Parameter selection method, parameter configuration method, terminal and network side device

Abstract

This application discloses a parameter selection method, a parameter configuration method, a terminal, and a network-side device, belonging to the field of communication technology. The parameter selection method in this application includes: the terminal determining a first condition it satisfies; and using the artificial intelligence (AI) model parameters corresponding to the first condition.

Description

Technical Field

[0001] This application belongs to the field of communication technology, specifically relating to a parameter selection method, a parameter configuration method, a terminal, and a network-side device. Background Technology

[0002] With the development of communication technology, artificial intelligence (AI) models are gradually becoming an indispensable part of network architecture. AI models have been widely used in many fields. However, currently, terminals typically use a single set of AI model parameters to cope with all application environments and scenarios, resulting in poor flexibility in using AI model parameters. Summary of the Invention

[0003] This application provides a parameter selection method, a parameter configuration method, a terminal, and a network-side device, which can solve the problem of poor flexibility in using AI model parameters in existing terminals.

[0004] Firstly, a parameter selection method is provided, which includes:

[0005] The terminal determines the first condition it meets;

[0006] The terminal uses the artificial intelligence (AI) model parameters corresponding to the first condition.

[0007] Secondly, a parameter configuration method is provided, which includes:

[0008] The network-side device sends the first configuration information to the terminal;

[0009] The first configuration information is used to configure AI model parameters for the terminal under different conditions.

[0010] Thirdly, a parameter selection device is provided, comprising:

[0011] The determination module is used to determine the first condition that the terminal meets.

[0012] The parameter usage module is used to use the AI ​​model parameters corresponding to the first condition.

[0013] Fourthly, a parameter configuration device is provided, comprising:

[0014] The first sending module is used to send the first configuration information to the terminal;

[0015] The first configuration information is used to configure AI model parameters for the terminal under different conditions.

[0016] Fifthly, a terminal is provided, the terminal including a processor, a memory, and a program or instructions stored in the memory and executable on the processor, wherein the program or instructions, when executed by the processor, implement the steps of the method described in the first aspect.

[0017] In a sixth aspect, a terminal is provided, including a processor and a communication interface, wherein the processor is used to determine a first condition satisfied by the terminal and to use AI model parameters corresponding to the first condition.

[0018] In a seventh aspect, a network-side device is provided, the network-side device including a processor, a memory, and a program or instructions stored in the memory and executable on the processor, wherein the program or instructions, when executed by the processor, implement the steps of the method as described in the second aspect.

[0019] Eighthly, a network-side device is provided, including a processor and a communication interface, wherein the communication interface is used to send first configuration information to a terminal, the first configuration information being used to configure AI model parameters for the terminal under different conditions.

[0020] In a ninth 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.

[0021] In a tenth 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.

[0022] Eleventhly, a computer program / program product is provided, the computer program / program product being stored in a non-transient storage medium, the program / program product being 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.

[0023] In this embodiment, after determining that it meets a first condition, the terminal can use the AI ​​model parameters corresponding to that first condition. This effectively improves the flexibility of the terminal in using AI model parameters and enhances system performance. Attached Figure Description

[0024] Figure 1 This is a block diagram of a wireless communication system applicable to embodiments of this application;

[0025] Figure 2 This is a schematic diagram of a neural network according to an embodiment of this application;

[0026] Figure 3 This is a schematic diagram of a neuron in a neural network according to an embodiment of this application;

[0027] Figure 4 This is a flowchart of a parameter selection method provided in an embodiment of this application;

[0028] Figure 5 This is a flowchart of a parameter configuration method provided in an embodiment of this application;

[0029] Figure 6 This is a schematic diagram of the structure of a parameter selection device provided in an embodiment of this application;

[0030] Figure 7 This is a schematic diagram of the structure of a parameter configuration device provided in an embodiment of this application;

[0031] Figure 8 This is a schematic diagram of the structure of a communication device provided in an embodiment of this application;

[0032] Figure 9 This is a schematic diagram of the structure of a terminal provided in an embodiment of this application;

[0033] Figure 10 This is a schematic diagram of the structure of a network-side device provided in an embodiment of this application. Detailed Implementation

[0034] 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.

[0035] The terms "first," "second," etc., used in the specification and claims of 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, a first object can be one or more. Furthermore, in the specification and claims, "and / or" indicates at least one of the connected objects, and the character " / " generally indicates that the preceding and following objects are in an "or" relationship.

[0036] 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), and other systems. The terms "system" and "network" in this application are often used interchangeably, and the described technologies can be used with the systems and radio technologies mentioned above, as well as with other systems and radio technologies. The following description describes New Radio (NR) systems for illustrative purposes, and the term NR is used in most of the following description; however, these technologies can also be applied to applications other than NR systems, such as 6th generation (6G) radio systems. th Generation 6G communication system.

[0037] Figure 1This diagram illustrates a block diagram of a wireless communication system applicable to embodiments of this application. The wireless communication system includes a terminal 11 and a network-side device 12. In this context, terminal 11 can also be referred to as terminal equipment or user equipment (UE). Terminal 11 can be a mobile phone, tablet computer, laptop 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, vehicle-mounted device (VUE), pedestrian terminal (PUE), smart home (home devices with wireless communication functions, such as refrigerators, televisions, washing machines, or furniture), 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, game consoles, etc. It should be noted that the specific type of terminal 11 is not limited in this embodiment. Network-side device 12 can be a base station or a core network. The base station can be referred to as a node B, evolved node B, access point, base transceiver station (BTS), radio base station, radio transceiver, basic service set (BSS), extended service set (ESS), B node, evolved B node (eNB), home B node, home evolved B node, WLAN access point, WiFi node, transmitting and receiving point (TRP), or any other suitable term in the field, as long as the same technical effect is achieved. The base station is not limited to specific technical terms. It should be noted that in this application embodiment, only the base station in the NR system is used as an example, but the specific type of base station is not limited.

[0038] Optionally, the AI ​​model in this application embodiment can be implemented in various ways, such as neural networks, decision trees, support vector machines, Bayesian classifiers, etc. The following embodiments use neural networks as an example for illustration, but do not limit the specific type of AI model.

[0039] Optionally, a neural network in one embodiment of this application can be as follows: Figure 2 As shown, it includes an input layer, a hidden layer, and an output layer. The input of the input layer is X1, X2, ..., X... n The output of the corresponding output layer is Y. A neural network is composed of neurons, which can function as follows: Figure 3 As shown. Where a1, a2...a K σ is the input to the neuron, w is the weight (or multiplicative coefficient), b is the bias (or additive coefficient), and σ(.) is the activation function. Common activation functions include the sigmoid function, the hyperbolic tangent tanh function, the rectified linear unit (ReLU), and so on.

[0040] In some embodiments, the parameters of the neural network are optimized using optimization algorithms. An optimization algorithm is a class of algorithms that minimizes or maximizes an objective function (or loss function). The objective function is often a mathematical combination of model parameters and data. For example, given model input data X and its corresponding label Y, a neural network model f(.) is constructed. After constructing the model, the predicted output f(x) can be obtained based on the input data x, and the difference between the predicted value and the true value (f(x)-Y) can be calculated; this is the loss function. The purpose of training a neural network model is to find suitable weights w and biases b that minimize the value of the corresponding loss function. The smaller the loss value, the closer the model is to the reality.

[0041] Optionally, the optimization algorithms used for neural networks in this application embodiment include, but are not limited to: Gradient Descent, Stochastic Gradient Descent (SGD), mini-batch gradient descent, Momentum, Nesterov (the inventor's name, specifically stochastic gradient descent with momentum), Adagrad (Adaptive Gradient Descent), Adadelta, RMSprop (root mean square propagation), and Adam (Adaptive Moment Estimation). During error backpropagation, these optimization algorithms calculate the gradient by taking the derivative / partial derivative of the error / loss obtained from the loss function with respect to the current neuron, adding the learning rate, previous gradients / partial derivatives / derivatives, etc., and then passing the gradient to the previous layer.

[0042] Optionally, the AI ​​model parameters in the embodiments of this application may also be referred to as AI network parameters, AI parameters, etc., and there is no limitation thereto.

[0043] The parameter selection method, parameter configuration method, terminal, and network-side device provided in this application will be described in detail below with reference to the accompanying drawings and through some embodiments and application scenarios.

[0044] Please see Figure 4 , Figure 4 This is a flowchart of a parameter selection method provided in an embodiment of this application. This method is executed by a terminal, such as... Figure 4 As shown, the method includes the following steps:

[0045] Step 41: The terminal determines the first condition it meets.

[0046] In this embodiment, the first condition may be related to a cell, an event, etc. When the terminal meets the first condition, it may be for initial access, multiple cells, cell handover, triggering a Radio Link Failure (RLF) event, and / or triggering a Radio Resource Management (RRM) event, etc.

[0047] Step 42: The terminal uses the AI ​​model parameters corresponding to the first condition.

[0048] Understandably, once the terminal determines that it meets the first condition, it can use the AI ​​model parameters that correspond to or match the first condition.

[0049] The parameter selection method in this application embodiment allows the terminal to use the AI ​​model parameters corresponding to a first condition after determining that it meets that condition. This effectively improves the flexibility of the terminal in using AI model parameters and enhances system performance.

[0050] In this embodiment of the application, after determining that it meets the first condition, the terminal can determine and use the AI ​​model parameters corresponding to the first condition based on different configuration methods, which are described below.

[0051] Method 1:

[0052] In this method 1, the network-side device can configure AI model parameters for the terminal under different conditions, so that when the terminal triggers a certain event / meets a certain condition / accesses a certain cell / switches to a certain cell, the corresponding AI model parameters are automatically used.

[0053] Optionally, the terminal can receive first configuration information from the network-side device. This first configuration information is used to configure AI model parameters for the terminal under different conditions. Then, the terminal can use the AI ​​model parameters corresponding to the first condition based on the first configuration information. In this way, with the help of the network-side device's configuration, the AI ​​model parameters corresponding to the first condition can be accurately determined and used.

[0054] Optionally, the terminal may receive first configuration information from the network-side device through at least one of the following: Radio Resource Control (RRC) signaling, Medium Access Control (MAC) control element (CE), and Downlink Control Information (DCI).

[0055] Optionally, when configuring AI model parameters for terminals under different conditions, the network-side device can indicate the correspondence between AI model parameters and conditions / events / cells through first configuration information. The first configuration information may include at least one of the following:

[0056] The correspondence between AI model parameters and conditions;

[0057] The correspondence between AI model parameters and events;

[0058] The correspondence between AI model parameters and cell locations.

[0059] In some embodiments, a set of model AI parameters can correspond to one or more conditions.

[0060] In some embodiments, a condition may correspond to one or more sets of AI model parameters.

[0061] In some embodiments, a set of model AI parameters can correspond to one or more cells.

[0062] In some embodiments, a cell may correspond to one or more sets of AI model parameters.

[0063] In this method 1, when configuring AI model parameters for the terminal under different conditions, the network-side device can have multiple scenarios, which are explained below.

[0064] Scenario 1: AI model parameters that can be used when the network-side device indicates / configures / activates various conditions.

[0065] Optionally, in this case 1, the first configuration information is used to indicate, configure, or activate the AI ​​model parameters corresponding to each condition, so that after the terminal determines that it meets the first condition, it can directly determine and use the AI ​​model parameters corresponding to the first condition.

[0066] Optionally, in case 1, each condition corresponds to one and only one set of AI model parameters.

[0067] In some embodiments, the network-side device can instruct / configure / activate the AI ​​model parameters used by the UE in the current cell and / or other cells. For example, the base station configures the UE to use AI model parameter 1 when in cell A and AI model parameter 2 when in cell B and cell C; if the UE is currently in cell A, then the UE uses AI model parameter 1.

[0068] Scenario 2: The network-side device indicates / configures / activates the set of AI model parameters that can be used under various conditions (or: AI model parameter list, AI model parameter candidate set, etc.), and specifies a set of AI model parameters for the terminal from it.

[0069] Optionally, in this second scenario, the first configuration information is used to indicate, configure, or activate the AI ​​model parameter set corresponding to each condition. Further, the terminal can receive first indication information from the network-side device and, based on the first configuration information and the first indication information, use the AI ​​model parameters corresponding to the first condition. The first indication information is used to indicate the AI ​​model parameters in the AI ​​model parameter set corresponding to the first condition, so that the terminal can determine and use the AI ​​model parameters corresponding to the first condition from the AI ​​model parameter set.

[0070] In some embodiments, the network-side device can configure or activate a list of AI model parameters, which serve as a set of candidate AI parameters for the terminal, and then specifically indicate a set of AI model parameters from the list of AI model parameters.

[0071] In some embodiments, the network-side device can instruct / configure / activate the set of AI model parameters used by the UE in the current cell and / or other cells. For example, the base station configures the set of AI model parameters used by the UE in cell A to include AI model parameter 1 and AI model parameter 2, and the set of AI model parameters shared in cells B and C includes AI model parameter 3 and AI model parameter 4; if the UE is currently in cell A, and the base station specifically instructs AI model parameter 1, then the UE uses AI model parameter 1.

[0072] In some embodiments, network-side devices can instruct / configure / activate a set of AI model parameters via RRC signaling and / or MAC CE, and specifically instruct a set of AI model parameters from it via DCI and / or MAC CE.

[0073] In some embodiments, the network-side device can configure AI parameter set 1, activate AI parameter set 2 from it, and then specifically indicate a set of AI model parameters 3 from AI parameter set 2. Here, AI parameter set 2 is a subset of AI parameter set 1, and AI model parameters 3 belong to AI model parameter set 2.

[0074] Scenario 3: The network-side device indicates / configures / activates a set of AI model parameters that can be used under various conditions, but does not specifically indicate a particular set of AI model parameters. Instead, it instructs the terminal to use the default / initially activated / preferred AI model parameters when the conditions are met (such as the current event / condition, other events / conditions, the current cell, other cells, etc.).

[0075] Optionally, in this case 3, the first configuration information is used to indicate, configure, or activate the AI ​​model parameter set corresponding to each condition. Further, the terminal can receive first indication information from the network-side device and, based on the first configuration information and the first indication information, use the AI ​​model parameters corresponding to the first condition. The first indication information is used to instruct the terminal to use at least one of the following when the condition is met: the default AI model parameter, the initially activated AI model parameter, or the preferred AI model parameter, so that after determining that it meets the first condition, the terminal uses the default / initial activated / preferred AI model parameter from the AI ​​model parameter set as the AI ​​model parameter corresponding to the first condition.

[0076] For example, when the base station configures the UE to use the AI ​​model parameter set in cell A, it includes AI model parameter 1 and AI model parameter 2. When the base station does not specifically indicate a set of AI model parameters, the base station indicates that AI model parameter 1 is used by default / preferred.

[0077] Scenario 4: The network-side device indicates / configures / activates a set of AI model parameters that can be used under various conditions, but does not specifically indicate a particular set of AI model parameters. However, the protocol stipulates that the terminal will use the default / initially activated / preferred AI model parameters when the conditions are met (such as the current event / condition, other events / conditions, the current cell, other cells, etc.).

[0078] Optionally, in scenario 4, the first configuration information is used to indicate, configure, or activate the AI ​​model parameter set corresponding to each condition. Further, the terminal can use the AI ​​model parameters corresponding to the first condition according to the first configuration information and the protocol agreement. The protocol agreement stipulates that the terminal uses at least one of the following when the condition is met: the default AI model parameter, the initially activated AI model parameter, or the preferred AI model parameter. Thus, after determining that it meets the first condition, the terminal can, according to the protocol agreement, use the default / initial activated / preferred AI model parameter from the AI ​​model parameter set as the AI ​​model parameter corresponding to the first condition.

[0079] Optionally, any one of the above-mentioned default AI model parameters, initially activated AI model parameters, and preferred AI model parameters may include at least one of the following:

[0080] Identify the smallest AI model parameter; for example, the default is to use / initial activation / preferred AI model parameter to identify the smallest AI model parameter; this identifier can also be an index, etc.

[0081] This identifier identifies the largest AI model parameter; for example, it can be used by default to identify the largest AI model parameter as either the initial activation or preferred AI model parameter; this identifier can also be an index, etc.

[0082] The AI ​​model parameters with the largest amount of data; for example, using by default / initial activation / prioritizing the AI ​​model parameters with the largest amount of data.

[0083] The AI ​​model parameters with the smallest data volume; for example, using by default / initial activation / preferential use of AI model parameters with the smallest data volume;

[0084] The parameters of the AI ​​model with the most complex model structure; for example, using the default / initial activation / preferential use of the AI ​​model parameters with the most complex model structure.

[0085] The parameters of the AI ​​model with the simplest model structure; for example, using the default / initial activation / preferential use of the parameters of the AI ​​model with the most complex model structure.

[0086] The AI ​​model parameter with the most model layers; for example, using the default / initial activation / prioritizing the AI ​​model parameter with the most model layers.

[0087] The AI ​​model parameters with the fewest model layers; for example, using the default / initial activation / preferential use of AI model parameters with the fewest model layers;

[0088] The AI ​​model parameters with the highest quantization level; for example, using the default / initial activation / preferential use of the AI ​​model parameters with the highest quantization level.

[0089] The AI ​​model parameters with the lowest quantization level; for example, using the default / initial activation / preferential use of the AI ​​model parameters with the lowest quantization level;

[0090] AI model parameters for fully connected neural network architectures; for example, default use / initial activation / preferential use of AI model parameters for fully connected neural network architectures.

[0091] AI model parameters for convolutional neural network architecture. For example, AI model parameters for default use / initial activation / preferred use of convolutional neural network architecture.

[0092] Method 2:

[0093] In this second mode, the network-side device does not configure AI model parameters for the terminal under different conditions. The terminal can, by default, initially activate, or preferentially use its own AI model parameters when the corresponding event / condition / cell (such as the current event / condition, other events / conditions, the current cell, other cells, etc.), or not restrict the AI ​​model parameters used, or use any AI model parameters, or default, initially activate, or preferentially use general AI model parameters.

[0094] Optionally, the terminal may use the AI ​​model parameters corresponding to the first condition according to a first preset rule. The first preset rule may include at least one of the following:

[0095] Under various conditions, the terminal's own AI model parameters will be used by default, during initial activation, or preferentially.

[0096] The terminal can use arbitrary AI model parameters;

[0097] Under each condition, the default, initial activation, or priority use of general AI model parameters will be implemented.

[0098] In some embodiments, for the default use / initial activation / preferred use of the terminal's own AI model parameters, or without restrictions on the AI ​​model parameters used, the corresponding prerequisite can be at least one of the following: the network-side device has not configured an AI model parameter set, the network-side device has not indicated AI model parameters, or the network-side device has configured an AI model parameter set but has not specifically indicated a certain set of AI model parameters.

[0099] In some embodiments, for the default use / initial activation / preferred use of general AI model parameters, the corresponding prerequisite can be at least one of the following: the network-side device has not configured an AI model parameter set, the network-side device has not indicated AI model parameters, or the network-side device has configured an AI model parameter set but has not specifically indicated a certain set of AI model parameters.

[0100] In some embodiments, the general AI model parameters can be AI parameters used by all cells or all UEs.

[0101] In some embodiments, general AI model parameters may be specified by a protocol or indicated by network-side devices.

[0102] In some embodiments, there can be multiple sets of general AI model parameters. For multiple sets of general AI model parameters, the terminal can select one set to use based on its own needs; alternatively, the network-side device can instruct one set of general AI model parameters for the terminal to use. For example, when the network-side device instructs a set of general AI model parameters, the identifier of that general AI model parameter can be carried in at least one of the following: System Information Block (SIB) information, Master Information Block (MIB) information, or random access information.

[0103] In this embodiment, the terminal can default to / initially activate / prefer non-AI model parameters when a corresponding event / condition / cell (such as the current event / condition, other events / conditions, the current cell, other cells, etc.) occurs. For example, the UE can use AI model parameter 1 and AI model parameter 2 in cell A. When the network-side device does not specifically indicate a set of AI model parameters, the network side indicates that non-AI model parameters should be used by default / preferred.

[0104] Optionally, the terminal may choose not to use the AI ​​model parameters corresponding to the first condition, based on a second preset rule. This second preset rule includes: using non-AI model parameters by default, initial activation, or prioritizing their use under each condition.

[0105] In some embodiments, for the default use, initial activation, or priority use of non-AI model parameters, the corresponding preconditions may be at least one of the following: the network-side device has not configured an AI model parameter set, the network-side device has not indicated AI model parameters, or the network-side device has configured an AI model parameter set but has not specifically indicated a set of AI model parameters.

[0106] In this embodiment, when the AI ​​model parameters are updated, the network-side device can send the updated AI model parameters to the terminal so that the terminal can use the updated AI model parameters.

[0107] Optionally, the terminal can receive second configuration information from the network-side device, which includes updated AI model parameters, so as to use the updated AI model parameters.

[0108] In some embodiments, when a terminal performs cell access, cell handover, or other events / conditions requiring RRC reconfiguration, the network-side device sends second configuration information to the terminal, including updated AI model parameters, so that the terminal can use the updated AI model parameters.

[0109] In some embodiments, when a UE performs cell access, the RRC configuration information sent by the base station to the UE includes updated AI model parameters.

[0110] In some embodiments, when a UE performs a cell handover, the RRC reconfiguration information sent by the base station to the UE includes updated AI model parameters.

[0111] Optionally, the cell identifier ID involved in the embodiments of this application may include at least one of the following: physical cell ID, serving cell ID, TRP ID, tracking area ID, cell group ID, reference signal (RS) identifier associated with the cell (for example, the synchronization signal and PBCH block (SSB) index is associated with the cell, and a certain SSB index represents a certain cell), etc.

[0112] Optionally, the first condition above may include at least one of the following:

[0113] 1) Initial access; for example, the initial access of a terminal to a cell is a condition.

[0114] 2) Multiple cells; for example, the terminal being in multiple cells is a condition.

[0115] 3) Cell handover; for example, a terminal triggering / occurring cell handover is a condition.

[0116] 4) Conditions determined based on cell ID; for example, different cell IDs correspond to different conditions.

[0117] 5) Conditions determined based on location region; for example, different location regions correspond to different conditions.

[0118] 6) Conditions determined based on at least one of the following: Signal-to-Noise Ratio (SNR), Reference Signal Receiving Power (RSRP), Signal-to-Interference Plus Noise Ratio (SINR), Reference Signal Received Quality (RSRQ), Layer 1 SNR, Layer 1 RSRP, Layer 1 SINR, and Layer 1 RSRQ. This category can be collectively referred to as channel quality. For example, different SNR ranges (such as high SNR range, low SNR range, and medium SNR range) correspond to different conditions; and different RSRP / SINR / RSRQ correspond to different conditions.

[0119] 7) Conditions determined based on the Bandwidth Part (BWP); for example, a terminal accessing via BWP or switching via BWP is a condition.

[0120] 8) Conditions determined based on the Tracking Area (TA) and / or Radio Access Network Notification Area (RNA); for example, a change in the TA is a condition, and different TAs correspond to different conditions, such as a certain TA area corresponding to a certain condition.

[0121] 9) Conditions determined by the operating frequency; for example, a change in the operating frequency is a condition, and different operating frequencies correspond to different conditions, such as a certain operating frequency corresponding to a certain condition.

[0122] 10) Conditions determined based on the Public Land Mobile Network (PLMN); for example, different PLMNs correspond to different conditions.

[0123] 11) Conditions determined based on terminal state; for example, whether the terminal is in a connected state or an idle state is a condition;

[0124] 12) Conditions determined based on Quality of Service (QoS) Flows and their combinations; for example, different QoS Flows correspond to different conditions. Also, if multiple QoS Flows are established simultaneously, different combinations of QoS Flows correspond to different conditions.

[0125] 13) Conditions determined based on RLF events; for example, the absence of an RLF event is a condition, and the occurrence of an RLF event is a condition.

[0126] 14) Conditions determined based on RRM events; where RRM events can include events A1 to A6, and different RRM events correspond to different conditions; for example, not having an RRM event is a condition, and having an RRM event is a condition.

[0127] 15) Conditions determined based on beam failure (BF) events and / or beam failure recovery (BFR) events; for example, no BF event is a condition, beam failure detection is a condition, new beam indication is a condition, and beam failure recovery is a condition.

[0128] 16) Conditions determined based on timing and / or timing advance (TA) measurement results; for example, different timing advance intervals correspond to different conditions.

[0129] 17) Conditions determined based on Round-Trip Time (RTT) measurement results; for example, different conditions correspond to different RTT intervals.

[0130] 18) Conditions determined based on the Observed Time Difference of Arrival (OTDOA) measurement results. For example, different OTDOA intervals correspond to different conditions.

[0131] In this embodiment of the application, the AI ​​model parameters described above may include, but are not limited to, at least one of the following:

[0132] (1) Structural information of AI models.

[0133] Taking an AI model that uses a neural network as an example, the structural information of the AI ​​model may include, but is not limited to, at least one of the following:

[0134] 1) The form of the neural network; for example, a fully connected neural network, a convolutional neural network, a recurrent neural network, or a residual network.

[0135] 2) Combinations of multiple small networks; for example, a combination of a fully connected neural network and a convolutional neural network, or a convolutional neural network and a residual network, etc.

[0136] 3) The number of hidden layers in a neural network.

[0137] 4) Connection methods between the input layer and hidden layers, connection methods between multiple hidden layers, and / or connection methods between hidden layers and output layers, etc.

[0138] 5) The number of neurons in each layer of a neural network.

[0139] 6) Special structures in neural networks. For example, special structures include batch normalization, residual structures, memory structures, attention structures, etc., which will not be listed here. For example, structural information includes the location and / or parameters of the special structures.

[0140] (2) Parameters of each neuron in the AI ​​model.

[0141] Optionally, the parameters of each neuron include, but are not limited to, at least one of the following: multiplicative coefficient w (weights), additive coefficient (bias), and activation function.

[0142] In this embodiment of the application, the AI ​​model corresponding to the above-mentioned AI model parameters can be used for at least one of the following:

[0143] a) Signal processing, including but not limited to signal detection, filtering, equalization, etc.

[0144] In some embodiments, the signal to be processed in a) may be at least one of the following: demodulation reference signal (DMRS), sounding reference signal (SRS), synchronization block (SSB), tracking reference signal (TRS), phase-tracking reference signal (PTRS), channel state information reference signal (CSI-RS), etc.

[0145] b) Signal transmission, including signal reception / transmission, etc.

[0146] In some embodiments, the channel corresponding to the signal transmission in b) may be at least one of the following: Physical Downlink Control Channel (PDCCH), Physical Downlink Shared Channel (PDSCH), Physical Uplink Control Channel (PUCCH), Physical Uplink Shared Channel (PUSCH), Physical Random Access Channel (PRACH), Physical Broadcast Channel (PBCH), etc.

[0147] c) Signal demodulation.

[0148] d) Acquisition of Channel State Information (CSI).

[0149] Optionally, the aforementioned CSI acquisition may include: 1) CSI feedback, including channel-related information, channel matrix-related information, channel characteristic information, channel matrix characteristic information, Precoding Matrix Indicator (PMI), Rank Indication (RI), CSI-RS Resource Indicator (CRI), Channel Quality Indication (CQI), Layer Indicator (LI), etc.; 2) Frequency Division Duplexing (FDD) uplink and downlink reciprocity. For FDD systems, based on partial reciprocity, the base station obtains angle and delay information from the uplink channel. This angle and delay information can be notified to the UE through CSI-RS precoding or direct indication. The UE reports according to the base station's indication or selects and reports within the range indicated by the base station, thereby reducing the UE's computational load and the overhead of CSI reporting.

[0150] e) Beam management, including but not limited to beam measurement, beam reporting, beam prediction, beam failure detection, beam failure recovery, and new beam indication during beam failure recovery.

[0151] f) Channel prediction, including but not limited to prediction of channel state information and beam prediction.

[0152] g) Interference suppression, including but not limited to intra-cell interference, inter-cell interference, out-of-band interference, intermodulation interference, etc.

[0153] h) Positioning can be achieved by estimating the specific location of the UE (including horizontal and / or vertical position) or its possible future trajectory using reference signals (e.g., SRS), or by using information such as auxiliary position estimation or trajectory estimation.

[0154] i) Forecasting of high-level services and parameters, including but not limited to forecasting throughput, required data packet size, service demands, mobility, noise information, etc.

[0155] j) Management of high-level services and parameters, including but not limited to the management of throughput, required data packet size, service requirements, movement speed, noise information, etc.

[0156] k) Parsing of control signaling, such as parsing power control related signaling and / or beam management related signaling.

[0157] Please see Figure 5 , Figure 5 This is a flowchart of a parameter configuration method provided in an embodiment of this application. This method is executed by a network-side device, such as... Figure 5 As shown, the method includes the following steps:

[0158] Step 51: The network-side device sends the first configuration information to the terminal.

[0159] In this embodiment, the first configuration information is used to configure AI model parameters for the terminal under different conditions.

[0160] The parameter configuration method of this application embodiment can configure AI model parameters for the terminal under different conditions by sending first configuration information. This allows the terminal to use the AI ​​model parameters corresponding to the first condition after determining that it meets the first condition, thereby effectively improving the flexibility of the terminal in using AI model parameters and improving system performance.

[0161] Optionally, depending on the configuration method, the first configuration information is used to indicate, configure or activate the AI ​​model parameters corresponding to each condition, or the first configuration information is used to indicate, configure or activate the set of AI model parameters corresponding to each condition, so that the terminal can determine and use the AI ​​model parameters corresponding to the first condition according to the first configuration information.

[0162] Optionally, the network-side device may send the first configuration information to the terminal through at least one of the following: RRC signaling, MAC CE, or DCI.

[0163] Optionally, when the first configuration information indicates, configures, or activates the AI ​​model parameter set corresponding to each condition, the network-side device can also send first indication information to the terminal. This first indication information is used to indicate the AI ​​model parameters in the AI ​​model parameter set corresponding to the terminal's current condition, so that the terminal can determine and use the AI ​​model parameters corresponding to the first condition from the AI ​​model parameter set. Alternatively, the first indication information is used to instruct the terminal to use at least one of the following when the condition is met: the default AI model parameter, the initially activated AI model parameter, or the preferred AI model parameter, so that after determining that it meets the first condition, the terminal uses the default / initial activated / preferred AI model parameters in the AI ​​model parameter set as the AI ​​model parameters corresponding to the first condition.

[0164] It should be noted that the default AI model parameters, the initially activated AI model parameters, or the preferred AI model parameters can be found in the above embodiments, and will not be repeated here.

[0165] In this embodiment, when the AI ​​model parameters are updated, the network-side device can send the updated AI model parameters to the terminal so that the terminal can use the updated AI model parameters. The network-side device can also send second configuration information to the terminal, which includes the updated AI model parameters, so that the terminal can use the updated AI model parameters.

[0166] In some embodiments, when the terminal performs cell access cell handover or other events / conditions that require RRC reconfiguration, the network-side device sends second configuration information to the terminal, including updated AI model parameters, so that the terminal can use the updated AI model parameters.

[0167] In some embodiments, when a UE performs cell access, the RRC configuration information sent by the base station to the UE includes updated AI model parameters.

[0168] In some embodiments, when a UE performs a cell handover, the RRC reconfiguration information sent by the base station to the UE includes updated AI model parameters.

[0169] It should be noted that the parameter selection method provided in this application embodiment can be executed by a parameter selection device, or by a control module within the parameter selection device for executing the parameter selection method. This application embodiment uses the execution of the parameter selection method by a parameter selection device as an example to illustrate the parameter selection device provided in this application embodiment.

[0170] Please see Figure 6 , Figure 6 This is a schematic diagram of a parameter selection device provided in an embodiment of this application. This device is applied to a terminal, such as... Figure 6 As shown, the parameter selection device 60 includes:

[0171] Module 61 is used to determine the first condition satisfied by the terminal;

[0172] The parameter usage module 62 is used to use the AI ​​model parameters corresponding to the first condition.

[0173] In this embodiment, after determining that it meets a first condition, the terminal can use the AI ​​model parameters corresponding to that first condition. This effectively improves the flexibility of the terminal in using AI model parameters and enhances system performance.

[0174] Optionally, the parameter selection device 60 further includes:

[0175] The first receiving module is configured to receive first configuration information from a network-side device, wherein the first configuration information is used to configure AI model parameters for the terminal under different conditions.

[0176] The parameter usage module 62 is further configured to: use the AI ​​model parameters corresponding to the first condition based on the first configuration information.

[0177] Optionally, the first configuration information is used to indicate, configure, or activate the AI ​​model parameters corresponding to each condition.

[0178] Optionally, the first configuration information includes at least one of the following:

[0179] The correspondence between AI model parameters and conditions;

[0180] The correspondence between AI model parameters and events;

[0181] The correspondence between AI model parameters and cell locations.

[0182] Optionally, the first configuration information is used to indicate, configure, or activate the set of AI model parameters corresponding to each condition.

[0183] Optionally, the first receiving module is further configured to: receive first indication information from the network-side device;

[0184] The parameter usage module 62 is further configured to: use the AI ​​model parameters corresponding to the first condition according to the first configuration information and the first indication information;

[0185] Wherein, the first indication information is used to indicate the AI ​​model parameter in the AI ​​model parameter set corresponding to the first condition; or, the first indication information is used to indicate that the terminal uses at least one of the following when the condition is met: the default AI model parameter, the initially activated AI model parameter, or the preferred AI model parameter.

[0186] Optionally, the parameter usage module 62 is further configured to: use the AI ​​model parameters corresponding to the first condition according to the first configuration information and the protocol agreement; wherein, the protocol agreement stipulates that the terminal uses at least one of the following when the condition is met: the default AI model parameters, the initially activated AI model parameters, and the preferred AI model parameters.

[0187] Optionally, any one of the default AI model parameters, the initially activated AI model parameters, and the preferred AI model parameters includes at least one of the following:

[0188] Identify the smallest AI model parameters;

[0189] The largest AI model parameter is identified;

[0190] The AI ​​model parameters with the largest amount of data;

[0191] AI model parameters with minimal data volume;

[0192] The parameters of the AI ​​model with the most complex model structure;

[0193] The parameters of the simplest AI model structure;

[0194] The parameters of the AI ​​model with the most model layers;

[0195] AI model parameters with the fewest model layers;

[0196] The highest level of quantization for AI model parameters;

[0197] The parameters of the AI ​​model with the lowest quantization level;

[0198] AI model parameters for a fully connected neural network architecture;

[0199] AI model parameters of convolutional neural network structure.

[0200] Optionally, the parameter usage module 62 is further used to: use the AI ​​model parameters corresponding to the first condition according to the first preset rule;

[0201] The first preset rule includes at least one of the following:

[0202] Under various conditions, the terminal's own AI model parameters will be used by default, during initial activation, or preferentially.

[0203] The terminal can use arbitrary AI model parameters;

[0204] Under each condition, the default, initial activation, or priority use of general AI model parameters will be implemented.

[0205] Optionally, the parameter usage module 62 is further configured to: not use the AI ​​model parameters corresponding to the first condition according to a second preset rule; wherein the second preset rule includes: using non-AI model parameters by default, activating them initially, or prioritizing their use under each condition.

[0206] Optionally, the first receiving module is configured to receive the first configuration information from the network-side device via at least one of the following: RRC signaling, MAC CE, and DCI.

[0207] Optionally, the parameter selection device 60 further includes:

[0208] The second receiving module is used to receive second configuration information from the network-side device; wherein the second configuration information includes updated AI model parameters.

[0209] Optionally, the first condition includes at least one of the following:

[0210] Initial access;

[0211] Multiple residential communities;

[0212] Cell handover;

[0213] Based on the conditions determined by the community identifier;

[0214] Conditions determined based on the location region;

[0215] Based on at least one of the following conditions: signal-to-noise ratio (SNR), reference signal received power (RSRP), signal-to-interference plus noise ratio (SINR), reference signal received quality (RSRQ), layer 1 SNR, layer 1 RSRP, layer 1 SINR, and layer 1 RSRQ.

[0216] Based on the conditions determined by the bandwidth portion of BWP;

[0217] Conditions determined based on the Tracking Area (TA) and / or the Radio Access Network Notification Area (RNA);

[0218] Based on the condition of a determined operating frequency;

[0219] Conditions determined based on the Public Land Mobile Network (PLMN);

[0220] Conditions determined based on the terminal state;

[0221] Conditions determined based on Quality of Service (QoS) Flow;

[0222] Conditions determined based on the Radio Link Failure (RLF) event;

[0223] Conditions determined based on Radio Resource Management (RRM) events;

[0224] The conditions determined based on beam failure (BF) events and / or beam failure recovery (BFR) events;

[0225] Conditions determined based on timing and / or timing advance measurement results;

[0226] Conditions determined based on round-trip time (RTT) measurement results;

[0227] The conditions were determined based on the observed time difference of arrival (OTDOA) measurement results.

[0228] Optionally, the AI ​​model parameters include at least one of the following:

[0229] Structural information of the AI ​​model;

[0230] The parameters of each neuron in an AI model.

[0231] Optionally, the AI ​​model corresponding to the AI ​​model parameters is used for at least one of the following:

[0232] Signal processing;

[0233] Signal transmission;

[0234] Signal demodulation;

[0235] Channel State Information Acquisition

[0236] Beam management;

[0237] Channel prediction;

[0238] Interference suppression;

[0239] position;

[0240] Forecasting of high-level business and parameters;

[0241] Management of high-level business operations and parameters;

[0242] Parsing control signaling.

[0243] The parameter selection device in this application embodiment can be a device, a device with an operating system, or an electronic device, or it can be a component, integrated circuit, or chip in a terminal. The device or electronic device can be a mobile terminal or a non-mobile terminal. For example, a mobile terminal can include, but is not limited to, the types of terminals 11 listed above, while a non-mobile terminal can be a personal computer (PC), a television set (TV), an ATM, or a self-service machine, etc. This application embodiment does not impose specific limitations.

[0244] The parameter selection device provided in this application embodiment can achieve... Figure 4 The various processes implemented in the method embodiments achieve the same technical effect, and will not be described again here to avoid repetition.

[0245] It should be noted that the parameter configuration method provided in this application can be executed by a parameter configuration device, or by a control module within that parameter configuration device for executing the parameter configuration method. This application uses the execution of the parameter configuration method by a parameter configuration device as an example to illustrate the parameter configuration device provided in this application.

[0246] Please see Figure 7 , Figure 7 This is a schematic diagram of a parameter configuration device provided in an embodiment of this application. This device is applied to network-side equipment, such as... Figure 7 As shown, the parameter configuration device 70 includes:

[0247] The first sending module 71 is used to send the first configuration information to the terminal;

[0248] The first configuration information is used to configure AI model parameters for the terminal under different conditions.

[0249] Optionally, depending on the configuration method, the first configuration information is used to indicate, configure or activate the AI ​​model parameters corresponding to each condition, or the first configuration information is used to indicate, configure or activate the set of AI model parameters corresponding to each condition, so that the terminal can determine and use the AI ​​model parameters corresponding to the first condition according to the first configuration information.

[0250] Optionally, the first sending module 71 is used to send first configuration information to the terminal via at least one of the following: RRC signaling, MAC CE, and DCI.

[0251] Optionally, when the first configuration information indicates, configures, or activates the AI ​​model parameter set corresponding to each condition, the first sending module 71 is further configured to: send first indication information to the terminal. The first indication information is used to indicate the AI ​​model parameters in the AI ​​model parameter set corresponding to the terminal's current condition, so that the terminal determines and uses the AI ​​model parameters corresponding to the first condition from the AI ​​model parameter set. Alternatively, the first indication information is used to instruct the terminal to use at least one of the following when the condition is met: a default AI model parameter, an initially activated AI model parameter, or a preferred AI model parameter, so that after determining that it meets the first condition, the terminal uses the default / initial activated / preferred AI model parameters in the AI ​​model parameter set as the AI ​​model parameters corresponding to the first condition.

[0252] Optionally, the parameter configuration device 70 also includes:

[0253] The second sending module is used to send second configuration information to the terminal, which includes updated AI model parameters so that the terminal can use the updated AI model parameters.

[0254] In some embodiments, when the terminal performs cell access cell handover or other events / conditions that require RRC reconfiguration, the network-side device sends second configuration information to the terminal, including updated AI model parameters, so that the terminal can use the updated AI model parameters.

[0255] The parameter configuration device provided in this application embodiment can achieve... Figure 5 The various processes implemented in the method embodiments achieve the same technical effect, and will not be described again here to avoid repetition.

[0256] Optional, such as Figure 8As shown, this application embodiment also provides a communication device 80, including a processor 81, a memory 82, and a program or instructions stored in the memory 82 and executable on the processor 81. For example, when the communication device 80 is a terminal, the program or instructions executed by the processor 81 implement the various processes of the above-described parameter selection method embodiment and achieve the same technical effect. When the communication device 80 is a network-side device, the program or instructions executed by the processor 81 implement the various processes of the above-described parameter configuration method embodiment and achieve the same technical effect. To avoid repetition, further details are omitted here.

[0257] This application also provides a terminal, including a processor and a communication interface. The processor is used to determine a first condition satisfied by the terminal and to use AI model parameters corresponding to the first condition. This terminal embodiment corresponds to the terminal-side method embodiment described above. All implementation processes and methods of the above method embodiments can be applied to this terminal embodiment and achieve the same technical effects.

[0258] Specifically, Figure 9 A schematic diagram of the hardware structure of a terminal to implement an embodiment of this application.

[0259] The terminal 900 includes, but is not limited to, at least some of the following components: radio frequency unit 901, network module 902, audio output unit 903, input unit 904, sensor 905, display unit 906, user input unit 907, interface unit 908, memory 909, and processor 910.

[0260] Those skilled in the art will understand that the terminal 900 may also include a power supply (such as a battery) for supplying power to various components. The power supply may be logically connected to the processor 910 through a power management system, thereby enabling functions such as managing charging, discharging, and power consumption through the power management system. Figure 9 The terminal structure shown does not constitute a limitation on the terminal. The terminal may include more or fewer components than shown, or combine certain components, or have different component arrangements, which will not be elaborated here.

[0261] It should be understood that, in this embodiment, the input unit 904 may include a graphics processing unit (GPU) 9041 and a microphone 9042. The GPU 9041 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 906 may include a display panel 9061, which may be configured in the form of a liquid crystal display, an organic light-emitting diode, or the like. The user input unit 907 includes a touch panel 9071 and other input devices 9072. The touch panel 9071 is also called a touch screen. The touch panel 9071 may include a touch detection device and a touch controller. Other input devices 9072 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.

[0262] In this embodiment, the radio frequency unit 901 receives downlink data from the network-side device and processes it for the processor 910; additionally, it sends uplink data to the network-side device. Typically, the radio frequency unit 901 includes, but is not limited to, an antenna, at least one amplifier, a transceiver, a coupler, a low-noise amplifier, a duplexer, etc.

[0263] The memory 909 can be used to store software programs or instructions and various data. The memory 909 may primarily include a program or instruction storage area and a data storage area. The program or instruction 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 909 may include high-speed random access memory and non-volatile memory, which 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. For example, at least one disk storage device, flash memory device, or other non-volatile solid-state storage device.

[0264] Processor 910 may include one or more processing units; optionally, processor 910 may integrate an application processor and a modem processor, wherein the application processor mainly handles the operating system, user interface, and applications or instructions, and the modem processor mainly handles wireless communication, such as a baseband processor. It is understood that the aforementioned modem processor may also not be integrated into processor 910.

[0265] The processor 910 is used to fulfill the first condition of the terminal 900 and utilizes the AI ​​model parameters corresponding to the first condition. This effectively enhances the flexibility of the terminal in using AI model parameters and improves system performance.

[0266] Optionally, the processor 910 is used to determine a first condition satisfied by the terminal 900 and to use the AI ​​model parameters corresponding to the first condition.

[0267] Optionally, the radio frequency unit 901 is used to receive first configuration information from the network-side device, the first configuration information being used to configure AI model parameters for the terminal under different conditions;

[0268] The processor 910 is also configured to use the AI ​​model parameters corresponding to the first condition based on the first configuration information.

[0269] Optionally, the first configuration information is used to indicate, configure, or activate the AI ​​model parameters corresponding to each condition.

[0270] Optionally, the first configuration information is used to indicate, configure, or activate the set of AI model parameters corresponding to each condition.

[0271] Optionally, the radio frequency unit 901 is further configured to receive first indication information from the network-side device; the first indication information is used to indicate the AI ​​model parameter in the AI ​​model parameter set corresponding to the first condition; or, the first indication information is used to instruct the terminal 900 to use at least one of the following when the condition is met: the default AI model parameter, the initially activated AI model parameter, or the preferred AI model parameter.

[0272] The processor 910 is also configured to use the AI ​​model parameters corresponding to the first condition based on the first configuration information and the first indication information.

[0273] Optionally, the processor 910 is further configured to use the AI ​​model parameters corresponding to the first condition according to the first configuration information and the protocol agreement; the protocol agreement stipulates that the terminal uses at least one of the following when the condition is met: the default AI model parameters, the initially activated AI model parameters, and the preferred AI model parameters.

[0274] Optionally, the processor 910 is also used to use the AI ​​model parameters corresponding to the first condition according to the first preset rule;

[0275] The first preset rule includes at least one of the following:

[0276] Under various conditions, the terminal's own AI model parameters will be used by default, during initial activation, or preferentially.

[0277] The terminal can use arbitrary AI model parameters;

[0278] Under each condition, the default, initial activation, or priority use of general AI model parameters will be implemented.

[0279] Optionally, the processor 910 is also configured to not use the AI ​​model parameters corresponding to the first condition according to a second preset rule; the second preset rule includes: using by default, initial activation, or preferential use of non-AI model parameters under each condition.

[0280] The terminal 900 provided in this embodiment can achieve... Figure 4 The various processes implemented in the method embodiments achieve the same technical effect, and will not be described again here to avoid repetition.

[0281] This application also provides a network-side device, including a processor and a communication interface. The communication interface is used to send first configuration information to a terminal, which is used to configure AI model parameters for the terminal under different conditions. This network-side device embodiment corresponds to the above-described network-side device method embodiment. All implementation processes and methods of the above method embodiments can be applied to this network-side device embodiment and achieve the same technical effects.

[0282] Specifically, embodiments of this application also provide a network-side device. For example... Figure 10 As shown, the network-side device 100 includes an antenna 101, a radio frequency (RF) device 102, and a baseband device 103. The antenna 101 is connected to the RF device 102. In the uplink direction, the RF device 102 receives information through the antenna 101 and transmits the received information to the baseband device 103 for processing. In the downlink direction, the baseband device 103 processes the information to be transmitted and sends it to the RF device 102. The RF device 102 processes the received information and transmits it through the antenna 101.

[0283] The aforementioned frequency band processing device can be located in the baseband device 103. The method executed by the network-side device in the above embodiments can be implemented in the baseband device 103, which includes a processor 104 and a memory 105.

[0284] The baseband device 103 may include, for example, at least one baseband board on which multiple chips are disposed, such as... Figure 10 As shown, one of the chips, for example, is a processor 104, which is connected to a memory 105 to call the program in the memory 105 and execute the network-side device operations shown in the above method embodiment.

[0285] The baseband device 103 may also include a network interface 106 for exchanging information with the radio frequency device 102, such as a common public radio interface (CPRI).

[0286] Specifically, the network-side device in this application embodiment further includes: instructions or programs stored in memory 105 and executable on processor 104, wherein processor 104 calls the instructions or programs in memory 105 to execute. Figure 7 The methods executed by each module shown herein achieve the same technical effect, and to avoid repetition, they will not be described in detail here.

[0287] 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 parameter selection method embodiment or the various processes of the above-described parameter configuration method embodiment, and can achieve the same technical effect. To avoid repetition, they will not be described again here.

[0288] The processor mentioned above is the processor in the terminal described in the above embodiments. The readable storage medium includes computer-readable storage media, such as computer read-only memory (ROM), random access memory (RAM), magnetic disk, or optical disk.

[0289] 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 parameter selection method embodiment or the various processes of the above parameter configuration method embodiment, and can achieve the same technical effect. To avoid repetition, it will not be described again here.

[0290] 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.

[0291] 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.

[0292] Through 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 software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a computer software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal (which may be a mobile phone, computer, server, air conditioner, or network-side device, etc.) to execute the methods described in the various embodiments of this application.

[0293] 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 forms under the guidance of this application without departing from the spirit and scope of the claims, and all of these forms are within the protection scope of this application.

Claims

1. A parameter selection method, characterized in that, include: The terminal determines the first condition it meets; The terminal uses the artificial intelligence (AI) model parameters corresponding to the first condition; The AI ​​model parameters include at least one of the following: Structural information of the AI ​​model; The parameters of each neuron in an AI model; The method further includes: The terminal receives first configuration information from the network-side device. The first configuration information is used to indicate, configure or activate the set of AI model parameters corresponding to each condition. The use of the AI ​​model parameters corresponding to the first condition includes: The terminal receives first indication information from the network-side device, and uses the AI ​​model parameters corresponding to the first condition according to the first configuration information and the first indication information. Wherein, the first indication information is used to indicate the AI ​​model parameter in the AI ​​model parameter set corresponding to the first condition; or, the first indication information is used to indicate that the terminal uses at least one of the following when the condition is met: the default AI model parameter, the initially activated AI model parameter, or the preferred AI model parameter.

2. The method according to claim 1, characterized in that, The first configuration information is also used to indicate, configure or activate the AI ​​model parameters corresponding to each condition.

3. The method according to claim 1, characterized in that, The first configuration information includes at least one of the following: The correspondence between AI model parameters and conditions; The correspondence between AI model parameters and events; The correspondence between AI model parameters and cell locations.

4. The method according to claim 1, characterized in that, The use of the AI ​​model parameters corresponding to the first condition also includes: The terminal uses the AI ​​model parameters corresponding to the first condition according to the first configuration information and the protocol agreement. The protocol stipulates that the terminal shall use at least one of the following when the conditions are met: the default AI model parameters, the initially activated AI model parameters, and the preferred AI model parameters.

5. The method according to claim 1 or 4, characterized in that, The default AI model parameters, the initially activated AI model parameters, and the preferred AI model parameters include at least one of the following: Identify the smallest AI model parameters; The largest AI model parameter is identified; The AI ​​model parameters with the largest amount of data; AI model parameters with minimal data volume; The parameters of the AI ​​model with the most complex model structure; The parameters of the simplest AI model structure; The parameters of the AI ​​model with the most model layers; AI model parameters with the fewest model layers; The highest level of quantization for AI model parameters; The parameters of the AI ​​model with the lowest quantization level; AI model parameters for a fully connected neural network architecture; AI model parameters of convolutional neural network structure.

6. The method according to claim 1, characterized in that, The use of the AI ​​model parameters corresponding to the first condition also includes: The terminal uses the AI ​​model parameters corresponding to the first condition according to the first preset rule; The first preset rule includes at least one of the following: Under various conditions, the terminal's own AI model parameters will be used by default, during initial activation, or preferentially. The terminal can use arbitrary AI model parameters; Under each condition, the default, initial activation, or priority use of general AI model parameters will be implemented.

7. The method according to claim 1, characterized in that, The method further includes: According to the second preset rule, the terminal does not use the AI ​​model parameters corresponding to the first condition; The second preset rule includes: using non-AI model parameters by default, initial activation, or priority use under various conditions.

8. The method according to claim 1, characterized in that, Receiving the first configuration information from the network-side device includes: The terminal receives the first configuration information from the network-side device through at least one of the following: Radio Resource Control (RRC) signaling, Media Access Control Unit (MAC CE), and Downlink Control Information (DCI).

9. The method according to claim 1, characterized in that, The method further includes: The terminal receives second configuration information from the network-side device; The second configuration information includes the updated AI model parameters.

10. The method according to claim 1, characterized in that, The first condition includes at least one of the following: Initial access; Multiple residential communities; Cell handover; Based on the conditions determined by the community identifier; Conditions determined based on the location region; Based on at least one of the following conditions: signal-to-noise ratio (SNR), reference signal received power (RSRP), signal-to-interference plus noise ratio (SINR), reference signal received quality (RSRQ), layer 1 SNR, layer 1 RSRP, layer 1 SINR, and layer 1 RSRQ; Based on the conditions determined by the bandwidth portion of BWP; Conditions determined based on the Tracking Area (TA) and / or the Radio Access Network Notification Area (RNA); Based on the condition of a determined operating frequency; Conditions determined based on the Public Land Mobile Network (PLMN); Conditions determined based on the terminal state; Conditions determined based on Quality of Service (QoS) Flow; Conditions determined based on the Radio Link Failure (RLF) event; Conditions determined based on Radio Resource Management (RRM) events; The conditions determined based on beam failure (BF) events and / or beam failure recovery (BFR) events; Conditions determined based on timing and / or timing advance measurement results; Conditions determined based on round-trip time (RTT) measurement results; The conditions were determined based on the observed time difference of arrival (OTDOA) measurement results.

11. The method according to claim 1, characterized in that, The AI ​​model corresponding to the AI ​​model parameters is used for at least one of the following: Signal processing; Signal transmission; Signal demodulation; Channel State Information Acquisition Beam management; Channel prediction; Interference suppression; position; Forecasting of high-level business and parameters; Management of high-level business operations and parameters; Parsing control signaling.

12. A parameter configuration method, characterized in that, include: The network-side device sends the first configuration information to the terminal; The first configuration information is used to indicate, configure or activate the set of AI model parameters corresponding to each condition; The AI ​​model parameters include at least one of the following: Structural information of the AI ​​model; The parameters of each neuron in an AI model; The method further includes: The network-side device sends a first instruction message to the terminal; Wherein, the first indication information is used to indicate the AI ​​model parameters in the AI ​​model parameter set that correspond to the current conditions of the terminal; or, the first indication information is used to indicate that the terminal uses at least one of the following when the conditions are met: the default AI model parameters, the initially activated AI model parameters, and the preferred AI model parameters.

13. The method according to claim 12, characterized in that, The first configuration information is also used to indicate, configure or activate the AI ​​model parameters corresponding to each condition.

14. The method according to claim 12, characterized in that, Sending the first configuration information to the terminal includes: The network-side device sends the first configuration information to the terminal through at least one of the following: RRC signaling, MAC CE, DCI.

15. The method according to claim 12, characterized in that, The method further includes: The network-side device sends second configuration information to the terminal; The second configuration information includes the updated AI model parameters.

16. A parameter selection device, characterized in that, include: The determination module is used to determine the first condition that the terminal meets. The parameter usage module is used to use the AI ​​model parameters corresponding to the first condition. The AI ​​model parameters include at least one of the following: Structural information of the AI ​​model; The parameters of each neuron in an AI model; The device further includes: A first receiving module is configured to receive first configuration information from a network-side device and first indication information from the network-side device; wherein, the first configuration information is configured to indicate, configure, or activate the AI ​​model parameter set corresponding to each condition; the first indication information is configured to indicate the AI ​​model parameter in the AI ​​model parameter set corresponding to the first condition; or, the first indication information is configured to instruct the terminal to use at least one of the following when the condition is met: the default AI model parameter, the initially activated AI model parameter, or the preferred AI model parameter; The parameter usage module is further configured to: use the AI ​​model parameters corresponding to the first condition based on the first configuration information and the first indication information.

17. The apparatus according to claim 16, characterized in that, The first configuration information is also used to indicate, configure or activate the AI ​​model parameters corresponding to each condition.

18. The apparatus according to claim 16, characterized in that, The parameter usage module is also used to: use the AI ​​model parameters corresponding to the first condition according to the first configuration information and the protocol agreement; The protocol stipulates that the terminal shall use at least one of the following when the conditions are met: the default AI model parameters, the initially activated AI model parameters, and the preferred AI model parameters.

19. The apparatus according to claim 16, characterized in that, The parameter usage module is also used to: use the AI ​​model parameters corresponding to the first condition according to the first preset rule; The first preset rule includes at least one of the following: Under various conditions, the terminal's own AI model parameters will be used by default, during initial activation, or preferentially. The terminal can use arbitrary AI model parameters; Under each condition, the default, initial activation, or priority use of general AI model parameters will be implemented.

20. A parameter configuration device, characterized in that, include: The first sending module is used to send the first configuration information to the terminal; The first configuration information is used to indicate, configure or activate the set of AI model parameters corresponding to each condition; The AI ​​model parameters include at least one of the following: Structural information of the AI ​​model; The parameters of each neuron in an AI model; The first sending module is further configured to: send first indication information to the terminal; the first indication information is used to indicate the AI ​​model parameters in the AI ​​model parameter set that correspond to the current conditions of the terminal; or, the first indication information is used to instruct the terminal to use at least one of the following when the conditions are met: the default AI model parameters, the initially activated AI model parameters, and the preferred AI model parameters.

21. The apparatus according to claim 20, characterized in that, The first configuration information is used to indicate, configure, or activate the AI ​​model parameters corresponding to each condition.

22. A terminal, characterized in that, It includes a processor, a memory, and a program or instructions stored in the memory and executable on the processor, wherein the program or instructions, when executed by the processor, implement the steps of the parameter selection method as described in any one of claims 1 to 11.

23. A network-side device, characterized in that, It includes a processor, a memory, and a program or instructions stored in the memory and executable on the processor, wherein the program or instructions, when executed by the processor, implement the steps of the parameter configuration method as described in any one of claims 12 to 15.

24. A readable storage medium, characterized in that, The readable storage medium stores a program or instructions that, when executed by a processor, implement the steps of the parameter selection method as described in any one of claims 1 to 11, or the steps of the parameter configuration method as described in any one of claims 12 to 15.

Images