index of the target AI model supervision is not met, or the index of the target AI model supervision does not meet a fifth preset condition, or a time length for which the index of the target AI model supervision is not met reaches a sixth time length, or a time length for which the index of the target AI model supervision does not meet the fifth preset condition reaches the sixth time length; A target result of the target AI model does not meet a sixth preset condition, or a time length for which the target result of the target AI model does not meet the sixth preset condition reaches a seventh time length; At least one of the indexes of the target AI model is not met, or at least one of the indexes of the target AI model does not meet a seventh preset condition.

47. The method of any one of claims 32 to 46, wherein, The index of the target AI model supervision includes at least one of the following: Error information or accuracy information between a prediction result and an actual result of the target AI model; A performance index of a communication system; Model related information of the target AI model.

48. The method of any of claims 32 to 47, further comprising at least one of the following: The second device sends AI related capability information of the second device; The second device determines AI related capability information of the first device; wherein The AI related capability information is used to indicate at least one of the following: Possessing or not possessing a capability of training an AI model for predicting activation or deactivation of a target transmission; with or without the capability of sending first assistance information for predicting activation or deactivation of target transmission by an AI model; with or without the capability of sending second assistance information for training an AI model for predicting activation or deactivation of target transmission.

49. A transmission control apparatus, comprising: a processing module configured to determine a target result based on a target artificial intelligence (AI) model; wherein 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 to indicate at least one of: activation or non-activation of a first transmission; sending or non-sending of an activation signal for activating or requesting activation of the first transmission; a number of the first transmission to be activated; a range of the first transmission to be activated; the second result is used to indicate at least one of: deactivation or non-deactivation of the first transmission; sending or non-sending of a deactivation signal for deactivating or requesting deactivation of the first transmission; a number of the first transmission to be deactivated; a range of the first transmission to be deactivated. the processing module is specifically configured to:

50. The device of claim 49, wherein, determine a target result based on first input information and the target AI model; wherein the first input information comprises at least one of: time information; state information of a terminal; state information of a network-side device; state information of a server; at least one of signal strength and signal quality measured by the terminal on a reference signal associated with a second transmission, or a value determined based on at least one of signal strength and signal quality measured by the terminal on the reference signal associated with the second transmission; at least one of signal strength and signal quality measured by the terminal based on a third transmission, or a value determined based on at least one of signal strength and signal quality measured by the terminal based on the third transmission; a number of random access failures or a number of reception failures of an access response message of the terminal on a physical random access channel (PRACH) corresponding to the third transmission; a number of PRACH repeated transmissions of the terminal on a PRACH resource associated with the third transmission; first indication information indicating whether the terminal fails to perform 2-step random access after attempting 2-step random access on the PRACH resource associated with the third transmission and then falls back to 4-step random access; second indication information indicating whether a transmission power of a PRACH signal of the terminal on the PRACH resource associated with the third transmission is greater than or equal to a first threshold. ​ a third indication information, the third indication information being used for indicating at least one of the following: whether the terminal receives a first random access response (RAR) message, a number of the first RAR messages received in a first time period, whether the number of the first RAR messages received in the first time period is greater than or equal to a second threshold value, wherein the first RAR message is a RAR message including a preamble identifier which is not the same as a preamble identifier sent by the terminal on a PRACH resource associated with a third transmission; a fourth indication information, the fourth indication information being used for indicating whether a number of times of sending an activation signal by the terminal is less than or equal to a first number of times, or the fourth indication information being used for indicating whether a number of times of sending a deactivation signal by the terminal is less than or equal to a second number of times; a fifth indication information, the fifth indication information being used for indicating whether a timing advance (TA) used for sending the activation signal is valid, or the fifth indication information being used for indicating whether a TA used for sending the deactivation signal is valid; a sixth indication information, the sixth indication information being used for indicating whether an interval between a current time and a time of sending the activation signal last time is greater than or equal to a first interval, or the sixth indication information being used for indicating whether an interval between the current time and a time of sending the deactivation signal last time is greater than or equal to a second interval; a seventh indication information, the seventh indication information being used for indicating whether an interval between a time of activating or deactivating the first transmission last time and the current time is greater than or equal to a third interval; an eighth indication information, the eighth indication information being used for indicating whether the terminal sends an activation signal of a fourth transmission, or the eighth indication information being used for indicating whether the terminal sends a deactivation signal of the fourth transmission; a ninth indication information, the ninth indication information being used for indicating whether a fifth transmission is activated, or the ninth indication information being used for indicating whether the fifth transmission is deactivated; a tenth indication information, the tenth indication information being used for indicating whether the terminal detects a sixth transmission; burst event information; a frequency domain feature of the first transmission; a time domain feature of the first transmission; a spatial domain feature of the first transmission; wherein the second transmission is different from the first transmission, and the third transmission is a transmission associated with a PRACH.

51. A transmission control apparatus, comprising: a processing module configured to perform a second operation, the second operation comprising at least one of: training at least part of a target AI model; sending at least part of the target AI model to a first device; sending first input information to the first device, the first input information being used for prediction of the target AI model; sending second input information to the first device, the second input information being used for training of the target AI model; receiving third input information from the first device, the third input information being used for training of the target AI model; receiving a target result sent by the first device, the target result being a result determined according to the target AI model; receiving a supervision result of the target AI model sent by the first device, or sending a supervision result of the target AI model to the first device; performing model supervision on the target AI model to obtain the supervision result of the target AI model; The first device is triggered to perform target AI model training based on the eleventh indication information; The first device is triggered to perform prediction based on the target AI model based on the twelfth indication information; The target AI model includes the first AI model or the second AI model; The first AI model is used to predict at least one of the following: Activation or non-activation of target transmission; Sending an activation signal or not sending an activation signal, the activation signal being used to activate or request to activate 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: Deactivation or non-deactivation of target transmission; Sending a deactivation signal or not sending a deactivation signal, the deactivation signal being used to deactivate or request to deactivate target transmission; The number of target transmissions that need to be deactivated; The range of target transmissions that need to be deactivated.

52. The device of claim 51, wherein, The processing module is specifically configured to: Train at least part of the target AI model based on target input information; The target input information includes at least one of the following: Time information; State information of the terminal; State information of the network side device; State information of the server; Frequency domain characteristics of the eleventh transmission; Time domain characteristics of the eleventh transmission; Space domain characteristics of the eleventh transmission; At least one of the signal strength and signal quality obtained by the terminal measuring the reference signal associated with the twelfth transmission, or a value determined according to at least one of the signal strength and signal quality obtained by the terminal measuring the reference signal associated with the twelfth transmission; At least one of the signal strength and signal quality measured by the terminal based on the twelfth transmission, or a value determined according to at least one of the signal strength and signal quality measured by the terminal based on the twelfth transmission; The number of random access failures or the number of access response message reception failures of the terminal on the physical random access channel (PRACH) corresponding to the thirteenth transmission; The number of PRACH repeated transmissions of the terminal on the PRACH resource associated with the thirteenth transmission; The thirteenth indication information is used to indicate whether the terminal fails to perform random access after falling back to 4-step random access after failing to attempt 2-step random access on the PRACH resource associated with the thirteenth transmission; The fourteenth indication information is used to indicate whether the power of the PRACH signal sent by the terminal on the PRACH resource associated with the thirteenth transmission is greater than or equal to a first threshold value; 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 the second RAR messages received within a first time period, and the number of the second RARs received within the first time period is greater than or equal to a second threshold value; wherein the second RAR message is an RAR message including a preamble identifier that is not the preamble identifier sent by the terminal on the PRACH resource associated with the thirteenth transmission. sixteenth indication information for indicating whether the number of times of sending the activation signal by the terminal is less than or equal to a first number of times, or for indicating whether the number of times of sending the deactivation signal by the terminal is less than or equal to a second number of times; seventeenth indication information for indicating whether a timing advance (TA) for sending the activation signal is valid, or for indicating whether a TA for sending the deactivation signal is valid; eighteenth indication information for indicating whether an interval between a current time and a time of sending the activation signal last time is greater than or equal to a first interval, or for indicating whether an interval between the current time and a time of sending the deactivation signal last time is greater than or equal to a second interval; nineteenth indication information for indicating whether an interval between a time of activating or deactivating the eleventh transmission last time and the current time is greater than or equal to a third interval; twentieth indication information for indicating whether the activation signal of the fourteenth transmission is sent by the terminal, or for indicating whether the deactivation signal of the fourteenth transmission is sent by the terminal; twenty-first indication information for indicating whether the fifteenth transmission is activated, or for indicating whether the fifteenth transmission is deactivated; twenty-second indication information for indicating whether the sixteenth transmission is detected by the terminal; event information of the burst; wherein the twelfth transmission is different from the eleventh transmission, and the thirteenth transmission is a transmission associated with the PRACH.

53. A first device comprising a processor and a memory, the memory storing programs or instructions executable on the processor, the programs or instructions being executed by the processor to implement the steps of the transmission control method according to any one of claims 1 to 31.

54. A second device comprising a processor and a memory, the memory storing programs or instructions executable on the processor, the programs or instructions being executed by the processor to implement the steps of the transmission control method according to any one of claims 32 to 48.

55. A readable storage medium, the readable storage medium storing programs or instructions executable on a processor, the programs or instructions being executed by the processor to implement the steps of the transmission control method according to any one of claims 1 to 31, or to implement the steps of the transmission control method according to any one of claims 32 to 48.

56. A computer program product executed by at least one processor to implement the steps of the transmission control method according to any one of claims 1 to 31, or to implement the steps of the transmission control method according to any one of claims 32 to 48.

Images