Communication parameter determination method, terminal, and network-side device

Abstract

The present application belongs to the technical field of communications. Disclosed are a communication parameter determination method, a terminal, and a network-side device. The communication parameter determination method in the embodiments of the present application comprises: a terminal receiving model parameters of a first AI model; and the terminal obtaining a first result on the basis of the model parameters of the first AI model, wherein the first result comprises at least one of the following: an on-off mode, which is applied to a target communication service, or a DRX configuration.

Description

Methods for determining communication parameters, terminals and network-side equipment

[0001] Cross-references to related applications

[0002] This application claims priority to Chinese Patent Application No. 202411940469.3, filed on December 26, 2024, entitled "Method for Determining Communication Parameters, Terminal and Network Side Device", the entire contents of which are incorporated herein by reference. Technical Field

[0003] This application belongs to the field of communication technology, specifically relating to a method for determining communication parameters, a terminal, and a network-side device. Background Technology

[0004] In related technologies, network-side devices can configure communication parameters for terminals, including, for example, periodic discontinuous reception (DRX) configuration. However, the communication parameters configured for terminals often do not match the actual service characteristics. For instance, the terminal's DRX configuration may not match the incoming service packets, leading to ineffective terminal monitoring, increased power consumption, and increased service latency. Therefore, it is necessary to determine more accurate communication parameters to reduce ineffective terminal activation or monitoring states, thereby achieving energy savings. Summary of the Invention

[0005] This application provides a method for determining communication parameters, a terminal, and a network-side device, which can solve the problem of inaccurate communication parameters of the terminal, which is detrimental to energy saving.

[0006] In a first aspect, a method for determining communication parameters is provided, comprising: a terminal receiving model parameters of a first AI model; the terminal obtaining a first result based on the model parameters of the first AI model; wherein the first result includes at least one of the following: an On-Off mode, wherein the On-Off mode is applied to a target communication service; and DRX configuration.

[0007] Secondly, a method for determining communication parameters is provided, comprising: a network-side device sending model parameters of a first AI model; the network-side device obtaining a first result based on the model parameters of the first AI model; wherein the first result includes at least one of the following: the On-Off mode of the terminal, the On-Off mode being applied to the target communication service; and the DRX configuration of the terminal.

[0008] Thirdly, a device for determining communication parameters is provided, applied to a terminal, comprising: a communication module for receiving model parameters of a first AI model; a processing module for obtaining a first result based on the model parameters of the first AI model; wherein the first result includes at least one of the following: an On-Off mode, wherein the On-Off mode is applied to a target communication service; and a DRX configuration.

[0009] Fourthly, a device for determining communication parameters is provided, applied to a network-side device, comprising: a communication module for sending model parameters of a first AI model; a processing module for obtaining a first result based on the model parameters of the first AI model; wherein the first result includes at least one of the following: an On-Off mode of a terminal, the On-Off mode being applied to a target communication service; and a DRX configuration of the terminal.

[0010] Fifthly, an apparatus for determining communication parameters is provided, the apparatus being configured to perform the steps of the method described in the first aspect, or to implement the steps of the method described in the second aspect.

[0011] In a sixth aspect, a terminal is provided, the terminal including a processor and a memory, the memory storing a program or instructions executable on the processor, the program or instructions, when executed by the processor, implementing the steps of the method as described in the first aspect.

[0012] In a seventh aspect, a terminal is provided, including a processor and a communication interface, wherein the communication interface is used to receive model parameters of a first AI model, and the processor is used to obtain a first result based on the model parameters of the first AI model; wherein the first result includes at least one of the following: an On-Off mode, wherein the On-Off mode is applied to a target communication service; and a DRX configuration.

[0013] Eighthly, a network-side device is provided, the network-side device including a processor and a memory, the memory storing a program or instructions executable on the processor, the program or instructions, when executed by the processor, implementing the steps of the method as described in the second aspect.

[0014] In a ninth aspect, a network-side device is provided, including a processor and a communication interface, wherein the communication interface is used to send model parameters of a first AI model, and the processor is used to obtain a first result based on the model parameters of the first AI model; wherein the first result includes at least one of the following: an On-Off mode of a terminal, the On-Off mode being applied to a target communication service; and a DRX configuration of the terminal.

[0015] In a tenth aspect, a readable storage medium is provided, on which a program or instructions are stored, which, when executed by a processor, implement the steps of the method described in the first aspect, or implement the steps of the method described in the second aspect.

[0016] Eleventhly, a wireless communication system is provided, comprising: a terminal and a network-side device, wherein the terminal can be used to perform the steps of the method as described in the first aspect, and the network-side device can be used to perform the steps of the method as described in the second aspect.

[0017] In a twelfth aspect, a chip is provided, the chip including a processor and a communication interface coupled to the processor, the processor being configured to run a program or instructions to implement the steps of the method described in the first aspect, or to implement the steps of the method described in the second aspect.

[0018] In a thirteenth aspect, a computer program / program product is provided, which is stored in a storage medium and is executed by at least one processor to implement the steps of the method as described in the first aspect, or to implement the steps of the method as described in the second aspect.

[0019] In this embodiment, the terminal receives model parameters from a first AI model and obtains its On-Off mode or DRX configuration based on these parameters. This embodiment obtains the terminal's On-Off mode or DRX configuration through a first AI model. By integrating AI into the wireless communication network, it facilitates matching the terminal's DRX configuration or On-Off mode with the incoming service packets, reducing invalid activation or monitoring states and promoting energy efficiency. Attached Figure Description

[0020] Figure 1 is a schematic diagram of a wireless communication system according to an embodiment of this application;

[0021] Figure 2 is a schematic flowchart of a method for determining communication parameters according to an embodiment of this application;

[0022] Figure 3 is a schematic flowchart of a method for determining communication parameters according to an embodiment of this application;

[0023] Figure 4 is a schematic diagram of the structure of a communication parameter determination device according to an embodiment of this application;

[0024] Figure 5 is a schematic diagram of the structure of a communication parameter determination device according to an embodiment of this application;

[0025] Figure 6 is a schematic diagram of the structure of a communication device according to an embodiment of this application;

[0026] Figure 7 is a schematic diagram of the structure of a terminal according to an embodiment of this application;

[0027] Figure 8 is a schematic diagram of the structure of a network-side device according to an embodiment of this application;

[0028] Figure 9 is a schematic diagram of the structure of a network-side device according to an embodiment of this application. Detailed Implementation

[0029] The technical solutions of the embodiments of this application will be clearly described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application are within the scope of protection of this application.

[0030] The terms "first," "second," etc., used in this application are used to distinguish similar objects and not to describe a specific order or sequence. It should be understood that such terms can be used interchangeably where appropriate so that embodiments of this application can be implemented in orders other than those illustrated or described herein, and the objects distinguished by "first" and "second" are generally of the same class, not limited in number; for example, the first object can be one or more. Furthermore, "or" in this application indicates at least one of the connected objects. For example, the scope of protection for "A or B" covers at least three scenarios: Scenario 1: including A but not B; Scenario 2: including B but not A; Scenario 3: including both A and B. In addition, the terms "A and / or B," "at least one of A and B," and "at least one of A or B" also cover at least the above three scenarios. The character " / " generally indicates that the preceding and following objects are in an "or" relationship.

[0031] The term "instruction" in this application can be either a direct instruction (or explicit instruction) or an indirect instruction (or implicit instruction). A direct instruction can be understood as the sender explicitly informing the receiver of specific information, the required operation, or the requested result in the instruction sent. An indirect instruction can be understood as the receiver determining the corresponding information based on the instruction sent by the sender, or making a judgment and determining the required operation or requested result based on the judgment result.

[0032] It is worth noting that the technologies described in this application are not limited to Long Term Evolution (LTE) / LTE-Advanced (LTE-A) systems, but can also be used in other wireless communication systems, such as Code Division Multiple Access (CDMA), Time Division Multiple Access (TDMA), Frequency Division Multiple Access (FDMA), Orthogonal Frequency Division Multiple Access (OFDMA), Single-carrier Frequency-Division Multiple Access (SC-FDMA), or other systems. The terms "system" and "network" in this application are often used interchangeably, and the described technologies can be used in the systems and radio technologies mentioned above, as well as in other systems and radio technologies. The following description describes New Radio (NR) systems for illustrative purposes, and the term NR is used in most of the following description; however, these technologies can also be applied to systems other than NR systems, such as 6th Generation (6G) communication systems.

[0033] Figure 1 shows a block diagram of a wireless communication system applicable to an embodiment of this application. The wireless communication system includes a terminal 11 and a network-side device 12. The terminal 11 can also be referred to as User Equipment (UE), and can be a mobile phone, tablet computer, laptop computer, notebook computer, personal digital assistant (PDA), handheld computer, netbook, ultra-mobile personal computer (UMPC), mobile internet device (MID), augmented reality (AR), virtual reality (VR) device, robot, wearable device, flight vehicle, vehicle user equipment (VUE), shipboard equipment, pedestrian user equipment (PUE), smart home (home devices with wireless communication capabilities, such as refrigerators, televisions, washing machines, or furniture), game console, personal computer (PC), ATM, or self-service machine, etc. Wearable devices include: smartwatches, smart bracelets, smart headphones, smart glasses, smart jewelry (smart bracelets, smart chains, smart rings, smart necklaces, smart anklets, smart anklets, etc.), smart wristbands, smart clothing, etc. Among these, in-vehicle devices can also be referred to as in-vehicle terminals, in-vehicle controllers, in-vehicle modules, in-vehicle components, in-vehicle chips, or in-vehicle units, etc. It should be noted that the specific type of terminal 11 is not limited in this application embodiment. Network-side equipment 12 may include access network equipment or core network equipment, wherein access network equipment may also be referred to as Radio Access Network (RAN) equipment, radio access network function, or radio access network unit. Access network equipment may include base stations, Wireless Local Area Network (WLAN) access points (APs), or Wireless Fidelity (WiFi) nodes, etc.Among them, base stations can be referred to as Node B (NB), Evolved Node B (eNB), Next Generation Node B (gNB), New Radio Node B (NR Node B), Access Point, Relay Base Station (RBS), Serving Base Station (SBS), Base Transceiver Station (BTS), Radio Base Station, Radio Transceiver, Basic Service Set (BSS), Extended Service Set (ESS), Home Node B (HNB), Home Evolved Node B, Transmit / Receive Point (TRP), Non-Terrestrial Network (NTN) equipment (such as satellite or high altitude platform stations). The term "base station" can be any suitable term in the field, such as "station" or any other appropriate term in the relevant field, as long as the same technical effect is achieved. The term "base station" is not limited to specific technical terms. It should be noted that the embodiments of this application only use the base station in the NR system as an example for introduction, and do not limit the specific type of base station.

[0034] Core network equipment, also known as core network nodes, core network functions, or core network elements, includes, but is not limited to, at least one of the following: Mobility Management Entity (MME), Access and Mobility Management Function (AMF), Session Management Function (SMF), User Plane Function (UPF), Policy Control Function (PCF), Policy and Charging Rules Function (PCRF), Edge Application Server Discovery Function (EASDF), Unified Data Management (UDM), Unified Data Repository (UDR), Home Subscriber Server (HSS), Centralized network configuration (CNC), Network Repository Function (NRF), Network Exposure Function (NEF), Local NEF (L-NEF), and Binding Support. Functions include BSF, Application Function (AF), Location Management Function (LMF), Gateway Mobile Location Centre (GMLC), Network Data Analytics Function (NWDAF), and Non-Terrestrial Network (NTN) equipment (such as satellite or high altitude platform station).It should be noted that the embodiments of this application only use the core network equipment in the NR system as an example for introduction, and do not limit the specific type of core network equipment. If the name of the core network equipment mentioned in the embodiments of this application changes in subsequent protocol versions (e.g., 6G), it is also within the scope of protection of this application.

[0035] Optionally, the core network equipment can be implemented by one or more functional modules in a single device, or by multiple devices working together; this application does not specifically limit this. It is understood that the aforementioned functional modules can be network elements in hardware devices, software functional modules running on dedicated hardware, or virtualized functional modules instantiated on a platform (e.g., a cloud platform).

[0036] The method for determining communication parameters provided in this application will be described in detail below with reference to the accompanying drawings and through some embodiments and application scenarios.

[0037] As shown in Figure 2, this application embodiment provides a method 200 for determining communication parameters. This method can be executed by a terminal, in other words, it can be executed by software or hardware installed on the terminal. The method includes the following steps.

[0038] S202: The terminal receives the model parameters of the first AI model.

[0039] In some embodiments, the model parameters of the first AI model include the architecture parameters of the first AI model, the type of the first AI model, the number of layers and coefficients of each layer of the first AI model, the ID of the first AI model, etc.

[0040] The first AI model is used to predict at least one of the DRX configuration and On-Off mode that matches the service packet arrival situation of the terminal. For example, on the terminal side, during the On time period of the DRX configuration, service packets arrive or the terminal is able to send service packets, and during the Inactivity time period of the DRX configuration, no service packets arrive or no service packets are sent; or, for another example, during the On time period of the On-Off mode, service packets arrive or the terminal is able to send service packets, and during the Off time period of the On-Off mode, no service packets arrive or no service packets are sent.

[0041] S204: The terminal obtains a first result based on the model parameters of the first AI model; wherein the first result includes at least one of the following: On-Off mode, wherein the On-Off mode is applied to the target communication service; DRX configuration.

[0042] In some embodiments, the terminal can input first information into the first AI model to obtain a first result. The first information is information related to the first result. For example, the first result includes the terminal's DRX configuration. The first information can be information related to the terminal's DRX configuration, such as the type, size, generation time, arrival time of the service packet at the core network device, transmission time from the core network device to the access network device, arrival time at the terminal, etc.

[0043] The first AI model is used to predict the first result. In some embodiments, the first AI model may be trained by a network-side device based on first training information. The first training information may be information related to the first result, including sample data and labels. The data type of the sample data is similar to the data type of the first information. For example, the sample data may include the type, size, generation time, arrival time of the core network device, transmission time from the core network device to the access network device, arrival time of the terminal, etc., of the service packet. The label is related to the first result. For example, if the first result includes the terminal's DRX configuration, the label may include information such as the optimal DRX configuration. The first AI model trained using this sample data and label is beneficial for predicting the DRX configuration that matches the arrival status of the service packet, thereby avoiding invalid terminal monitoring and reducing service latency, thus achieving the goal of terminal energy saving. Another example is if the first result includes the terminal's On-Off mode. The label may include the PDCCH timing for data transmission within a target time. The first AI model trained using this sample data and label is beneficial for predicting the On-Off mode that matches the arrival status of the service packet, thereby avoiding invalid terminal monitoring and reducing service latency, thus achieving the goal of terminal energy saving.

[0044] For network-side devices, during the On period of the On-Off mode of the terminal, the network-side device can send data to the terminal or receive data from the terminal, which helps to reduce service latency; during the Off period of the On-Off mode (such as the intersection of the Off periods of multiple terminals), the network-side device can go into sleep mode, thereby achieving the purpose of energy saving.

[0045] Similarly, network-side devices can send PDCCHs to terminals during the On period configured in the DRX of the terminal to schedule service data transmission, which helps reduce service latency; network-side devices can hibernate during the Inactivity period configured in the DRX (such as the intersection of the Inactivity periods of multiple terminals), thereby achieving energy saving.

[0046] The On-Off modes in various embodiments of this application may include periodic configurations, On-Off indications specifying time granularity, etc., and can be used to control a single channel or multiple channels. For example, an On-Off mode used only for monitoring the Physical Downlink Control Channel (PDCCH) can also be represented as a search space or a time-domain location for PDCCH monitoring.

[0047] In some embodiments, the target communication service applied in the On-Off mode includes at least one of the following: PDCCH monitoring, Radio Resource Management (RRM) measurement, radio link measurement, beam management measurement, Channel State Information (CSI) measurement, Physical Downlink Shared Channel (PDSCH) reception, Physical Uplink Control Channel (PUCCH) transmission, Sounding Reference Signal (SRS) transmission, and Physical Uplink Shared Channel (PUSCH) transmission.

[0048] The aforementioned beam management measurements may include beam failure monitoring signal measurements, candidate beam signal measurements, etc.

[0049] The aforementioned CSI measurements may include CSI measurements based on the Synchronization Signal and Physical Broadcast Channel Block (SSB), CSI measurements based on the Channel State Information-Reference Signal (CSI-RS), and so on.

[0050] The aforementioned PDSCH reception includes Semi-Persistent Scheduling (SPS) PDSCH reception and Dynamic Grant (DG) PDSCH reception.

[0051] The above PUSCH transmissions include Configured Grant (CG) PUSCH transmissions, DG PUSCH transmissions, etc.

[0052] This embodiment applies the On-Off mode to the target communication service. During the On period of the On-Off mode, the terminal can perform operations such as data monitoring, receiving data, and sending data, which helps to reduce service latency. During the Off period of the On-Off mode, the terminal can go into sleep mode, thereby avoiding invalid monitoring by the terminal and achieving the purpose of energy saving.

[0053] In some embodiments, the DRX configuration includes at least one of the following: DRX period, DRX on duration timer, DRX retransmission timer for uplink or downlink, DRX long period and offset, DRX short period, DRX short period timer, start offset of DRX on duration timer, Hybrid Automatic Repeat Request Round Trip Time (HARQ RTT) timer for uplink or downlink, DRX wake-up time, or the result of whether the DRX on duration timer is enabled.

[0054] The results of whether DRX wake-up time is enabled can include the results of whether DRX on duration is enabled for one cycle, or the results of whether DRX on duration is enabled for multiple cycles.

[0055] In this embodiment, the result of whether the DRX wake-up time or the DRX continuous listening timer is enabled is included in the DRX configuration. In other embodiments, the result of whether the DRX wake-up time or the DRX continuous listening timer is enabled can also be listed alongside the DRX configuration.

[0056] This embodiment, through the predicted DRX configuration, helps to match the terminal's DRX configuration with the service packet arrival situation, thereby avoiding invalid terminal monitoring and reducing service latency, thus achieving the goal of terminal energy saving.

[0057] The communication parameter determination method provided in this application involves the terminal receiving model parameters from a first AI model and obtaining the terminal's On-Off mode or DRX configuration based on these model parameters. This application's method obtains the terminal's On-Off mode or DRX configuration through the first AI model. By integrating AI into the wireless communication network, it facilitates matching the terminal's DRX configuration or On-Off mode with the incoming service packets, reducing invalid activation or monitoring states of the terminal and promoting energy saving.

[0058] In some embodiments, the terminal obtaining a first result based on the model parameters of the first AI model includes: the terminal obtaining a second result based on the model parameters of the first AI model; the terminal obtaining the first result based on the second result and first configuration information; wherein, the second result includes at least one of the following: 1) a service prediction result, the service prediction result being related to the On-Off mode or the DRX configuration; 2) an intermediate output result of the AI ​​model; the first configuration information is the configuration parameters for obtaining the first result based on the second result.

[0059] In this embodiment, the second result can be referred to as an intermediate result. The terminal can obtain the DRX configuration or On-Off mode based on the second result and the first configuration information.

[0060] In some embodiments, the second result includes at least one of the following for the future M service packets: generation time, arrival time at the core network node (or core network device), arrival time at the radio access network node (or access network device), size, and type; where M is a positive integer.

[0061] In some embodiments, the On-Off mode of the terminal is represented by at least one of the following:

[0062] 1) A first bitmap with a first time unit as the granularity, wherein each bit in the first bitmap is used to indicate on or off.

[0063] For example, the On-Off mode uses a first-bit graph with slots as the granularity. The first-bit graph is 101010... with a length of 20. Each bit in the first-bit graph corresponds to a slot. A bit value of 1 indicates that the corresponding slot is in the On state, and the terminal can perform operations such as data monitoring, receiving data, and sending data, which helps reduce service latency. A bit value of 0 indicates that the corresponding slot is in the Off state, and the terminal can sleep, thereby avoiding invalid monitoring by the terminal and achieving the purpose of energy saving.

[0064] 2) A second bitmap with the granularity of the transmission timing (or listening timing) of the signal or channel, where each bit in the second bitmap is used to indicate on or off.

[0065] For example, the On-Off mode is a second bitmap with the granularity of the signal or channel transmission occasion. The length of the second bitmap is M. These M bits correspond to M PDCCH monitoring occasions after the effective time. 1 in the second bitmap indicates the On state, that is, the terminal needs to monitor at the corresponding PDCCH monitoring occasion; 0 in the second bitmap indicates the Off state, that is, the terminal does not need to monitor at the corresponding PDCCH monitoring occasion.

[0066] 3) One or more periodic On-Off configurations.

[0067] A periodic On-Off mode configuration may include at least one of the following: period and offset, start position and duration of On duration; wherein, within a period, the time outside the On duration is the Off duration.

[0068] For multiple periodic On-Off mode configurations, the union or intersection of the On durations of multiple On-Off modes is used as the On duration that the terminal needs to use, and the remaining time is the Off duration.

[0069] 4) Whether the terminal is turned on or whether the terminal has become active.

[0070] For example, whether the terminal is turned on or becomes active within the target time period. When the terminal is turned on or becomes active within the target time period, it can be considered to be in the "On" state. The terminal can perform operations such as data monitoring, receiving data, and sending data, which helps reduce service latency. When the terminal is not turned on or becomes active within the target time period, it can be considered to be in the "Off" state. The terminal can go into sleep mode, thereby avoiding invalid monitoring by the terminal and achieving the purpose of energy saving.

[0071] 5) The starting position or time window of the time when the terminal is turned on or becomes active.

[0072] When a terminal is turned on or becomes active within a target time period, it can be considered to be in an "On" state. The terminal can perform operations such as data monitoring, receiving data, and sending data, which helps reduce service latency.

[0073] In some embodiments, the method further includes at least one of the following:

[0074] 1) The terminal receives a first message, the first message being used to indicate at least one of the following: the time for inference using the first AI model; the first AI model; the rule for selecting the first AI model; the input parameters of the first AI model (such as first information); the output parameters of the first AI model (such as first result).

[0075] 2) The terminal sends a second message, which indicates at least one of the following: the time when the terminal expects or will use the first AI model for inference; the time when the terminal expects or will use the first AI model; the rule for selecting the first AI model; the input parameters of the first AI model that the terminal expects or will use; and the input parameter information of the first AI model sent by the network-side device.

[0076] This embodiment, by limiting the understanding through a first message or a second message, helps ensure consistency between the terminal and network-side devices, avoiding the problem of reduced prediction accuracy caused by inconsistent understanding. For example, the terminal and network-side devices use the same first AI model; the time for inference using the first AI model by both the terminal and network-side devices is within a first time range; the terminal and network-side devices can select the same first AI model; the input parameters of the first AI model used by the terminal and network-side devices are consistent; the output parameters of the first AI model used by the terminal and network-side devices are consistent, for example, both instructing the first AI model to output an On-Off mode.

[0077] In some embodiments, the first AI model is a general AI model; or, the first AI model is one of multiple AI models, which are distinguished by at least one of the following: terminal type; type of region where the terminal is located; service type; current time interval; cell type.

[0078] This embodiment uses a general AI model, which helps to reduce model training overhead.

[0079] This embodiment utilizes multiple AI models, which helps to select a more reasonable first AI model for different types of terminals and terminals in different regions, thereby further improving the accuracy of the predicted On-Off mode or DRX configuration.

[0080] In some embodiments, the method further includes the terminal receiving third information, the third information being used to instruct the terminal to use the first AI model, the third information being used to instruct at least one of the following:

[0081] 1) The identifier ID of the first AI model.

[0082] 2) The time period during which the first AI model was used.

[0083] 3) Activation command for the first AI model.

[0084] 4) Change the AI ​​model used, for example, change from using the second AI model to using the first AI model.

[0085] In this embodiment, the network-side device can indicate AI model-related information to the terminal, which helps the terminal and the network-side device to maintain a consistent understanding of the currently used AI model and avoids the problem of reduced prediction accuracy caused by inconsistent understanding.

[0086] In some embodiments, the method further includes the terminal determining the first AI model based on at least one of the following:

[0087] 1) The network-side device indicated that the first AI model was used.

[0088] 2) The current service type of the terminal.

[0089] 3) The current scenario of the terminal.

[0090] 4) The current DRX configuration of the terminal.

[0091] 5) The cell type of the terminal.

[0092] 6) The type of terminal.

[0093] 7) The current time interval.

[0094] By limiting the information described above, this embodiment helps the terminal and network-side devices to maintain a consistent understanding of the first AI model used, thus avoiding the problem of reduced prediction accuracy caused by inconsistent understanding.

[0095] In some embodiments, the method further includes the terminal reporting fourth information, the fourth information including monitoring information of the first AI model, the fourth information being used to indicate at least one of the following:

[0096] 1) Identification of the first AI model.

[0097] 2) Monitoring period.

[0098] 3) Whether the QoS requirements of the terminal are met.

[0099] 4) The satisfaction level of the terminal.

[0100] 5) Service packet latency of the terminal.

[0101] 6) The energy consumption or energy efficiency of the terminal.

[0102] 7) The percentage of data scheduling that the terminal has during the activation time under the DRX configuration.

[0103] 8) The percentage of effective scheduling during PDCCH listening time.

[0104] In this embodiment, the network-side device can configure the terminal to monitor and report on the first AI model. The monitoring and reporting content can be related to terminal energy saving, which is beneficial for the network-side device to update the first AI model and thus obtain a more reasonable On-Off mode or DRX configuration.

[0105] In some embodiments, the method further includes the terminal receiving second configuration information, the second configuration information being used by the terminal to monitor the first AI model, and the second configuration information being used to indicate at least one of the following:

[0106] 1) The identifier ID of the first AI model.

[0107] 2) The time period that the terminal needs to monitor.

[0108] 3) The timing of the terminal reporting.

[0109] 4) The content reported by the terminal includes at least one of the following: whether the QoS requirements of the terminal are met; the satisfaction level of the terminal; the service packet latency of the terminal; the energy consumption or energy efficiency of the terminal; the percentage of data scheduling by the terminal during the activation time under the DRX configuration; and the percentage of effective scheduling during PDCCH monitoring.

[0110] In this embodiment, the network-side device can configure the terminal to monitor and report on the first AI model. The monitoring and reporting content can be related to terminal energy saving, which is beneficial for the network-side device to update the first AI model and thus obtain a more reasonable On-Off mode or DRX configuration.

[0111] In some embodiments, the terminal obtaining a first result based on the model parameters of the first AI model includes: the terminal inputting first information into the first AI model to obtain the first result; the first information includes at least one of the following:

[0112] 1) Types of business packages, for example, the first information includes the types of X business packages.

[0113] 2) The size of the service package, for example, the first information includes the size of X service packages.

[0114] 3) The generation time of the service package, for example, the first information includes the generation time of X service packages.

[0115] 4) Information on the time or time interval of service packets arriving at the core network node. For example, the first piece of information includes the time when X service packets arrive at the core network node.

[0116] 5) Information on the time or time interval for service packets to be transmitted from the core network node to the radio access network node. For example, the first information includes the time for X service packets to be transmitted from the core network to the radio access network node.

[0117] 6) The time when the service package arrives at the terminal.

[0118] 7) Grouping information of business packages.

[0119] 8) Terminal type.

[0120] 9) The current time interval, such as daytime or nighttime.

[0121] 10) Community type.

[0122] 11) Terminal identifier (e.g., UE ID).

[0123] 12) Terminal location.

[0124] 13) The mobile status of the terminal.

[0125] 14) The terminal's operating status, such as power saving or non-power saving status.

[0126] 15) Terminal type.

[0127] 16) The area type where the terminal is located, such as indoor or outdoor.

[0128] 17) Reference Signal Receiving Power (RSRP) of the terminal.

[0129] 18) Interference situation of the terminal.

[0130] 19) The terminal's search space configuration may include, for example, the type of search space, the DCI format associated with the search space, the control resource set associated with the search space, the PDCCH monitoring period and time offset, the number of continuously monitored time slots, the PDCCH monitoring pattern in a time slot, the aggregation level, and at least one of the following: the number of PDCCH candidates corresponding to the aggregation level.

[0131] 20) DRX configuration of the terminal.

[0132] 21) The power consumption or energy efficiency of the terminal.

[0133] 22) Service package delay.

[0134] This embodiment uses a first AI model and various first pieces of information to perform model prediction, which helps the first AI model predict the DRX configuration that matches the incoming service packet situation, thereby avoiding invalid terminal monitoring and reducing service latency, thus achieving the purpose of terminal energy saving; it also helps the first AI model predict the On-Off mode that matches the incoming service packet situation, thereby avoiding invalid terminal monitoring and reducing service latency, thus achieving the purpose of terminal energy saving.

[0135] The method for determining communication parameters according to an embodiment of this application has been described in detail above with reference to FIG2. The method for determining communication parameters according to another embodiment of this application will now be described in detail with reference to FIG3. It is understood that the interaction between the network-side device and the terminal described from the perspective of the network-side device is the same as or corresponds to the terminal-side description in the method shown in FIG2; to avoid repetition, relevant descriptions are appropriately omitted.

[0136] Figure 3 is a schematic flowchart illustrating the method for determining communication parameters according to an embodiment of this application, which can be applied to network-side devices. As shown in Figure 3, the method 300 includes the following steps.

[0137] S302: The network-side device sends the model parameters of the first AI model.

[0138] S304: The network-side device obtains a first result based on the model parameters of the first AI model; wherein the first result includes at least one of the following: the On-Off mode of the terminal, wherein the On-Off mode is applied to the target communication service; and the DRX configuration of the terminal.

[0139] This embodiment does not limit the order of S302 and S304.

[0140] The communication parameter determination method provided in this application involves a network-side device sending model parameters of a first AI model. Based on these model parameters, the network-side device obtains the terminal's On-Off mode or DRX configuration. This application's method obtains the terminal's On-Off mode or DRX configuration through a first AI model. By integrating AI into the wireless communication network, it facilitates matching the terminal's DRX configuration or On-Off mode with the incoming service packets, reducing invalid activation or monitoring states of the terminal and promoting energy saving.

[0141] In some embodiments, the target communication service includes at least one of the following: PDCCH monitoring, RRM measurement, radio link measurement, beam management measurement, CSI measurement, PDSCH reception, PUCCH transmission, SRS transmission, and PUSCH transmission.

[0142] In some embodiments, the DRX configuration includes at least one of the following: DRX period, DRX continuous listener timer, DRX retransmission timer, DRX long period and offset, DRX short period, DRX short period timer, DRX continuous listener start offset, HARQ RTT timer, DRX wake-up time, or the result of whether the DRX continuous listener timer is enabled.

[0143] In some embodiments, the On-Off mode is represented by at least one of the following: 1) a first bit map with a first time unit as the granularity, each bit in the first bit map being used to indicate on or off; 2) a second bit map with a signal or channel transmission timing as the granularity, each bit in the second bit map being used to indicate on or off; 3) one or more periodic On-Off configurations; 4) whether the terminal is turned on or whether the terminal becomes active; 5) the start position or time window of the time when the terminal is turned on or becomes active.

[0144] In some embodiments, the method further includes at least one of the following: 1) the network-side device sends a first message, the first message indicating at least one of the following: the time for inference using the first AI model; the first AI model; the rule for selecting the first AI model; the input parameters of the first AI model; the output parameters of the first AI model; 2) the network-side device receives a second message, the second message indicating at least one of the following: the time when the terminal expects or will use the first AI model for inference; the time when the terminal expects or will use the first AI model; the rule for selecting the first AI model; the input parameters of the first AI model that the terminal expects or will use; and information related to the input parameters of the first AI model sent by the network-side device.

[0145] In some embodiments, the first AI model is a general AI model; or, the first AI model is one of a plurality of AI models, which are distinguished by at least one of the following: terminal type; type of region where the terminal is located; service type; current time interval; cell type.

[0146] In some embodiments, the method further includes the network-side device sending third information, the third information being used to instruct the terminal to use the first AI model, the third information being used to instruct at least one of the following: 1) the identifier ID of the first AI model; 2) the usage period of the first AI model; 3) the activation command of the first AI model; 4) changing the AI ​​model used.

[0147] In some embodiments, the method further includes the network-side device determining the first AI model based on at least one of the following: 1) the network-side device indicates that the first AI model is used; 2) the current service type of the terminal; 3) the current scenario of the terminal; 4) the current DRX configuration of the terminal; 5) the cell type of the terminal; 6) the type of the terminal; 7) the current time interval.

[0148] In some embodiments, the method further includes the network-side device receiving fourth information, the fourth information including monitoring information of the first AI model, the fourth information being used to indicate at least one of the following: 1) the identifier of the first AI model; 2) the monitoring time period; 3) whether the QoS requirements of the terminal are met; 4) the satisfaction of the terminal; 5) the service packet latency of the terminal; 6) the energy consumption or energy efficiency of the terminal; 7) the percentage of data scheduling performed by the terminal during the activation time under the DRX configuration; 8) the percentage of effective scheduling during PDCCH monitoring.

[0149] In this embodiment, the network-side device can configure the terminal to monitor and report on the first AI model. The monitoring and reporting content can be related to terminal energy saving, which is beneficial for the network-side device to update the first AI model and thus obtain a more reasonable On-Off mode or DRX configuration.

[0150] In some embodiments, the method further includes the network-side device sending second configuration information, the second configuration information being used by the terminal to monitor the first AI model, the second configuration information being used to indicate at least one of the following: 1) the identifier ID of the first AI model; 2) the time period for which the terminal needs to monitor; 3) the timing of the terminal reporting; 4) the content reported by the terminal, including at least one of the following: whether the QoS requirements of the terminal are met; the satisfaction level of the terminal; the service packet latency of the terminal; the energy consumption or energy efficiency of the terminal; the percentage of data scheduling by the terminal during the activation time under the DRX configuration; and the percentage of effective scheduling during PDCCH monitoring.

[0151] In this embodiment, the network-side device can configure the terminal to monitor and report on the first AI model. The monitoring and reporting content can be related to terminal energy saving, which is beneficial for the network-side device to update the first AI model and thus obtain a more reasonable On-Off mode or DRX configuration.

[0152] In some embodiments, the method further includes: the network-side device performing model training based on first training information to obtain the first AI model.

[0153] In this embodiment, the network-side device can pre-train the model to obtain the first AI model.

[0154] In some embodiments, the network-side device obtaining a first result based on the model parameters of the first AI model includes: the network-side device inputting first information into the first AI model to obtain a first result.

[0155] The first information may be related to one terminal or multiple terminals. For example, the first information may be the service type, service arrival time information, service packet size information, search space configuration information, control resource set configuration information of one or more terminals, and time information, corresponding aggregation level, and number of blind detections of the PDCCH monitored by one or more terminals.

[0156] This embodiment, by limiting the terminal, helps the terminal and network-side devices to maintain a consistent understanding of the first information, thus avoiding the problem of reduced prediction accuracy caused by inconsistent understanding of the first information.

[0157] In some embodiments, the first information or the first training information includes at least one of the following:

[0158] 1) The type of service package, for example, the first information or the first training information includes X types of service packages.

[0159] 2) The size of the service package, for example, the size of X service packages included in the first information or the first training information.

[0160] 3) The generation time of the service package, for example, the generation time of X service packages included in the first information or the first training information.

[0161] 4) Information on the time or time interval of service packets arriving at the core network node, for example, the first information or the first training information includes the time of arrival of X service packets at the core network node.

[0162] 5) Time or time interval information of service packets being transmitted from the core network node to the radio access network node, for example, the first information or the first training information includes the time of X service packets being transmitted from the core network to the radio access network node.

[0163] 6) The time when the service package arrives at the terminal.

[0164] 7) Grouping information of business packages.

[0165] 8) Terminal type.

[0166] 9) The current time interval, such as daytime or nighttime.

[0167] 10) Community type.

[0168] 11) Terminal identifier (e.g., UE ID).

[0169] 12) Terminal location.

[0170] 13) The mobile status of the terminal.

[0171] 14) The terminal's operating status, such as power saving or non-power saving status.

[0172] 15) Terminal type.

[0173] 16) The area type where the terminal is located, such as indoor or outdoor.

[0174] 17) Reference Signal Receiving Power (RSRP) of the terminal.

[0175] 18) Interference situation of the terminal.

[0176] 19) The terminal's search space configuration may include, for example, the type of search space, the DCI format associated with the search space, the control resource set associated with the search space, the PDCCH monitoring period and time offset, the number of continuously monitored time slots, the PDCCH monitoring pattern in a time slot, the aggregation level, and at least one of the following: the number of PDCCH candidates corresponding to the aggregation level.

[0177] 20) DRX configuration of the terminal.

[0178] 21) The power consumption or energy efficiency of the terminal.

[0179] 22) Service package delay.

[0180] This embodiment obtains a first AI model by training it with multiple first training information, or by using the first AI model and multiple first information for model prediction. This is beneficial for the first AI model to predict the DRX configuration that matches the incoming service packet situation, thereby avoiding invalid terminal monitoring and reducing service latency, thus achieving the purpose of terminal energy saving; it is also beneficial for the first AI model to predict the On-Off mode that matches the incoming service packet situation, thereby avoiding invalid terminal monitoring and reducing service latency, thus achieving the purpose of terminal energy saving.

[0181] In some embodiments, the first information or the first training information is obtained through at least one of the following methods:

[0182] 1) Obtained from the packet header of the service packet. For example, the packet header of the service packet carries some service-related information, and the network-side device obtains the first information or the first training information by parsing the packet header of the service packet.

[0183] 2) The network-side device collects or receives the information. For example, if the inference node or training node is a radio access network node, the information about the arrival of service packets at the radio access network node can be recorded by that node; if the inference node or training node is a core network node, the information is transmitted from the radio access network node to the core network node; if the inference node or training node is a radio access network node, the information is transmitted from the core network node to the radio access network node.

[0184] 3) Obtained based on the terminal's reporting. For example, the terminal may report first information or first training information to the network-side device.

[0185] This embodiment provides various methods to help network-side devices obtain first information or first training information.

[0186] In some embodiments, the first training information includes sample data and labels for the sample data, satisfying at least one of the following:

[0187] 1) The sample data consists of information related to X service packages, and the label consists of information related to Y service packages following the X service packages, where X and Y are positive integers.

[0188] Information related to the service packet includes, for example, the type, size, generation time, arrival time of the core network device, transmission time from the core network device to the access network device, and arrival time of the terminal.

[0189] Optionally, the first training information used for training the first AI model may include, in addition to the sample data and labels mentioned above, other information besides the relevant information of the business packages within the time period corresponding to the X business packages, such as terminal identifiers, etc. See the introduction of the first training information below.

[0190] 2) The sample data consists of information related to X service packages, and the label is the optimal DRX configuration determined based on the information of Y service packages following the X service packages, where X and Y are positive integers.

[0191] Optionally, the first training information used for training the first AI model may include, in addition to the sample data and labels mentioned above, other information besides the relevant information of the business packages within the time period corresponding to the X business packages, such as terminal identifiers, etc., as can be found in the introduction of the first training information.

[0192] 3) The sample data consists of information related to X service packets, and the tag is: the PDCCH timing within the target time after the X service packets, where PDCCH within the PDCCH timing schedules data transmission, and X and Y are positive integers.

[0193] Optionally, the first training information used for training the first AI model may include, in addition to the sample data and labels mentioned above, other information besides the relevant information of the business packages within the time period corresponding to the X business packages, such as terminal identifiers, etc. See the introduction of the first training information above.

[0194] This embodiment uses a first AI model trained with sample data and labels to predict the DRX configuration that matches the incoming service packet situation, thereby avoiding invalid terminal monitoring and reducing service latency, thus achieving the goal of terminal energy saving; it also helps to predict the On-Off mode that matches the incoming service packet situation, thereby avoiding invalid terminal monitoring and reducing service latency, thus achieving the goal of terminal energy saving.

[0195] To explain in detail the method for determining communication parameters provided in the embodiments of this application, the following will be described in conjunction with several specific embodiments.

[0196] Example 1: Energy-saving method for terminal-based transmission (Transfer) of the first AI model.

[0197] In this embodiment, both the terminal and the network-side device perform AI inference to obtain the terminal's On-Off mode or DRX configuration. This On-Off mode or DRX configuration can be matched with the terminal's service characteristics or optimal activity characteristics, thereby solving the problem of power wastage caused by the terminal performing a large number of invalid monitoring or activities, and achieving the gains of reducing power consumption and improving energy efficiency.

[0198] This embodiment includes the following steps:

[0199] Step 1: The terminal receives the model parameters of the first AI model sent by the wireless access network node or the core network node.

[0200] In some embodiments, the model parameters of the first AI model include the architecture parameters of the first AI model, the type of the first AI model, the number of layers and coefficients of each layer of the first AI model, the ID of the first AI model, etc.

[0201] In some embodiments, the model parameters of the first AI model include AI model update parameters, including at least one of the following:

[0202] 1) Instruct or agree in advance on the parameter subset one of the first AI model, and update all parameters of the parameter subset one; wherein the parameter subset one of the first AI model is a subset of all parameters of the first AI model.

[0203] 2) In advance, the parameter subset one of the first AI model is indicated or agreed upon, and this update indicates the parameter subset two of the first AI model, updating all parameters of parameter subset two; wherein, the parameter subset two of the first AI model is a subset of parameter subset one.

[0204] 3) Indicate all model parameters of the first AI model or a subset thereof.

[0205] Step 2: The terminal obtains a first result based on the model parameters of the first AI model; wherein, the first result includes at least one of the following: On-Off mode, wherein the On-Off mode is applied to the target communication service; DRX configuration; and the result of whether the DRX wake-up time or the DRX continuous listening timer is enabled.

[0206] The terminal's On-Off mode is applied in at least one of the following: PDCCH monitoring, RRM measurement, wireless link measurement, beam management measurement, CSI measurement, PDSCH reception, PUCCH transmission, SRS transmission, and PUSCH transmission.

[0207] The terminal's On-Off mode includes at least one of the following:

[0208] 1) The first AI model outputs the monitoring time-domain position of the PDCCH, which is the time-domain position of the PDCCH search space. In this case, the time-domain position of the search space received by the terminal is generated by the configured first AI model (i.e., the AI-based search space).

[0209] 2) The search space or search space group of the PDCCH to be monitored by the first AI model output terminal, which is a configured periodic search space.

[0210] 3) For a configured search space or search space group, the first AI model outputs the On duration and Off duration over a period of time, which may be periodic or non-periodic. The terminal monitors the PDCCH at the PDCCH listening time corresponding to the On duration.

[0211] 4) The first AI model outputs the result of whether each PDCCH listening time is on or off, for example, represented by a bitmap.

[0212] For other signals or channels, such as CSI-RS, PDSCH, PUCCH, SRS, and CG-PUSCH, the processing method is similar to that of PDCCH described above.

[0213] In some embodiments, the first result is an On-Off mode of multiple channels or signals, or a non-energy-saving to energy-saving mode, including at least one of the following:

[0214] 1) This On-Off mode is a periodic mode, that is, there is an On duration or non-energy-saving duration every period.

[0215] 2) The On-Off mode is a non-periodic or irregular mode, such as On-Off based on a certain time granularity or non-energy-saving-energy-saving bitmap indication.

[0216] The DRX configuration includes at least one of the following: DRX period, DRX on duration timer, DRX retransmission timer for uplink or downlink, DRX long period and offset, DRX short period, DRX short period timer, DRX on duration start offset, and Hybrid Automatic Repeat Request Round Trip Time (HARQ RTT) timer for uplink or downlink.

[0217] In this embodiment, in addition to transmitting the model parameters of the first AI model, the terminal and the wireless access network node / core network node can also transmit some input information and AI inference time configuration information so that the terminal and the network-side device can obtain the same output.

[0218] Example 2: Terminal energy-saving method based on AI model transmission for network-side devices.

[0219] In this embodiment, both the network-side device and the terminal perform AI inference to obtain the terminal's On-Off mode or DRX configuration. This On-Off mode or DRX configuration can be matched with the terminal's service characteristics or optimal activity characteristics, thereby solving the problem of power wastage caused by the terminal performing a large number of invalid monitoring or activities, and achieving the gains of reducing power consumption and improving energy efficiency.

[0220] This embodiment includes the following steps:

[0221] Step 1: The wireless access network node or core network node sends the model parameters of the first AI model.

[0222] Step 2: Obtain a first result based on the model parameters of the first AI model sent, wherein the first result includes at least one of the following:

[0223] 1) The terminal's On-Off mode is applied to at least one of the following: PDCCH monitoring, RRM measurement, radio link measurement, beam management measurement, CSI measurement, PDSCH reception, PUCCH transmission, SRS transmission, and PUSCH transmission. The result of whether the terminal's DRX configuration or DRX on duration is enabled.

[0224] 2) The terminal's DRX configuration includes at least one of the following: DRX period, DRX on duration timer, DRX retransmission timer for uplink or downlink, DRX long period and offset, DRX short period, DRX short period timer, DRX on duration start offset, and Hybrid Automatic Repeat Request Round Trip Time (HARQ RTT) timer for uplink or downlink.

[0225] 3) The result of whether the DRX wake-up timer or the DRX continuous listening timer is enabled.

[0226] In this embodiment, the wireless access network node or the core network node trains the first AI model. For specific training details, please refer to the previous embodiment.

[0227] The communication parameter determination method provided in this application can be executed by a communication parameter determination device. This application uses the example of a communication parameter determination device executing the communication parameter determination method to illustrate the communication parameter determination device provided in this application.

[0228] This application provides a communication parameter determination device. As an example, the communication parameter determination device can be a communication device or a component in a communication device, such as a chip. The communication device can be a terminal, a network-side device, or a server, etc. Exemplarily, the terminal can be, but is not limited to, the type of terminal 11 listed above, and the network-side device can be, but is not limited to, the type of network-side device 12 listed above. This application does not impose specific limitations.

[0229] The communication parameter determination device includes a receiving module, a transmitting module, and a processing module. These modules can be implemented in software or hardware. When implemented in hardware, the processing module can be implemented by a processor. For example, the processor can include general-purpose processors, special-purpose processors, etc., such as central processing units (CPUs), microprocessors, digital signal processors (DSPs), artificial intelligence (AI) processors, graphics processing units (GPUs), application-specific integrated circuits (ASICs), network processors (NPs), field-programmable gate arrays (FPGAs), or other programmable logic devices, gate circuits, transistors, discrete hardware components, etc. The receiving and transmitting modules can be implemented by a communication interface, which can include one or more of the following: transceivers, pins, circuits, buses, radio frequency units, etc.

[0230] Specifically, referring to Figure 4, when the communication parameter determining device is a terminal or a component within a terminal, the communication parameter determining device 400 includes:

[0231] The communication module 402 is used to receive the model parameters of the first AI model.

[0232] Processing module 404 is used to obtain a first result based on the model parameters of the first AI model; wherein the first result includes at least one of the following: On-Off mode, wherein the On-Off mode is applied to the target communication service; DRX configuration.

[0233] The communication parameter determination device provided in this application embodiment includes a communication module receiving model parameters from a first AI model, and a processing module obtaining the terminal's On-Off mode or DRX configuration based on the model parameters of the first AI model. This application embodiment obtains the terminal's On-Off mode or DRX configuration through a first AI model. By integrating AI into the wireless communication network, it facilitates matching the terminal's DRX configuration or On-Off mode with the incoming service packets, reducing invalid activation or monitoring states of the terminal, and promoting energy saving.

[0234] In some embodiments, the target communication service includes at least one of the following: physical downlink control channel (PDCCH) monitoring, radio resource management (RRM) measurement, radio link measurement, beam management measurement, channel state information (CSI) measurement, physical downlink shared channel (PDSCH) reception, physical uplink control channel (PUCCH) transmission, sounding reference signal (SRS) transmission, and physical uplink shared channel (PUSCH) transmission.

[0235] In some embodiments, the DRX configuration includes at least one of the following: DRX period, DRX continuous listener timer, DRX retransmission timer, DRX long period and offset, DRX short period, DRX short period timer, DRX continuous listener start offset, Hybrid Automatic Repeat Request Round Trip Time (HARQ RTT) timer, DRX wake-up time, or the result of whether the DRX continuous listener timer is enabled.

[0236] In some embodiments, the processing module 404 is configured to obtain a second result based on the model parameters of the first AI model; and obtain the first result based on the second result and the first configuration information; wherein the second result includes at least one of the following: a business prediction result, which is related to the On-Off mode or the DRX configuration; an intermediate output result of the AI ​​model; and the first configuration information is the configuration parameters for obtaining the first result based on the second result.

[0237] In some embodiments, the On-Off mode is represented by at least one of the following: 1) a first bit map with a first time unit as the granularity, each bit in the first bit map being used to indicate on or off; 2) a second bit map with a signal or channel transmission timing as the granularity, each bit in the second bit map being used to indicate on or off; 3) one or more periodic On-Off configurations; 4) whether the terminal is turned on or whether the terminal becomes active; 5) the start position or time window of the time when the terminal is turned on or becomes active.

[0238] In some embodiments, the communication module 402 is further configured to: 1) receive a first message, the first message indicating at least one of the following: the time for inference using the first AI model; the first AI model; the rule for selecting the first AI model; the input parameters of the first AI model; the output parameters of the first AI model; 2) send a second message, the second message indicating at least one of the following: the time when the terminal expects or will use the first AI model for inference; the time when the terminal expects or will use the first AI model; the rule for selecting the first AI model; the input parameters of the first AI model that the terminal expects or will use; and information related to the input parameters of the first AI model sent by the network-side device.

[0239] In some embodiments, the first AI model is a general AI model; or, the first AI model is one of a plurality of AI models, which are distinguished by at least one of the following: terminal type; type of region where the terminal is located; service type; current time interval; cell type.

[0240] In some embodiments, the communication module 402 is further configured to receive third information, the third information being used to instruct the terminal to use the first AI model, the third information being used to instruct at least one of the following: 1) the identifier ID of the first AI model; 2) the usage time period of the first AI model; 3) the activation command of the first AI model; 4) changing the AI ​​model used.

[0241] In some embodiments, the processing module 404 is further configured to determine the first AI model based on at least one of the following: 1) the network-side device indicates that the first AI model is used; 2) the current service type of the terminal; 3) the current scenario of the terminal; 4) the current DRX configuration of the terminal; 5) the cell type of the terminal; 6) the type of the terminal; 7) the current time interval.

[0242] In some embodiments, the communication module 402 is further configured to report fourth information, which includes monitoring information of the first AI model. The fourth information is used to indicate at least one of the following: 1) the identifier of the first AI model; 2) the monitoring time period; 3) whether the QoS requirements of the terminal are met; 4) the satisfaction of the terminal; 5) the service packet latency of the terminal; 6) the energy consumption or energy efficiency of the terminal; 7) the proportion of data scheduling of the terminal during the activation time under the DRX configuration; and 8) the proportion of effective scheduling during PDCCH monitoring.

[0243] In some embodiments, the communication module 402 is further configured to receive second configuration information, the second configuration information being used by the terminal to monitor the first AI model, the second configuration information being used to indicate at least one of the following: 1) the identifier ID of the first AI model; 2) the time period for which the terminal needs to monitor; 3) the timing of the terminal reporting; 4) the content reported by the terminal, including at least one of the following: whether the QoS requirements of the terminal are met; the satisfaction level of the terminal; the service packet latency of the terminal; the energy consumption or energy efficiency of the terminal; the percentage of data scheduling by the terminal during the activation time under the DRX configuration; and the percentage of effective scheduling during PDCCH monitoring.

[0244] In some embodiments, the processing module 404 is configured to input first information into the first AI model to obtain a first result; the first information includes at least one of the following:

[0245] 1) The type of service package, for example, the first information or the first training information includes X types of service packages.

[0246] 2) The size of the service package, for example, the size of X service packages included in the first information or the first training information.

[0247] 3) The generation time of the service package, for example, the generation time of X service packages included in the first information or the first training information.

[0248] 4) Information on the time or time interval of service packets arriving at the core network node, for example, the first information or the first training information includes the time of arrival of X service packets at the core network node.

[0249] 5) Time or time interval information of service packets being transmitted from the core network node to the radio access network node, for example, the first information or the first training information includes the time of X service packets being transmitted from the core network to the radio access network node.

[0250] 6) The time when the service package arrives at the terminal.

[0251] 7) Grouping information of business packages.

[0252] 8) Terminal type.

[0253] 9) The current time interval, such as daytime or nighttime.

[0254] 10) Community type.

[0255] 11) Terminal identifier (e.g., UE ID).

[0256] 12) Terminal location.

[0257] 13) The mobile status of the terminal.

[0258] 14) The terminal's operating status, such as power saving or non-power saving status.

[0259] 15) Terminal type.

[0260] 16) The area type where the terminal is located, such as indoor or outdoor.

[0261] 17) Reference Signal Receiving Power (RSRP) of the terminal.

[0262] 18) Interference situation of the terminal.

[0263] 19) The terminal's search space configuration may include, for example, the type of search space, the DCI format associated with the search space, the control resource set associated with the search space, the PDCCH monitoring period and time offset, the number of continuously monitored time slots, the PDCCH monitoring pattern in a time slot, the aggregation level, and at least one of the following: the number of PDCCH candidates corresponding to the aggregation level.

[0264] 20) DRX configuration of the terminal.

[0265] 21) The power consumption or energy efficiency of the terminal.

[0266] 22) Service package delay.

[0267] Referring to Figure 5, when the communication parameter determination device is a network-side device or a component within a network-side device, the communication parameter determination device 500 includes:

[0268] The communication module 502 is used to send the model parameters of the first AI model.

[0269] The processing module 504 is used to obtain a first result based on the model parameters of the first AI model; wherein the first result includes at least one of the following: the On-Off mode of the terminal, wherein the On-Off mode is applied to the target communication service; and the DRX configuration of the terminal.

[0270] The communication parameter determination device provided in this application embodiment involves a communication module sending model parameters of a first AI model, and a processing module obtaining the terminal's On-Off mode or DRX configuration based on the model parameters of the first AI model. This application embodiment obtains the terminal's On-Off mode or DRX configuration through a first AI model. By integrating AI into the wireless communication network, it facilitates matching the terminal's DRX configuration or On-Off mode with the incoming service packets, reducing invalid activation or monitoring states of the terminal, and promoting energy saving.

[0271] In some embodiments, the target communication service includes at least one of the following: PDCCH monitoring, RRM measurement, radio link measurement, beam management measurement, CSI measurement, PDSCH reception, PUCCH transmission, SRS transmission, and PUSCH transmission.

[0272] In some embodiments, the DRX configuration includes at least one of the following: DRX period, DRX continuous listener timer, DRX retransmission timer, DRX long period and offset, DRX short period, DRX short period timer, DRX continuous listener start offset, HARQ RTT timer, DRX wake-up time, or the result of whether the DRX continuous listener timer is enabled.

[0273] In some embodiments, the On-Off mode is represented by at least one of the following: 1) a first bit map with a first time unit as the granularity, each bit in the first bit map being used to indicate on or off; 2) a second bit map with a signal or channel transmission timing as the granularity, each bit in the second bit map being used to indicate on or off; 3) one or more periodic On-Off configurations; 4) whether the terminal is turned on or whether the terminal becomes active; 5) the start position or time window of the time when the terminal is turned on or becomes active.

[0274] In some embodiments, the communication module 502 is further configured to: 1) send a first message, the first message indicating at least one of the following: the time for inference using the first AI model; the first AI model; the rule for selecting the first AI model; the input parameters of the first AI model; the output parameters of the first AI model; 2) receive a second message, the second message indicating at least one of the following: the time when the terminal expects or will use the first AI model for inference; the time when the terminal expects or will use the first AI model; the rule for selecting the first AI model; the input parameters of the first AI model that the terminal expects or will use; and information related to the input parameters of the first AI model sent by the network-side device.

[0275] In some embodiments, the first AI model is a general AI model; or, the first AI model is one of a plurality of AI models, which are distinguished by at least one of the following: terminal type; type of region where the terminal is located; service type; current time interval; cell type.

[0276] In some embodiments, the communication module 502 is further configured to send third information, the third information being used to instruct the terminal to use the first AI model, the third information being used to instruct at least one of the following: 1) the identifier ID of the first AI model; 2) the usage time period of the first AI model; 3) the activation command of the first AI model; 4) changing the AI ​​model used.

[0277] In some embodiments, the processing module 504 is further configured to determine the first AI model based on at least one of the following: 1) the network-side device indicates that the first AI model is used; 2) the current service type of the terminal; 3) the current scenario of the terminal; 4) the current DRX configuration of the terminal; 5) the cell type of the terminal; 6) the type of the terminal; 7) the current time interval.

[0278] In some embodiments, the communication module 502 is further configured to receive fourth information, the fourth information including monitoring information of the first AI model, the fourth information being used to indicate at least one of the following: 1) the identifier of the first AI model; 2) the monitoring time period; 3) whether the QoS requirements of the terminal are met; 4) the satisfaction of the terminal; 5) the service packet latency of the terminal; 6) the energy consumption or energy efficiency of the terminal; 7) the proportion of data scheduling of the terminal during the activation time under the DRX configuration; 8) the proportion of effective scheduling during PDCCH monitoring.

[0279] In some embodiments, the communication module 502 is further configured to send second configuration information, the second configuration information being used by the terminal to monitor the first AI model, the second configuration information being used to indicate at least one of the following: 1) the identifier ID of the first AI model; 2) the time period for which the terminal needs to monitor; 3) the timing of the terminal reporting; 4) the content reported by the terminal, including at least one of the following: whether the QoS requirements of the terminal are met; the satisfaction level of the terminal; the service packet latency of the terminal; the energy consumption or energy efficiency of the terminal; the percentage of data scheduling by the terminal during the activation time under the DRX configuration; and the percentage of effective scheduling during PDCCH monitoring.

[0280] In some embodiments, the processing module 504 is further configured to perform model training based on the first training information to obtain the first AI model.

[0281] In some embodiments, the processing module 504 is used to input first information into the first AI model to obtain a first result.

[0282] In some embodiments, the first information or the first training information includes at least one of the following:

[0283] 1) The type of service package, for example, the first information or the first training information includes X types of service packages.

[0284] 2) The size of the service package, for example, the size of X service packages included in the first information or the first training information.

[0285] 3) The generation time of the service package, for example, the generation time of X service packages included in the first information or the first training information.

[0286] 4) Information on the time or time interval of service packets arriving at the core network node, for example, the first information or the first training information includes the time of arrival of X service packets at the core network node.

[0287] 5) Time or time interval information of service packets being transmitted from the core network node to the radio access network node, for example, the first information or the first training information includes the time of X service packets being transmitted from the core network to the radio access network node.

[0288] 6) The time when the service package arrives at the terminal.

[0289] 7) Grouping information of business packages.

[0290] 8) Terminal type.

[0291] 9) The current time interval, such as daytime or nighttime.

[0292] 10) Community type.

[0293] 11) Terminal identifier (e.g., UE ID).

[0294] 12) Terminal location.

[0295] 13) The mobile status of the terminal.

[0296] 14) The terminal's operating status, such as power saving or non-power saving status.

[0297] 15) Terminal type.

[0298] 16) The area type where the terminal is located, such as indoor or outdoor.

[0299] 17) Reference Signal Receiving Power (RSRP) of the terminal.

[0300] 18) Interference situation of the terminal.

[0301] 19) The terminal's search space configuration may include, for example, the type of search space, the DCI format associated with the search space, the control resource set associated with the search space, the PDCCH monitoring period and time offset, the number of continuously monitored time slots, the PDCCH monitoring pattern in a time slot, the aggregation level, and at least one of the following: the number of PDCCH candidates corresponding to the aggregation level.

[0302] 20) DRX configuration of the terminal.

[0303] 21) The power consumption or energy efficiency of the terminal.

[0304] 22) Service package delay.

[0305] In some embodiments, the first information or the first training information is obtained through at least one of the following methods:

[0306] 1) Obtained from the packet header of the service packet. For example, the packet header of the service packet carries some service-related information, and the network-side device obtains the first information or the first training information by parsing the packet header of the service packet.

[0307] 2) The network-side device collects or receives the information. For example, if the inference node or training node is a radio access network node, the information about the arrival of service packets at the radio access network node can be recorded by that node; if the inference node or training node is a core network node, the information is transmitted from the radio access network node to the core network node; if the inference node or training node is a radio access network node, the information is transmitted from the core network node to the radio access network node.

[0308] 3) Obtained based on the terminal's reporting. For example, the terminal may report first information or first training information to the network-side device.

[0309] In some embodiments, the first training information includes sample data and labels for the sample data, satisfying at least one of the following:

[0310] 1) The sample data consists of information related to X service packages, and the label consists of information related to Y service packages following the X service packages, where X and Y are positive integers.

[0311] Information related to the service packet includes, for example, the type, size, generation time, arrival time of the core network device, transmission time from the core network device to the access network device, and arrival time of the terminal.

[0312] 2) The sample data consists of information related to X service packages, and the label is the optimal DRX configuration determined based on the information of Y service packages following the X service packages, where X and Y are positive integers.

[0313] 3) The sample data consists of information related to X service packets, and the tag is: the PDCCH timing within the target time after the X service packets, where PDCCH within the PDCCH timing schedules data transmission, and X and Y are positive integers.

[0314] The communication parameter determination device provided in this application embodiment can implement the various processes implemented in the method embodiments of Figures 2 to 3 and achieve the same technical effect. To avoid repetition, it will not be described again here.

[0315] As shown in Figure 6, this application embodiment also provides a communication device 600, including a processor 601 and a memory 602. The memory 602 stores a program or instructions that can run on the processor 601. For example, when the communication device 600 is a terminal, the program or instructions executed by the processor 601 implement the various steps of the above-described method embodiment for determining communication parameters, and achieve the same technical effect. When the communication device 600 is a network-side device, the program or instructions executed by the processor 601 implement the various steps of the above-described method embodiment for determining communication parameters, and achieve the same technical effect. To avoid repetition, this will not be described again here.

[0316] This application also provides a terminal, including a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is used to run programs or instructions to implement the steps in the method embodiment shown in FIG2. This terminal embodiment corresponds to the above-described terminal-side method embodiment, and all implementation processes and methods of the above-described method embodiments can be applied to this terminal embodiment and can achieve the same technical effect. The terminal can be the communication parameter determination device shown in FIG4. Specifically, FIG7 is a schematic diagram of the hardware structure of a terminal implementing an embodiment of this application.

[0317] The terminal 700 includes, but is not limited to, at least some of the following components: radio frequency unit 701, network module 702, audio output unit 703, input unit 704, sensor 705, display unit 706, user input unit 707, interface unit 708, memory 709, and processor 710.

[0318] Those skilled in the art will understand that the terminal 700 may also include a power supply (such as a battery) for powering various components. The power supply can be logically connected to the processor 710 through a power management system, thereby enabling functions such as managing charging, discharging, and power consumption through the power management system. The terminal structure shown in Figure 7 does not constitute a limitation on the terminal. The terminal may include more or fewer components than shown, or combine certain components, or have different component arrangements, which will not be elaborated here.

[0319] It should be understood that, in this embodiment, the input unit 704 may include a graphics processor 7041 and a microphone 7042. The graphics processor 7041 processes image data of still images or videos obtained by an image capture device (such as a camera) in video capture mode or image capture mode. The display unit 706 may include a display panel 7061, which may be configured in the form of a liquid crystal display, an organic light-emitting diode, or the like. The user input unit 707 includes at least one of a touch panel 7071 and other input devices 7072. The touch panel 7071 is also called a touch screen. The touch panel 7071 may include a touch detection device and a touch controller. Other input devices 7072 may include, but are not limited to, physical keyboards, function keys (such as volume control buttons, power buttons, etc.), trackballs, mice, and joysticks, which will not be described in detail here.

[0320] In this embodiment, after receiving downlink data from the network-side device, the radio frequency unit 701 can transmit it to the processor 710 for processing; in addition, the radio frequency unit 701 can send uplink data to the network-side device. Typically, the radio frequency unit 701 includes, but is not limited to, antennas, amplifiers, transceivers, couplers, low-noise amplifiers, duplexers, etc.

[0321] The memory 709 can be used to store software programs or instructions, as well as various data. The memory 709 may primarily include a first storage area for storing programs or instructions and a second storage area for storing data. The first storage area may store the operating system, application programs or instructions required for at least one function (such as sound playback, image playback, etc.). Furthermore, the memory 709 may include volatile memory or non-volatile memory. The non-volatile memory may be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. Volatile memory can be random access memory (RAM), static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDRSDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM), and direct memory bus RAM (DRRAM). The memory 709 in the embodiments of this application includes, but is not limited to, these and any other suitable types of memory.

[0322] Processor 710 may include one or more processing units; optionally, processor 710 integrates an application processor and a modem processor, wherein the application processor mainly handles operations involving the operating system, user interface, and applications, and the modem processor mainly handles wireless communication signals, such as a baseband processor. It is understood that the aforementioned modem processor may also not be integrated into processor 710.

[0323] The radio frequency unit 701 is used to receive model parameters of the first AI model; the processor 710 is used to obtain a first result based on the model parameters of the first AI model; wherein the first result includes at least one of the following: On-Off mode, the On-Off mode being applied to the target communication service; DRX configuration.

[0324] In this embodiment, the terminal receives model parameters from a first AI model and obtains its On-Off mode or DRX configuration based on these parameters. This embodiment obtains the terminal's On-Off mode or DRX configuration through a first AI model. By integrating AI into the wireless communication network, it facilitates matching the terminal's DRX configuration or On-Off mode with the incoming service packets, reducing invalid activation or monitoring states and promoting energy efficiency.

[0325] It is understood that the implementation process of each implementation method mentioned in this embodiment can refer to the relevant description of the embodiment of the method for determining communication parameters, and achieve the same or corresponding technical effects. To avoid repetition, it will not be described again here.

[0326] This application also provides a network-side device, including a processor and a communication interface. The communication interface is coupled to the processor, and the processor is used to run programs or instructions to implement the steps of the method embodiment shown in FIG3. This network-side device embodiment corresponds to the above-described network-side device method embodiment. All implementation processes and methods of the above-described method embodiments can be applied to this network-side device embodiment and can achieve the same technical effect.

[0327] Specifically, this application embodiment also provides a network-side device, which can be the communication parameter determination device shown in FIG5. As shown in FIG8, the network-side device 800 includes: an antenna 81, a radio frequency device 82, a baseband device 83, a processor 84, and a memory 85. The antenna 81 is connected to the radio frequency device 82. In the uplink direction, the radio frequency device 82 receives information through the antenna 81 and sends the received information to the baseband device 83 for processing. In the downlink direction, the baseband device 83 processes the information to be transmitted and sends it to the radio frequency device 82. The radio frequency device 82 processes the received information and transmits it through the antenna 81.

[0328] The method executed by the network-side device in the above embodiments can be implemented in the baseband device 83, which includes a baseband processor.

[0329] The baseband device 83 may include at least one baseband board, on which multiple chips are disposed, as shown in FIG8. One of the chips is, for example, a baseband processor, which is connected to the memory 85 via a bus interface to call the program or instructions in the memory 85 to execute the network device operation shown in the above method embodiment.

[0330] The network-side device may also include a network interface 86, such as a Common Public Radio Interface (CPRI).

[0331] The radio frequency device 82 is used to transmit model parameters of the first AI model; the processor 84 is used to obtain a first result based on the model parameters of the first AI model; wherein the first result includes at least one of the following: On-Off mode, the On-Off mode being applied to the target communication service; DRX configuration.

[0332] In addition, the network-side device 800 of this application embodiment also includes: a program or instructions stored in a memory 85 and executable on a processor 84. The processor 84 calls the program or instructions in the memory 85 to execute the methods executed by each module shown in FIG5 and achieve the same technical effect. To avoid repetition, it will not be described in detail here.

[0333] Specifically, this application also provides a network-side device. As shown in FIG9, the network-side device 900 includes a processor 901, a network interface 902, and a memory 903. The network-side device may be the communication parameter determination device shown in FIG5. The network interface 902 is, for example, a Common Public Radio Interface (CPRI).

[0334] The network interface 902 is used to send model parameters of the first AI model; the processor 901 is used to obtain a first result based on the model parameters of the first AI model; wherein the first result includes at least one of the following: the On-Off mode of the terminal, the On-Off mode being applied to the target communication service; and the DRX configuration of the terminal.

[0335] In addition, the network-side device 900 of this application embodiment also includes: a program or instructions stored in a memory 903 and executable on a processor 901. The processor 901 calls the program or instructions in the memory 903 to execute the methods executed by each module shown in FIG5 and achieve the same technical effect. To avoid repetition, it will not be described in detail here.

[0336] This application also provides a readable storage medium storing a program or instructions. When the program or instructions are executed by a processor, they implement the various processes of the above-described method for determining communication parameters and achieve the same technical effect. To avoid repetition, they will not be described again here.

[0337] The processor mentioned above is either the processor in the terminal described in the above embodiments or the processor in the network-side device. The readable storage medium includes computer-readable storage media, such as computer read-only memory (ROM), random access memory (RAM), magnetic disk, or optical disk. In some examples, the readable storage medium may be a non-transient readable storage medium.

[0338] This application embodiment also provides a chip, which includes a processor and a communication interface. The communication interface is coupled to the processor. The processor is used to run programs or instructions to implement the various processes of the above-described method embodiment for determining communication parameters, and can achieve the same technical effect. To avoid repetition, it will not be described again here.

[0339] It should be understood that the chip mentioned in the embodiments of this application may also be referred to as a system-on-a-chip, system chip, chip system, or system-on-a-chip, etc.

[0340] This application also provides a computer program / program product, which is stored in a storage medium and executed by at least one processor to implement the various processes of the above-described method for determining communication parameters, and can achieve the same technical effect. To avoid repetition, it will not be described again here.

[0341] This application embodiment also provides a communication parameter determination system, including: a terminal and a network-side device, wherein the terminal can be used to execute the steps of the communication parameter determination method described above, and the network-side device can be used to execute the steps of the communication parameter determination method described above.

[0342] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element. Furthermore, it should be noted that the scope of the methods and apparatuses in the embodiments of this application is not limited to performing functions in the order shown or discussed, but may also include performing functions substantially simultaneously or in the reverse order, depending on the functions involved. For example, the described methods may be performed in a different order than described, and various steps may be added, omitted, or combined. Additionally, features described with reference to certain examples may be combined in other examples.

[0343] From the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of computer software products plus necessary general-purpose hardware platforms, and of course, they can also be implemented by hardware. The computer software product is stored in a storage medium (such as ROM, RAM, magnetic disk, optical disk, etc.), and the computer software product includes several instructions to cause the terminal or network-side device to execute the methods described in the various embodiments of this application.

[0344] The embodiments of this application have been described above with reference to the accompanying drawings. However, this application is not limited to the specific embodiments described above. The specific embodiments described above are merely illustrative and not restrictive. Those skilled in the art can make many other implementations under the guidance of this application without departing from the spirit and scope of the claims. All of these implementations are within the protection scope of this application.

Claims

1. A method for determining communication parameters, comprising: The terminal receives the model parameters of the first AI model; The terminal obtains a first result based on the model parameters of the first AI model; wherein the first result includes at least one of the following: On-Off mode, wherein the On-Off mode is applied to the target communication service; Discontinuous reception DRX configuration.

2. The method according to claim 1, wherein, The target communication service includes at least one of the following: physical downlink control channel (PDCCH) monitoring, radio resource management (RRM) measurement, radio link measurement, beam management measurement, channel state information (CSI) measurement, physical downlink shared channel (PDSCH) reception, physical uplink control channel (PUCCH) transmission, sounding reference signal (SRS) transmission, and physical uplink shared channel (PUSCH) transmission. or, The DRX configuration includes at least one of the following: DRX period, DRX continuous listener timer, DRX retransmission timer, DRX long period and offset, DRX short period, DRX short period timer, DRX continuous listener start offset, Hybrid Automatic Repeat Request Round Trip Time (HARQ RTT) timer, DRX wake-up time, or whether the DRX continuous listener timer is enabled.

3. The method of claim 1 or 2, wherein, The terminal obtains a first result based on the model parameters of the first AI model, including: The terminal obtains a second result based on the model parameters of the first AI model; The terminal obtains the first result based on the second result and the first configuration information; The second result includes at least one of the following: business forecast result, which is related to the On-Off mode or the DRX configuration; intermediate output result of the AI ​​model; The first configuration information is the configuration parameters obtained based on the second result.

4. The method according to any one of claims 1 to 3, wherein, The On-Off mode is represented by at least one of the following: The first bitmap is defined with a first time unit as the granularity, and each bit in the first bitmap is used to indicate whether it is on or off; A second bitmap with the transmission timing of a signal or channel as the granularity, where each bit in the second bitmap is used to indicate on or off; One or more periodic On-Off configurations; Whether the terminal is turned on or whether the terminal has become active; The starting position or time window of the time when the terminal is turned on or becomes active.

5. The method according to any one of claims 1 to 4, wherein, The method further includes at least one of the following: The terminal receives a first message, which indicates at least one of the following: the time for inference using the first AI model; the first AI model; the rule for selecting the first AI model; the input parameters of the first AI model; and the output parameters of the first AI model. The terminal sends a second message, which indicates at least one of the following: the time when the terminal expects or will use the first AI model for inference; the time when the terminal expects or will use the first AI model; the rule for selecting the first AI model; the input parameters of the first AI model that the terminal expects or will use; and information related to the input parameters of the first AI model sent by the network-side device.

6. The method according to any one of claims 1 to 5, wherein, The first AI model is a general AI model; or, The first AI model is one of multiple AI models, which are distinguished by at least one of the following: terminal type; type of region where the terminal is located; service type; current time interval; cell type.

7. The method according to any one of claims 1 to 6, wherein, The method further includes the terminal receiving third information, the third information being used to instruct the terminal to use the first AI model, the third information being used to instruct at least one of the following: The identifier ID of the first AI model; The time period during which the first AI model was used; The activation command for the first AI model; Change the AI ​​model used.

8. The method according to any one of claims 1 to 7, wherein, The method further includes the terminal determining the first AI model based on at least one of the following: The network-side device indicated that the first AI model was used; The current service type of the terminal; The current scenario in which the terminal is located; The current DRX configuration of the terminal; The cell type of the terminal; The type of terminal; The current time interval.

9. The method according to any one of claims 1 to 8, wherein, The method further includes the terminal reporting fourth information, the fourth information including monitoring information of the first AI model, the fourth information being used to indicate at least one of the following: The identifier of the first AI model; The monitoring period; Does the terminal meet the QoS requirements? The satisfaction level of the terminal; The service packet latency of the terminal; The energy consumption or energy efficiency of the terminal; The terminal has a certain percentage of data scheduling during the activation time under the DRX configuration; There is a percentage of effective scheduling during PDCCH listening.

10. The method according to any one of claims 1 to 9, wherein, The method further includes the terminal receiving second configuration information, the second configuration information being used by the terminal to monitor the first AI model, and the second configuration information being used to indicate at least one of the following: The identifier ID of the first AI model; The time period that the terminal needs to monitor; The timing of the terminal's reporting; The information reported by the terminal includes at least one of the following: whether the QoS requirements of the terminal are met; the satisfaction level of the terminal; the service packet latency of the terminal; the energy consumption or energy efficiency of the terminal; and the percentage of data scheduling performed by the terminal during the activation time under the DRX configuration. There is a percentage of effective scheduling during PDCCH listening.

11. The method according to any one of claims 1 to 10, wherein, The terminal obtaining the first result based on the model parameters of the first AI model includes: the terminal inputting first information into the first AI model to obtain the first result; the first information includes at least one of the following: Types of business packages; Size of the service package; The generation time of the business package; Information on the time or time interval at which service packets arrive at the core network node; Information on the time or time interval between the transmission of service packets from the core network node to the radio access network node; The time it takes for the service packet to arrive at the terminal; Grouping information for service packages; Terminal type; The current time interval; Community type; Terminal identifier; Terminal location; The mobile status of the terminal; The terminal's operating status; Terminal type; The region type where the terminal is located; The terminal's reference signal received power RSRP; Interference experienced by the terminal; Terminal search space configuration; Terminal DRX configuration; The power consumption or energy efficiency of the terminal; Service package latency.

12. A method for determining communication parameters, comprising: The network-side device sends the model parameters of the first AI model; The network-side device obtains a first result based on the model parameters of the first AI model; wherein the first result includes at least one of the following: The terminal's On-Off mode, wherein the On-Off mode is applied to the target communication service; DRX configuration for the terminal.

13. The method according to claim 12, wherein, The target communication service includes at least one of the following: PDCCH monitoring, RRM measurement, radio link measurement, beam management measurement, CSI measurement, PDSCH reception, PUCCH transmission, SRS transmission, and PUSCH transmission. or, The DRX configuration includes at least one of the following: DRX period, DRX continuous listener timer, DRX retransmission timer, DRX long period and offset, DRX short period, DRX short period timer, DRX continuous listener start offset, HARQ RTT timer, DRX wake-up time, or whether the DRX continuous listener timer is enabled.

14. The method of claim 12 or 13, wherein, The On-Off mode is represented by at least one of the following: The first bitmap is defined with a first time unit as the granularity, and each bit in the first bitmap is used to indicate whether it is on or off; A second bitmap with the transmission timing of a signal or channel as the granularity, where each bit in the second bitmap is used to indicate on or off; One or more periodic On-Off configurations; Whether the terminal is turned on or whether the terminal has become active; The starting position or time window of the time when the terminal is turned on or becomes active.

15. The method according to any one of claims 12 to 14, wherein, The method further includes at least one of the following: The network-side device sends a first message, which indicates at least one of the following: the time for inference using the first AI model; the first AI model; the rule for selecting the first AI model; the input parameters of the first AI model; and the output parameters of the first AI model. The network-side device receives a second message, which indicates at least one of the following: the time when the terminal expects or will use the first AI model for inference; the time when the terminal expects or will use the first AI model; the rule for selecting the first AI model; the input parameters of the first AI model that the terminal expects or will use; and information related to the input parameters of the first AI model sent by the network-side device.

16. The method according to any one of claims 12 to 15, wherein, The first AI model is a general AI model; or, The first AI model is one of multiple AI models, which are distinguished by at least one of the following: terminal type; type of region where the terminal is located; service type; current time interval; cell type.

17. The method according to any one of claims 12 to 16, wherein, The method further includes the network-side device sending third information, the third information being used to instruct the terminal to use the first AI model, the third information being used to instruct at least one of the following: The identifier ID of the first AI model; The time period during which the first AI model was used; The activation command for the first AI model; Change the AI ​​model used.

18. The method according to any one of claims 12 to 16, wherein, The method further includes the network-side device determining the first AI model based on at least one of the following: The network-side device indicated that the first AI model was used; The current service type of the terminal; The current scenario in which the terminal is located; The current DRX configuration of the terminal; The cell type of the terminal; The type of terminal; The current time interval.

19. The method according to any one of claims 12 to 18, wherein, The method further includes the network-side device receiving fourth information, the fourth information including monitoring information of the first AI model, the fourth information being used to indicate at least one of the following: The identifier of the first AI model; The monitoring period; Does the terminal meet the QoS requirements? The satisfaction level of the terminal; The service packet latency of the terminal; The energy consumption or energy efficiency of the terminal; The terminal has a certain percentage of data scheduling during the activation time under the DRX configuration; There is a percentage of effective scheduling during PDCCH listening.

20. The method of any one of claims 12 to 19, wherein, The method further includes the network-side device sending second configuration information, the second configuration information being used by the terminal to monitor the first AI model, and the second configuration information being used to indicate at least one of the following: The identifier ID of the first AI model; The time period that the terminal needs to monitor; The timing of the terminal's reporting; The information reported by the terminal includes at least one of the following: whether the QoS requirements of the terminal are met; the satisfaction level of the terminal; the service packet latency of the terminal; the energy consumption or energy efficiency of the terminal; and the percentage of data scheduling performed by the terminal during the activation time under the DRX configuration. There is a percentage of effective scheduling during PDCCH listening.

21. The method according to any one of claims 12 to 20, wherein, The method further includes: The network-side device trains the model based on the first training information to obtain the first AI model.

22. The method of any one of claims 12 to 21, wherein, The network-side device obtains the first result based on the model parameters of the first AI model, including: The network-side device inputs the first information into the first AI model to obtain the first result.

23. The method of claim 21 or 22, wherein, The first information or the first training information includes at least one of the following: Types of business packages; Size of the service package; The generation time of the business package; Information on the time or time interval at which service packets arrive at the core network node; Information on the time or time interval between the transmission of service packets from the core network node to the radio access network node; The time it takes for the service packet to arrive at the terminal; Grouping information for service packages; Terminal type; The current time interval; Community type; Terminal identifier; Terminal location; The mobile status of the terminal; The terminal's operating status; Terminal type; The region type where the terminal is located; The terminal's reference signal received power RSRP; Interference experienced by the terminal; Terminal search space configuration; Terminal DRX configuration; The power consumption or energy efficiency of the terminal; Service package latency.

24. The method of claim 23, wherein, The first information or the first training information is obtained through at least one of the following methods: Obtained based on the packet header of the business packet; The network-side device collects or receives the information; This is obtained based on the report from the terminal.

25. The method according to claim 23, wherein, The first training information includes sample data and the labels of the sample data, satisfying at least one of the following: The sample data consists of information related to X service packages, and the tags are: information related to Y service packages following the X service packages; The sample data consists of relevant information for X service packages, and the label is: the optimal DRX configuration determined based on the relevant information of Y service packages following the X service packages; The sample data consists of information related to X service packets, and the tag is: the PDCCH timing within the target time after the X service packets, where PDCCH scheduling data transmission occurs within the PDCCH timing; Where X and Y are positive integers.

26. A device for determining communication parameters, applied to a terminal, comprising: The communication module is used to receive the model parameters of the first AI model; The processing module is configured to obtain a first result based on the model parameters of the first AI model; wherein the first result includes at least one of the following: On-Off mode, which is applied to the target communication service; DRX configuration.

27. The apparatus of claim 26, wherein, The processing module is used to obtain a second result based on the model parameters of the first AI model; and to obtain the first result based on the second result and the first configuration information. The second result includes at least one of the following: business forecast result, which is related to the On-Off mode or the DRX configuration; intermediate output result of the AI ​​model; The first configuration information is the configuration parameters obtained based on the second result.

28. The apparatus of claim 26 or 27, wherein, The communication module is also used for at least one of the following: Receive a first message, the first message indicating at least one of the following: the time for inference using the first AI model; the first AI model; the rule for selecting the first AI model; the input parameters of the first AI model; the output parameters of the first AI model; Send a second message, the second message being used to indicate at least one of the following: the time when the terminal expects or will use the first AI model for inference; the time when the terminal expects or will use the first AI model; the rule for selecting the first AI model; the input parameters of the first AI model that the terminal expects or will use; and information related to the input parameters of the first AI model sent by the network-side device.

29. A device for determining communication parameters, applied to a network-side device, comprising: The communication module is used to send the model parameters of the first AI model; The processing module is configured to obtain a first result based on the model parameters of the first AI model; wherein the first result includes at least one of the following: The terminal's On-Off mode, wherein the On-Off mode is applied to the target communication service; DRX configuration for the terminal.

30. The apparatus of claim 29, wherein, The communication module is also used for at least one of the following: Send a first message, the first message being used to indicate at least one of the following: the time for inference using the first AI model; the first AI model; the rule for selecting the first AI model; the input parameters of the first AI model; the output parameters of the first AI model; A second message is received, the second message indicating at least one of the following: the time when the terminal expects or will use the first AI model for inference; the time when the terminal expects or will use the first AI model; the rule for selecting the first AI model; the input parameters of the first AI model that the terminal expects or will use; and information related to the input parameters of the first AI model sent by the network-side device.

31. The apparatus of claim 29 or 30, wherein, The communication module is further configured to send third information, the third information being used to instruct the terminal to use the first AI model, and the third information being used to instruct at least one of the following: The identifier ID of the first AI model; The time period during which the first AI model was used; The activation command for the first AI model; Change the AI ​​model used.

32. A terminal comprising a processor and a memory, the memory storing a program or instructions executable on the processor, the program or instructions, when executed by the processor, implementing the steps of the method as claimed in any one of claims 1 to 11.

33. A network-side device, comprising a processor and a memory, the memory storing a program or instructions executable on the processor, the program or instructions, when executed by the processor, implementing the steps of the method as claimed in any one of claims 12 to 25.

34. A readable storage medium storing a program or instructions that, when executed by a processor, implement the steps of the method as claimed in any one of claims 1-11, or implement the steps of the method as claimed in any one of claims 12-25.

Images