Information processing method and device, user equipment and network side equipment

Abstract

Disclosed are an information processing method, device, user equipment and network side device, which belong to the field of communications, the information processing method comprising: a user equipment receiving first information, the first information comprising at least one of the following: a reason for failure of a target unit, the target unit being a unit for processing channel state CSI information; the indication information of the target unit is deactivated; switching the indication information of the target unit; updating information related to the target unit; information related to the new target unit; the first indication information is used for indicating to update or optimize the target unit, and the second indication information is used for indicating the quantization level or optimization level of the target unit.

Description

Technical Field

[0001] This application belongs to the field of communication technology, and specifically relates to an information processing method, apparatus, user equipment, and network-side equipment. Background Technology

[0002] In related technologies, CSI information can be processed using artificial intelligence (AI) methods or non-AI methods. When using AI methods to process CSI information, the user equipment (UE) uses an AI model to process the target CSI information and sends the obtained CSI feedback information to the network-side equipment (e.g., the serving base station). The network-side equipment then uses the AI ​​model to further process the CSI feedback information.

[0003] However, AI models on the UE side and network device side may fail, and the relevant technologies do not provide a solution for CSI information processing in the event of model failure. Summary of the Invention

[0004] This application provides an information processing method, apparatus, user equipment, and network-side equipment. The user equipment can determine whether a target unit (AI model) has failed based on first information, and can determine the cause of the target unit failure if the target unit fails. Furthermore, it can determine the subsequent actions performed by the UE and the network-side equipment after the target unit fails, thereby realizing CSI information processing in the case of target unit failure.

[0005] Firstly, an information processing method is provided, executed by a user device, the method comprising:

[0006] User equipment (UE) receives first information, the first information including at least one of the following:

[0007] The reason for the failure of the target unit is that the target unit is a unit used to process channel state (CSI) information;

[0008] Deactivate the target unit;

[0009] Switch the indication information of the target unit;

[0010] Information related to the update of the target unit;

[0011] Information related to the new target unit;

[0012] The first instruction information is used to instruct the target unit to be updated or optimized:

[0013] The second indication information is used to indicate the quantization level or optimization level of the target unit.

[0014] Secondly, an information processing method is provided, executed by a network-side device, the method comprising:

[0015] The network-side equipment receives auxiliary information reported by the user equipment (UE);

[0016] The network-side device determines the reason for whether the target unit is valid or invalid based on the auxiliary information, wherein the target unit is a unit used to process CSI information;

[0017] The auxiliary information includes at least one of the following:

[0018] Target CSI information;

[0019] The monitoring information of the target unit estimated by the terminal;

[0020] The quantized value of the target CSI information;

[0021] The second CSI feedback information obtained by the UE based on the quantized value of the target CSI information;

[0022] The UE uses the third CSI feedback information obtained from the reference model.

[0023] Thirdly, an information processing apparatus is provided, the apparatus comprising:

[0024] A first receiving module is configured to receive first information, the first information including at least one of the following:

[0025] The reason for the failure of the target unit, which is a unit used to process CSI information;

[0026] Deactivate the target unit;

[0027] Switch the indication information of the target unit;

[0028] Information related to the update of the target unit;

[0029] Information related to the new target unit;

[0030] The first instruction information is used to instruct the target unit to be updated or optimized:

[0031] The second indication information is used to indicate the quantization level or optimization level of the target unit.

[0032] Fourthly, an information processing apparatus is provided, the apparatus comprising:

[0033] The second receiving module is used to receive auxiliary information reported by the user equipment (UE).

[0034] The first determining module is used to determine, based on the auxiliary information, the reason for or first information of whether the target unit is effective or ineffective, wherein the target unit is a unit used to process CSI information;

[0035] The auxiliary information includes at least one of the following:

[0036] Target CSI information;

[0037] The monitoring information of the target unit estimated by the terminal;

[0038] The quantized value of the target CSI information;

[0039] The second CSI feedback information obtained by the UE based on the quantized value of the target CSI information;

[0040] The UE uses the third CSI feedback information obtained from the reference model.

[0041] Fifthly, a user equipment is provided, the user equipment 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 information processing method as described in the first aspect.

[0042] In a sixth aspect, 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 information processing method as described in the second aspect.

[0043] In a seventh 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 information processing method as described in the first aspect, or implement the steps of the information processing method as described in the second aspect.

[0044] Eighthly, a wireless communication system is provided, comprising: a user equipment and a network-side device, wherein the user equipment is configured to perform the steps of the information processing method as described in the first aspect, and the network-side device is configured to perform the steps of the information processing method as described in the second aspect.

[0045] In a ninth aspect, a chip is provided, the chip including a processor and a communication interface coupled to the processor, the processor being configured to run programs or instructions to implement the information processing method as described in the first aspect, or to implement the information processing method as described in the second aspect.

[0046] In a tenth 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 information processing method as described in the first aspect, or to implement the steps of the information processing method as described in the second aspect.

[0047] In this embodiment, the user equipment receives first information, which includes at least one of the following: the reason for the failure of the target unit, wherein the target unit is a unit used for processing CSI information; indication information for deactivating the target unit; indication information for switching the target unit; information related to target unit updates; information related to a new target unit; first indication information for instructing the target unit to be updated or optimized; and second indication information for instructing the quantization level or optimization level of the target unit. Thus, the user equipment can determine whether the target unit (AI model) has failed based on the first information, and if the target unit fails, determine the reason for the failure, and determine the subsequent actions to be performed by the UE and network-side equipment after the target unit fails, thereby realizing CSI information processing in the case of target unit failure. Attached Figure Description

[0048] Figure 1 This is a block diagram of a wireless communication system applicable to embodiments of this application;

[0049] Figure 2 This is a schematic diagram of the neural network in an embodiment of this application;

[0050] Figure 3 This is a schematic diagram of a neuron in a neural network according to an embodiment of this application;

[0051] Figure 4 This is a schematic diagram of CSI information processing by a user equipment and a network-side device in an embodiment of this application;

[0052] Figure 5 This is a flowchart of an information processing method according to an embodiment of this application;

[0053] Figure 6 This is a flowchart illustrating an implementation of an information processing method in this application.

[0054] Figure 7 This is a flowchart illustrating another information processing method in the embodiments of this application;

[0055] Figure 8 This is a flowchart illustrating another information processing method in the embodiments of this application;

[0056] Figure 9 This is a flowchart of another information processing method in the embodiments of this application;

[0057] Figure 10 This is a schematic diagram of an information processing device according to an embodiment of this application;

[0058] Figure 11 This is a schematic diagram of another information processing device in an embodiment of this application;

[0059] Figure 12 This is a schematic diagram of the structure of a communication device according to an embodiment of this application;

[0060] Figure 13 This is a schematic diagram of the structure of a user equipment according to an embodiment of this application;

[0061] Figure 14 This is a schematic diagram of the structure of a network-side device in an embodiment of this application. Detailed Implementation

[0062] 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.

[0063] 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.

[0064] The term "instruction" in this application can be either a direct instruction (or explicit instruction) or an indirect instruction (or implicit instruction). A direct instruction can be understood as one in which the sender explicitly informs the receiver of specific information, the operation to be performed, or the requested result, etc., in the instruction sent. An indirect instruction can be understood as one in which the receiver determines the corresponding information based on the instruction sent by the sender, or makes a judgment and determines the operation to be performed or the requested result, etc., based on the judgment result.

[0065] It is worth noting that the technologies described in this application are not limited to Long Term Evolution (LTE) / LTE-Advanced (LTE-A) systems, but can also be used in other wireless communication systems, such as Code Division Multiple Access (CDMA), Time Division Multiple Access (TDMA), Frequency Division Multiple Access (FDMA), Orthogonal Frequency Division Multiple Access (OFDMA), Single-carrier Frequency-Division Multiple Access (SC-FDMA), or other systems. The terms "system" and "network" in this application are often used interchangeably, and the described technologies can be used with the systems and radio technologies mentioned above, as well as with other systems and radio technologies. The following description describes New Radio (NR) systems for illustrative purposes, and the term NR is used in most of the following description; however, these technologies can also be applied to systems other than NR systems, such as 6th generation (6G) radio systems. th Generation 6G communication system.

[0066] Figure 1This diagram illustrates a block diagram of a wireless communication system applicable to embodiments of this application. The wireless communication system includes a terminal 11 and a network-side device 12. The terminal 11 can be a mobile phone, tablet computer, laptop computer, notebook computer, personal digital assistant (PDA), handheld computer, netbook, ultra-mobile personal computer (UMPC), mobile internet device (MID), augmented reality (AR), virtual reality (VR) device, robot, wearable device, flight vehicle, vehicle user equipment (VUE), shipboard equipment, pedestrian user equipment (PUE), smart home devices (home appliances with wireless communication capabilities, such as refrigerators, televisions, washing machines, or furniture), game consoles, personal computers (PCs), ATMs, or self-service machines, etc. Wearable devices include: smartwatches, smart bracelets, smart headphones, smart glasses, smart jewelry (smart bracelets, smart chains, smart rings, smart necklaces, smart anklets, smart anklets, etc.), smart wristbands, smart clothing, etc. Among these, in-vehicle devices can also be referred to as in-vehicle terminals, in-vehicle controllers, in-vehicle modules, in-vehicle components, in-vehicle chips, or in-vehicle units, etc. It should be noted that the specific type of terminal 11 is not limited in this application embodiment. Network-side equipment 12 may include access network equipment or core network equipment, wherein access network equipment may also be referred to as Radio Access Network (RAN) equipment, radio access network function, or radio access network unit. Access network equipment may include base stations, Wireless Local Area Network (WLAN) access points (AS), or Wireless Fidelity (WiFi) nodes, etc.The term "base station" can be referred to as Node B (NB), Evolved Node B (eNB), Next Generation Node B (gNB), New Radio Node B (NR Node B), Access Point, Relay Base Station (RBS), Serving Base Station (SBS), Base Transceiver Station (BTS), Radio Base Station, Radio Transceiver, Basic Service Set (BSS), Extended Service Set (ESS), Home Node B (HNB), Home Evolved Node B, Transmit / Receive Point (TRP), or any other suitable term in the relevant field, as long as the same technical effect is achieved. The term "base station" is not limited to any specific technical terminology. It should be noted that this application embodiment only uses a base station in an NR system as an example for description and does not limit the specific type of base station.

[0067] Core network equipment, also known as core network nodes, core network functions, or core network elements, includes, but is not limited to, at least one of the following: Mobility Management Entity (MME), Access and Mobility Management Function (AMF), Session Management Function (SMF), User Plane Function (UPF), Policy Control Function (PCF), Policy and Charging Rules Function (PCRF), Edge Application Server Discovery Function (EASDF), Unified Data Management (UDM), Unified Data Repository (UDR), Home Subscriber Server (HSS), Centralized network configuration (CNC), Network Repository Function (NRF), Network Exposure Function (NEF), Local NEF (or L-NEF), and Binding Support Function. Support Functions (BSF), Application Functions (AF), Location Management Functions (LMF), Gateway Mobile Location Centres (GMLC), and Network Data Analytics Functions (NWDAF), etc. It should be noted that this application embodiment only uses core network equipment in the NR system as an example and does not limit the specific type of core network equipment. If the name of the core network equipment mentioned in this application embodiment changes in subsequent protocol versions (e.g., 6G), it will still be within the scope of protection of this application.

[0068] 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).

[0069] To facilitate understanding of the technical solutions provided in this application, the main technical concepts involved in the embodiments of this application are briefly described below.

[0070] AI:

[0071] Artificial intelligence has been widely applied in various fields, and AI models can be implemented in various ways, such as neural networks, decision trees, support vector machines, and Bayesian classifiers. This application uses neural networks as an example for illustration, but does not limit the specific type of AI model. Figure 2 This is a schematic diagram of a neural network, which consists of an input layer, hidden layers, and an output layer. The input layer directly receives the input data; the hidden layers are the most important part of the entire neural network, used to process the data; and the output layer outputs the values ​​processed by the network. Furthermore, a neural network is composed of neurons, as shown in the schematic diagram below. Figure 3 As shown. In Figure 3 In this diagram, a1, a2, ..., aK represent the inputs, w represents the weights (i.e., multiplicative coefficients), b represents the biases (i.e., additive coefficients), z represents the intermediate processing result, a represents the neuron's output, and σ(.) represents the activation function. Common activation functions include Sigmoid (maps variables to between 0 and 1), tanh (translation and contraction of Sigmoid), and Rectified Linear Unit (ReLU).

[0072] The parameters of a neural network are optimized using optimization algorithms. An optimization algorithm is a class of algorithms that minimizes or maximizes an objective function (sometimes called a loss function). The objective function is often a mathematical combination of model parameters and data. For example, given data X and its corresponding label Y, a neural network model f(.) can be constructed. After obtaining the model, the predicted output f(x) can be obtained based on the input x, and the difference between the predicted value and the true value (f(x) - Y) can be calculated; this is the loss function. The goal of optimization algorithms is to find suitable W and b that minimize the value of the aforementioned loss function. The smaller the loss value, the closer our model is to the reality.

[0073] Currently, most common optimization algorithms are based on the BP (error back propagation) algorithm. The basic idea of ​​the BP algorithm is that the learning process consists of two stages: forward propagation of the signal and backward propagation of the error. During forward propagation, the input sample is introduced from the input layer, processed layer by layer through each hidden layer, and then propagated to the output layer. If the actual output of the output layer does not match the expected output, the process transitions to the error back propagation stage. Error back propagation involves propagating the output error back to the input layer layer by layer through the hidden layers, distributing the error to all units in each layer, thereby obtaining the error signal of each unit. This error signal serves as the basis for adjusting the weights of each unit. This process of adjusting the weights of each layer through forward and backward propagation is repeated continuously. The continuous adjustment of the weights is the learning and training process of the network. This process continues until the error of the network output is reduced to an acceptable level, or until the predetermined number of learning iterations is reached.

[0074] In addition, optimization algorithms may include gradient descent, stochastic gradient descent (SGD), mini-batch gradient descent, momentum method, Nesterov (a type of stochastic gradient descent algorithm with momentum), adaptive gradient descent (Adagrad), Adadelta (an extension of Adagrad), root mean square prop (RMSprop), and adaptive momentum estimation (Adam).

[0075] During error backpropagation, these optimization algorithms calculate the gradient based on the error / loss obtained from the loss function with respect to the current neuron, add the learning rate, previous gradients / derivatives / partial derivatives, etc., and then pass the gradient to the previous layer.

[0076] Model lifecycle:

[0077] The lifecycle of a model (AI model / ML model) includes at least one or more of the following: model training, model deployment, model inference, model monitoring, and model updates. Related technologies utilize AI models to process CSI information. However, model failure can occur during the model's lifecycle. These technologies do not provide solutions for determining the causes of model failure or for how terminal and network devices should perform subsequent actions after model failure.

[0078] Therefore, embodiments of this application provide an information processing method, apparatus, user equipment, and network-side equipment. The information processing method includes: the user equipment receiving first information, the first information including at least one of the following: a reason for the failure of a target unit, the target unit being a unit used for processing CSI information; indication information for deactivating the target unit; indication information for switching the target unit; information related to target unit updates; information related to a new target unit; first indication information for indicating that the target unit should be updated or optimized; and second indication information for indicating the quantization level or optimization level of the target unit. Thus, the user equipment can determine whether the target unit (AI model) has failed based on the first information, and in the case of target unit failure, can determine the reason for the target unit failure, and after the target unit fails, can determine the subsequent actions to be performed by the UE and the network-side equipment, thereby realizing CSI information processing in the case of target unit failure.

[0079] The information processing method, apparatus, user equipment, and network-side equipment provided in this application will be described in detail below with reference to the accompanying drawings and through some embodiments and application scenarios.

[0080] To facilitate understanding of this application, the method for processing CSI information in the embodiments of this application will first be described. (Refer to...) Figure 4 As shown, Figure 4 This diagram illustrates the CSI information processing process between the user equipment (UE) and network-side equipment. Specifically, an encoder is deployed on the UE side, and at least a decoder is deployed on the network-side equipment. Optionally, the network-side equipment also has an encoder. Both the UE-side encoder and the network-side encoder and decoder are AI-based models. Optionally, the UE-side encoder can be obtained through the following methods: independently acquired by the UE, trained based on the network-side equipment's encoder, transmitted by the network-side equipment, or trained based on the network-side equipment's decoder.

[0081] The target CSI information can be obtained based on reference signal measurements. The target CSI information can be channel information, codebook information, precoded codebook information, or PMI information.

[0082] Specifically, the UE processes the target CSI information using an encoder to obtain first CSI feedback information, and the network-side device processes the first CSI feedback information using a decoder to obtain first reconstructed CSI information. The network-side device can also process the target CSI information using an encoder to obtain desired CSI feedback information, and then process the desired CSI feedback information using a decoder to obtain second reconstructed CSI information. Furthermore, the difference between the CSI information is measured based on the target CSI information and the first reconstructed CSI information, or based on the SGCS converted from the target CSI information and the second reconstructed CSI information.

[0083] If the target unit (e.g., the encoder on the UE side, and the (optional encoder and) decoder on the network side) is not faulty, the target CSI information is similar to the first reconstructed CSI information and the second reconstructed CSI information, and the first CSI feedback information is similar to the expected CSI feedback information. Therefore, the reason for whether the target unit is valid or faulty can be determined based on the similarity (error) between the two CSI information.

[0084] A first aspect of this application provides an information processing method applied to a user equipment, see [link to relevant documentation]. Figure 5 The diagram shown is a flowchart of an information processing method according to an embodiment of this application. The method may include the following steps:

[0085] Step S510: The user equipment (UE) receives first information, the first information including at least one of the following:

[0086] Item A-1: ​​Reasons for target unit failure, wherein the target unit is a unit used to process channel state CSI information;

[0087] Item A-2: Deactivate the instruction information of the target unit;

[0088] Item A-3: Instruction information for switching the target unit;

[0089] Item A-4: Information related to the update of the target unit;

[0090] Item A-5: Information related to the new target unit;

[0091] Item A-6: First indication information, used to indicate whether the target unit should be updated or optimized:

[0092] Item A-7: Second indication information, used to indicate the quantization level or optimization level of the target unit.

[0093] In this embodiment of the application, the user equipment may be Figure 1 For example of terminal 11, please refer to the previous text, and it will not be repeated here.

[0094] The first information may be sent by the network-side device. In some embodiments, when the target unit fails, the UE receives the first information sent by the network-side device. The first information includes at least one of items A-1 to A-7 above. Based on the contents included in the first information, the UE determines whether the target unit has failed, the cause of the target unit's failure, and / or can determine the subsequent actions to be performed by the UE and the network-side device after the target unit fails.

[0095] Regarding item A-1, the UE can determine the cause of the target unit failure; wherein the target unit includes at least one of the following: an AI unit used by the UE or network-side device to process CSI information, a reference AI unit of the AI ​​unit used by the UE or network-side device, an AI unit used by the UE, network-side device, or test device in testing, and a reference AI unit of the AI ​​unit used by the UE, network-side device, or test device in testing. In some embodiments, the target unit failure may be due to a malfunction of the target unit, improper optimization of the target unit, or data offset.

[0096] In an optional embodiment, the cause of target unit failure includes at least one of the following: target unit failure on the UE side, CSI feedback information error exceeding a second threshold, or data offset occurring.

[0097] Regarding item A-2, the target unit's state includes one or more of the following: it can be activated and used, it is in a pending activation state, it has been released, or it is in an unavailable state. The network-side device can send an indication to the UE to deactivate the target unit via a first message. The UE then activates the target unit based on this indication, allowing the UE to process CSI information subsequently based on the activated target unit. Alternatively, the target unit's state can include either an active or deactivated state, allowing it to be deactivated once the network-side device or terminal determines that the target unit is invalid.

[0098] In an optional embodiment, the indication information for deactivating the target unit is used to indicate the deactivation of the target unit. Optionally, 1 bit or X bits are used to indicate activation or deactivation of the target unit; optionally, the indication information for deactivating the target unit also includes the identification information of the target unit.

[0099] Regarding item A-3, the UE can switch the target unit; in some embodiments, when the target unit fails (e.g., the target unit and the data to be processed are incompatible), the network-side device can send the indication information for switching the target unit to the UE through the first information, and the UE switches the target unit according to the indication information for switching the target unit, so that the UE can subsequently process the CSI information based on the switched target unit.

[0100] In an optional embodiment, the indication information for switching the target unit is used to indicate the target unit to be switched. Optionally, the indication information for the target unit may also include identification information of the target unit.

[0101] Regarding item A-4, the UE can update the target unit based on information related to the target unit update to obtain the updated target unit. In some embodiments, the information related to the target unit update may be the model structure information or model parameter information of the target unit, or it may be a dataset. The dataset is used to obtain or update the target unit on the terminal side. Optionally, the dataset includes at least one or more expected CSI feedback information.

[0102] In one optional embodiment, the dataset includes at least one or more expected CSI feedback messages and target CSI information. If a target unit on the UE side fails due to a fault, the network-side device can send relevant information about the target unit, such as a dataset including expected CSI feedback messages, to the UE via first information. The UE then updates the failed target unit based on this dataset. In another optional embodiment, the dataset includes multiple data sets, and the dataset information includes: the number of data sets, the data format, and the expected CSI feedback messages and target CSI information corresponding to the number of data sets.

[0103] Regarding item A-5, the UE can update the target unit based on information related to the new target unit. In some embodiments, the information related to the new target unit may be a new dataset. When the target unit on the UE side fails due to data offset, the network-side device can send the new dataset to the UE through the first information, and the UE can train (i.e. update) the target unit based on the new data.

[0104] In an optional embodiment, the information related to the new target unit includes the target unit's identification information, model structure information or model parameter information, or it may be dataset information for obtaining the target unit, wherein the dataset includes multiple data, and the dataset information includes: the number of data, the format of the data, the expected CSI feedback information corresponding to the number of data, and the target CSI information.

[0105] For item A-6, the UE updates or optimizes the target unit according to the instructions of the first instruction information. For example, when the target unit on the UE side fails, the network side device can send the first instruction information to the UE through the first information. After receiving the first instruction information, the UE updates or optimizes the target unit.

[0106] For item A-7, the UE determines the quantization level or optimization level of the target unit based on the second indication information, and optimizes the corresponding AI unit according to the quantization level or optimization level of the target unit to obtain the optimized target unit. For example, the target unit is obtained by optimizing a reference model. Different optimization levels result in different models. Therefore, the UE optimizes the reference model according to the optimization level of the target unit indicated by the first indication information to obtain the optimized target unit. For example, CSI feedback information or target CSI information is quantized, or the target unit is obtained by quantization based on a reference model. However, excessive quantization may cause the target unit to fail. Therefore, the second indication information indicates the quantization level of the target unit.

[0107] Through the above implementation process, when using AI to process CSI information, the user equipment can determine whether the target unit (AI model) has failed based on the first information received, and in the case of target unit failure, it can determine the cause of target unit failure, and after target unit failure, it can determine the subsequent actions performed by the UE and network-side equipment, thus realizing CSI information processing in the case of target unit failure.

[0108] Through the above implementation process, when processing CSI information using AI, the user equipment can determine whether the target unit (AI model) has failed based on whether the target unit (AI model) has failed or the reason for the failure of the target unit (AI model) determined from both sides of the equipment.

[0109] Through the above implementation process, when processing CSI information using AI, the user equipment can determine the subsequent actions to be performed by the UE and the network-side equipment based on the indication information for deactivating the target unit, switching the indication information of the target unit, and updating information related to the target unit.

[0110] 1. The following explains the content included in the first piece of information in different scenarios:

[0111] In one specific implementation, the first information includes at least information related to the target unit update; the information related to the target unit update includes at least one of the following:

[0112] F-1 item: Third dataset, which includes expected CSI feedback information;

[0113] In one embodiment, the third dataset includes multiple datasets, and the dataset information includes the number of datasets, the format of the datasets, the expected CSI feedback information corresponding to the number of datasets, and the target CSI information.

[0114] In one embodiment, the third dataset includes multiple datasets, each including expected CSI feedback information. Optionally, the third dataset includes target CSI information corresponding to the expected CSI feedback information.

[0115] F-2: Second threshold, which is the upper limit of the error between the first CSI feedback information obtained by the UE using the updated first AI unit and the expected CSI feedback information;

[0116] In one embodiment, the information related to the target unit update includes the second threshold, which is an upper limit of the error between the first CSI feedback information obtained by the UE using the first AI unit and the expected CSI feedback information.

[0117] In one embodiment, the information related to the target unit update includes the second threshold, which is an error threshold between the first CSI feedback information obtained by the UE using the first AI unit and the expected CSI feedback information.

[0118] F-3: SGCS threshold, which is the lower limit of SGCS between the first CSI feedback information obtained by the UE using the updated first AI unit and the expected CSI feedback information.

[0119] In one embodiment, the information related to the target unit update includes an SGCS threshold, which is the lower limit of the SGCS between the first CSI feedback information obtained by the first AI unit used by the UE and the expected CSI feedback information.

[0120] In one embodiment, the information related to the target unit update includes an SGCS threshold, which is the threshold of the SGCS between the first CSI feedback information obtained by the first AI unit used by the UE and the expected CSI feedback information.

[0121] In this embodiment of the application, when the first AI unit on the UE side fails, the first information includes at least information related to the target unit update, and the information related to the target unit update includes at least one of items F-1 to F-3; thus, after receiving the first information, the UE updates the first AI unit using the information related to the target unit update in the first information, and determines that the updated first AI unit meets the following conditions, such as the error between the first CSI feedback information obtained by the UE using the updated first AI unit and the expected CSI feedback information is less than or equal to a second threshold, or the SGCS between the first CSI feedback information obtained by the UE using the updated first AI unit and the expected CSI feedback information is greater than or equal to the SGCS threshold.

[0122] For item F-1, the expected CSI feedback information in the third dataset is the expected CSI feedback information associated with the target CSI information. The UE uses the target CSI information and the expected CSI feedback information in the third dataset to update the first AI unit. For example, if the first AI unit fails, the UE outputs the target CSI information to the first AI unit and optimizes the first AI unit based on the error between the feedback information output by the first AI unit and the expected CSI feedback information.

[0123] For item F-2, the first AI unit is updated. The error between the first CSI feedback information output by the updated first AI unit and the expected CSI feedback information cannot be greater than the second threshold; otherwise, the updated first AI unit is still considered to be in a failed state.

[0124] For item F-3, the first AI unit is updated. The SGCS between the first CSI feedback information output by the updated first AI unit and the expected CSI feedback information cannot be less than the SGCS threshold; otherwise, the updated first AI unit is still considered to be in a failed state.

[0125] In one specific implementation, when the cause of the target unit failure is a failure of the target unit on the terminal side, the first information includes at least one of the following:

[0126] Item G-1: Instruction information for switching the target unit;

[0127] In an optional embodiment, the indication information for switching the target unit is used to indicate the target unit to be switched. Optionally, the indication information for the target unit may also include identification information of the target unit.

[0128] G-2: Information related to the new target unit;

[0129] Specifically, the information related to the new target unit includes: target unit identification information, target unit model structure information, model parameter information, and one or more of the dataset information used to obtain the target unit; wherein the dataset includes multiple data sets, and the dataset information includes: the number of data sets, the data format, the expected CSI feedback information corresponding to the number of data sets, and the target CSI information.

[0130] G-3: Used to obtain the second dataset of the target unit.

[0131] In one embodiment, the second dataset includes multiple datasets, and the dataset information includes the number of datasets, the format of the datasets, the expected CSI feedback information corresponding to the number of datasets, and the target CSI information.

[0132] In this embodiment of the application, when the cause of the target unit failure is a data offset, the network-side device can directly send the indication information for switching the target unit (i.e., item G-1) to the UE through the first information. The UE switches the target unit according to the indication information for switching the target unit (for example, switches to the target unit adapted to the dataset), so that the UE can process the CSI information based on the switched target unit.

[0133] The network-side device can also send information related to the new target unit (i.e., item G-2) to the UE via the first information. The new target unit refers to the target unit obtained by the network-side device based on the new dataset, and this new target unit is compatible with the data to be processed on the UE side. After the network-side device obtains the new target unit based on the new dataset, it sends the information related to the new target unit to the UE via the first information. The UE can then process the CSI information based on the new target unit.

[0134] The network-side device can also send a second dataset (i.e., G-3 item) to the UE through the first information to obtain the target unit. The second dataset is a dataset that is adapted to the data to be processed on the UE side. The UE can train the target unit based on the second dataset to obtain an effective target unit.

[0135] In this embodiment of the application, when the cause of the target unit failure is a data offset, the first information includes at least one of the above-mentioned G-1 to G-3 items. Thus, after receiving the first information, the UE can perform subsequent actions after the target unit failure according to at least one of the G-1 to G-3 items, so that CSI information can still be processed even when the target unit fails.

[0136] In one specific implementation, the first information further includes:

[0137] CSI reporting configuration information is used to instruct the UE to update the first AI unit on the UE side, or to instruct the UE to return to non-AI CSI reporting.

[0138] In this embodiment, the UE processes CSI information based on the first AI unit. When the first AI unit fails, the network-side device can instruct the UE to update the first AI unit through CSI reporting configuration information, so that the UE can subsequently process CSI information based on the updated first AI unit. Furthermore, when the first AI unit fails, the network-side device can also instruct the UE to revert to non-AI CSI reporting through CSI reporting configuration information, meaning the UE processes CSI information using a non-AI method.

[0139] In one optional embodiment, the CSI reporting configuration information includes indication information of the first AI unit to instruct the UE to update the first AI unit on the UE side, or to instruct the UE to return to non-AI CSI reporting; or, the CSI reporting configuration information includes whether the CSI reporting configuration is AI-based or non-AI-based.

[0140] In one specific implementation, the first information further includes:

[0141] R-1: Model recognition information;

[0142] R-2 term: Dataset identification information;

[0143] R-3: CSI reports identification information;

[0144] R-4: Monitoring and identification information.

[0145] In this embodiment of the application, model identification information is used to identify target units, dataset identification information is used to identify datasets, CSI reporting identification information is used to identify CSI reporting configurations, and monitoring identification information is used to identify monitoring reporting configurations.

[0146] 2. The following describes the execution process before the UE receives the first information:

[0147] In one specific implementation, the UE performs the following steps before receiving the first information:

[0148] The UE reports auxiliary information, which includes at least one of the following:

[0149] Item B-1: Target CSI Information;

[0150] Item B-2: Monitoring information of the target unit estimated by the terminal;

[0151] Item B-3: The quantified value of the target CSI information;

[0152] Item B-4: The second CSI feedback information obtained by the UE based on the quantized value of the target CSI information;

[0153] Item B-5: The UE uses the third CSI feedback information obtained from the reference model.

[0154] The auxiliary information is used by the network-side device to determine the cause of the target unit failure or the first information, or the auxiliary information is used to trigger the network-side device to send the first information to the UE.

[0155] In some embodiments, the auxiliary information is used by the network-side device to determine the subsequent behavior of the UE in the event of a target unit failure. For example, deactivating the target unit, updating the target unit, switching the target unit, or falling back to non-AI CSI reporting.

[0156] In this embodiment of the application, the target CSI information in item B-1 may be obtained by the UE through measurement reference signal, and / or the target CSI information may be the input of the first AI unit on the UE side. The UE may send the target CSI information to the network-side device through auxiliary information, so that the network-side device may determine the cause of the target unit failure or send the first information to the UE based on the target CSI information.

[0157] Regarding item B-2, the monitoring information of the target unit estimated by the terminal may include: the SGCS estimated by the terminal, and the effectiveness and degree of effectiveness of the target unit. In some embodiments, the UE itself has the ability to estimate monitoring information. When the target unit fails, the UE can estimate the monitoring information of the target unit based on its own monitoring information estimation ability, and obtain the terminal-estimated monitoring information of the target unit. Then, the UE sends the terminal-estimated monitoring information of the target unit to the network-side device through auxiliary information, so that the network-side device can determine the cause of the target unit failure or send first information to the UE based on the terminal-estimated monitoring information of the target unit.

[0158] Regarding item B-3, the quantized value of the target CSI information represents the quantized information of the target CSI information. In some embodiments, the data volume of the target CSI information is large. To facilitate reporting, the UE performs quantization processing on the target CSI information to reduce the data volume of the reported CSI information. Therefore, the UE also sends the quantized value of the target CSI information to the network-side device through auxiliary information. In some embodiments, the quantized value of the target CSI information is the target CSI information quantized according to type II or etype II.

[0159] Regarding item B-4, the second CSI feedback information is obtained by the UE compressing the quantized value of the target CSI information based on the target cell, according to the quantized value of the target CSI information. It can be understood that the second CSI feedback information is a smaller CSI information compared to the target CSI information.

[0160] For item B-5, the reference model can be a model used by the UE to obtain the AI ​​unit (for example, the AI ​​unit on the UE side is optimized based on the reference model). In order to determine whether the reference model is valid, the UE uses the reference model to obtain the third CSI feedback information and sends the third CSI feedback information to the network-side device by reporting auxiliary information, so that the network-side device can determine whether the reference model is valid based on the third CSI feedback information. If the reference model determined according to the third CSI feedback information is valid, the UE can be instructed to switch to the reference model.

[0161] In an optional embodiment, the UE uses the fifth model to obtain the fourth CSI feedback information and sends the fourth CSI feedback information to the network-side device by reporting auxiliary information, so that the network-side device can determine whether the reference model is valid based on the fourth CSI feedback information. If the fifth model determined based on the fourth CSI feedback information is valid, the UE can be instructed to switch to the fifth model.

[0162] Correspondingly, after the UE reports the assistance information, the network-side device performs the following steps:

[0163] Step C1: The network-side equipment receives auxiliary information reported by the user equipment (UE);

[0164] Step C2: The network-side device determines the reason or first information for whether the target unit is valid or invalid based on the auxiliary information, wherein the target unit is a unit used to process CSI information.

[0165] In this embodiment of the application, the UE reports auxiliary information to the network-side device. The auxiliary information includes at least one of items B-1 to B-5. After receiving the auxiliary information, the network-side device determines the cause of the target unit failure or sends first information to the UE based on the auxiliary information.

[0166] In one specific implementation, the network-side device determines the reason for whether the target unit is valid or invalid based on the auxiliary information, including:

[0167] If the error between the expected CSI feedback information and the first CSI feedback information obtained by the first AI unit on the UE side is greater than a first threshold, and the error between the first reconstructed CSI information obtained based on the first CSI feedback information and the target CSI information is less than a second threshold, the target unit is determined to be valid.

[0168] If the error between the expected CSI feedback information and the first CSI feedback information obtained by the first AI unit on the UE side is less than the first threshold, and the error between the first reconstructed CSI information obtained based on the first CSI feedback information and the target CSI information is greater than the second threshold, the cause of the target unit failure is determined to be: data offset occurs, wherein the data offset indicates that the first data or the first dataset obtained in time slot n is offset relative to the second dataset used to obtain the target unit;

[0169] If the error between the expected CSI feedback information and the first CSI feedback information obtained through the first AI unit on the UE side is greater than the first threshold, and the error between the first reconstructed CSI information obtained based on the first CSI feedback information and the target CSI information is greater than the second threshold, the cause of the target unit failure is determined to be: data offset or failure of the first AI unit on the UE side.

[0170] In this embodiment, the UE reports the target CSI information and the first CSI feedback information to the network-side device through auxiliary information. The network-side device reconstructs the target CSI information based on the first CSI feedback information to obtain the first reconstructed CSI information. Based on the target CSI, the first CSI feedback information and the first reconstructed CSI information, the UE determines whether the target unit is valid or invalid. The first CSI feedback information is obtained by the UE using the first AI unit on the UE side.

[0171] If the target unit is not faulty, the expected CSI feedback information and the first CSI feedback information are similar. The reason for whether the target unit is effective or faulty can be determined based on the similarity (or error) between the expected CSI feedback information and the first CSI feedback information. Similarly, if the target unit is not faulty, the first reconstructed CSI information and the target CSI information are also similar. The reason for whether the target unit is effective or faulty can be determined based on the similarity (or error) between the first reconstructed CSI information and the target CSI information.

[0172] Thus, the error between the expected CSI feedback information and the first CSI feedback is measured by a first threshold, and the error between the first reconstructed CSI information and the target CSI information is measured by a second threshold. Based on the relationship between the error between the expected CSI feedback information and the first CSI feedback and the first threshold, and based on the relationship between the error between the first reconstructed CSI information and the target CSI information and the second threshold, the reason for whether the target unit is effective or not can be determined.

[0173] In some embodiments, when the first AI unit on the UE side consists of multiple models (e.g., model 0, model 2, and model 3 are deployed on the UE side), the network-side device can determine whether the multiple models are valid or the reason for their failure.

[0174] In one specific implementation, the expected CSI feedback information is obtained by the network-side device based on the target CSI information or the quantized value of the target CSI information.

[0175] In this embodiment, the UE reports the target CSI information and the quantized value of the target CSI information as auxiliary information to the network-side device. After receiving the auxiliary information, the network-side device can obtain the expected CSI feedback information based on the target CSI information or the quantized value of the target CSI information.

[0176] In one specific implementation, the UE performs the following steps before receiving the first information:

[0177] Step N1: The UE sends a fourth indication information to the network-side device at a first moment. The fourth indication information is used to instruct the network-side device to send the first information. The first information includes at least information related to the target unit update.

[0178] In this embodiment, if the first AI unit on the UE side fails, the UE sends a fourth indication message to the network-side device at a first moment to instruct the network-side device to send information including at least information related to the target unit update; thus, upon receiving the first message, the UE can update the first AI unit based on the information related to the target unit update in the first message. The first moment refers to a time when both the UE and the network-side device are idle and communicable.

[0179] 3. The reasons for the target unit's failure are explained below:

[0180] In one specific implementation, the cause of target unit failure includes at least one of the following:

[0181] Item D-1: The first artificial intelligence (AI) unit on the UE side has failed;

[0182] Item D-2: The second AI unit on the network-side device side has failed;

[0183] D-3: Data offset occurs, which indicates that the first data or first dataset obtained in time slot n is offset relative to the second dataset used to obtain the target unit;

[0184] D-4: The error between the expected CSI feedback information and the first CSI feedback information obtained through the first AI unit on the UE side is greater than a first threshold;

[0185] Item D-5: The quantization level or optimization level of the target unit.

[0186] In this embodiment of the application, the reason for the target unit failure in the first information includes at least one of the above-mentioned items D-1 to D-5. The UE can know the reason for the target unit failure based on the received first information. The target unit includes a first AI unit on the UE side and a second AI unit on the network side device side. Therefore, the failure of the target unit can be a failure of the first AI unit on the UE side (i.e., item D-1) or a failure of the second AI unit on the network side device side (i.e., item D-2).

[0187] Regarding item D-3, target unit failure may also be caused by data offset. For example, the target unit may be obtained based on a second dataset (e.g., trained on a second dataset), where the data in the second dataset corresponds to scenario A, similar to the data in the training scenario. The first data or first dataset is the data used by the terminal in inference, such as the first data or first dataset obtained by the terminal at the current moment or several moments prior to the current moment. For instance, if the first data or first dataset obtained by the UE in time slot n corresponds to scenario B, then the first data or first dataset obtained in time slot n is offset relative to the second dataset, causing the target unit to fail. In other words, if there is a data offset between the data corresponding to the training scenario and the data used in inference, such as inconsistent data features or excessive deviation, the target model will fail.

[0188] Regarding item D-4, the expected CSI feedback information is obtained through the second AI unit on the network-side device side, while the first CSI feedback information is obtained through the first AI unit on the UE side. If the target unit (either the first or second AI unit) is not faulty, the expected CSI feedback information and the first CSI feedback information are similar. Therefore, when the error between the expected CSI feedback information and the first CSI feedback information exceeds a first threshold, the target unit is considered faulty. In this case, target unit failure refers to the failure of both the first and / or second AI units.

[0189] Regarding item D-5, target cell failure may be due to the quantization level or optimization level of the target cell. For example, if the target cell is optimized based on a reference model, failure may occur if the quantization level or optimization level of the target cell does not meet the requirements.

[0190] In one specific implementation, the first AI unit on the UE side is determined to be faulty if at least one of the following conditions is met:

[0191] E-1: The error between the first CSI feedback information and the expected CSI feedback information is greater than the second threshold in the first information;

[0192] E-2: The SGCS between the first CSI feedback information and the expected CSI feedback information is less than the first SGCS threshold in the first information;

[0193] E-3: The error between the first reconstructed CSI information obtained based on the first CSI feedback information and the target CSI information is greater than the third threshold;

[0194] E-4: The SGCS of the first reconstructed CSI information obtained based on the first CSI feedback information and the target CSI information is less than the second SGCS threshold;

[0195] Item E-5: The error between the first reconstructed CSI information obtained based on the first CSI feedback information and the target CSI information is greater than the fourth threshold, and the error between the second reconstructed CSI information obtained based on the expected CSI feedback information and the target CSI information is less than the fifth threshold;

[0196] Item E-6: The SGCS of the first reconstructed CSI information obtained based on the first CSI feedback information and the target CSI information is less than the third SGCS threshold, and the SGCS of the second reconstructed CSI information obtained based on the expected CSI feedback information and the target CSI information is greater than the fourth SGCS threshold;

[0197] E-7: The error between the first reconstructed CSI information obtained based on the first CSI feedback information and the second reconstructed CSI information obtained based on the expected CSI feedback information is greater than the sixth threshold;

[0198] Item E-8: The SGCS of the first reconstructed CSI information obtained based on the first CSI feedback information and the second reconstructed CSI information obtained based on the expected CSI feedback information is less than the fifth SGCS threshold.

[0199] In this embodiment, the first CSI feedback information is obtained using the first AI unit on the UE side based on the target CSI information; the expected CSI feedback information is obtained using the second AI unit on the network side based on the target CSI information; the first reconstructed CSI information is obtained using the second AI unit on the network side based on the first CSI feedback information; and the second reconstructed CSI information is obtained using the second AI unit on the network side based on the expected CSI feedback information.

[0200] If the target unit (i.e., the first AI unit or the second AI unit) is not faulty, the first CSI feedback information is similar to the expected CSI feedback information, the first reconstructed CSI information is similar to the target CSI information, and the second reconstructed CSI information is also similar to the target CSI information. Therefore, the error between the two CSI information is used to determine whether the first AI unit on the UE side is faulty.

[0201] For item E-1, when the error between the first CSI feedback information and the expected CSI feedback information is greater than the second threshold in the first information, it indicates that the difference between the first CSI feedback information and the expected CSI feedback information is large, and the first AI unit is considered to be ineffective. Among them, the error between the first CSI feedback information and the expected CSI feedback information being greater than the second threshold in the first information includes the following two situations: (1) The error between the first CSI feedback information and the expected CSI feedback information corresponding to more than X% of the data is less than the first SGCS threshold in the first information, where X% is set according to the actual situation, indicated by the network side, or specified by the protocol; optionally, X can be 5, 10, or 20. (2) The average error between the first CSI feedback information and the expected CSI feedback information corresponding to the first SGCS threshold in the first information.

[0202] For item E-2, SGCS is used as a measure of the difference between two CSI information. SGCS is an indicator parameter that measures the difference between two CSI information. When the SGCS between the first CSI feedback information and the expected CSI feedback information is less than the first SGCS threshold in the first information, it indicates that the difference between the first CSI feedback information and the expected CSI feedback information is large, and the first AI unit is considered to be ineffective. Among them, the SGCS between the first CSI feedback information and the expected CSI feedback information being less than the first SGCS threshold in the first information includes the following two cases: (1) The SGCS between the first CSI feedback information and the expected CSI feedback information corresponding to more than X% of the data is less than the first SGCS threshold in the first information; indicated by the network side or specified by the protocol; optionally, X can be 5, 10, or 20 (2) The SGCS between the first CSI feedback information and the expected CSI feedback information corresponding to the average is less than the first SGCS threshold in the first information.

[0203] For item E-3, if the error between the first reconstructed CSI information and the target CSI information is greater than the third threshold, it indicates that the difference between the first reconstructed CSI information and the target CSI information is large, and the first AI unit is considered to be ineffective.

[0204] For item E-4, SGCS is used to measure the difference between two CSI information. When the SGCS of the first reconstructed CSI information and the target CSI information is less than the second SGCS threshold, it indicates that the difference between the first reconstructed CSI information and the target CSI information is large, and the first AI unit is considered to be ineffective.

[0205] Regarding item E-5, when the error between the first reconstructed CSI information and the target CSI information is greater than the fourth threshold, it indicates that the difference between the first reconstructed CSI information and the target CSI information is large, which may be due to the failure of the first AI unit on the UE side or the second AI unit on the network side device side. Since the error between the second reconstructed CSI information and the target CSI information is less than the fifth threshold, it indicates that the second AI unit on the network side device side is effective, and therefore the first AI unit is determined to be ineffective.

[0206] For item E-6, SGCS is used to measure the difference between two CSI information. If the SGCS of the first reconstructed CSI information and the target CSI information is less than the third SGCS threshold, it indicates that the difference between the first reconstructed CSI information and the target CSI information is large, which may be due to the failure of the first AI unit on the UE side or the failure of the second AI unit on the network side device side. Since the SGCS of the second reconstructed CSI information and the target CSI information is greater than the fourth SGCS threshold, it indicates that the second AI unit on the network side device side is effective, and therefore the first AI unit is determined to be ineffective.

[0207] For item E-7, if the error between the first reconstructed CSI information and the second reconstructed CSI information is greater than the sixth threshold, it indicates that the difference between the first reconstructed CSI information and the second reconstructed CSI information is large, and therefore the first AI unit is considered to be faulty.

[0208] For item E-8, SGCS is used to measure the difference between two CSI information. When the SGCS of the first reconstructed CSI information and the second reconstructed CSI information is less than the fifth SGCS threshold, it indicates that the difference between the first reconstructed CSI information and the second reconstructed CSI information is large, and the first AI unit is considered to be ineffective.

[0209] In one specific implementation, the first AI unit on the UE side is determined to be faulty if at least one of the following conditions is met:

[0210] Item O-1: The error between the second CSI feedback information and the expected CSI feedback information is greater than the second threshold in the first information;

[0211] O-2: The SGCS between the second CSI feedback information and the expected CSI feedback information is less than the first SGCS threshold in the first information;

[0212] Item O-3: The error between the third reconstructed CSI information obtained based on the second CSI feedback information and the target CSI information is greater than the third threshold;

[0213] Item O-4: The SGCS of the third reconstructed CSI information obtained based on the second CSI feedback information and the target CSI information is less than the second SGCS threshold;

[0214] Item O-5: The error between the third reconstructed CSI information obtained based on the second CSI feedback information and the target CSI information is greater than the fourth threshold, and the error between the second reconstructed CSI information obtained based on the expected CSI feedback information and the target CSI information is less than the fifth threshold;

[0215] Item O-6: The SGCS of the third reconstructed CSI information obtained based on the second CSI feedback information and the target CSI information is less than the third SGCS threshold, and the SGCS of the second reconstructed CSI information obtained based on the expected CSI feedback information and the target CSI information is greater than the fourth SGCS threshold;

[0216] Item O-7: The error between the third reconstructed CSI information obtained based on the second CSI feedback information and the second reconstructed CSI information obtained based on the expected CSI feedback information is greater than the sixth threshold;

[0217] Item O-8: The SGCS of the third reconstructed CSI information obtained based on the second CSI feedback information and the second reconstructed CSI information obtained based on the expected CSI feedback information is less than the fifth SGCS threshold.

[0218] In this embodiment, the first CSI feedback information is obtained using the first AI unit on the UE side based on the target CSI information; the expected CSI feedback information is obtained using the second AI unit on the network side based on the target CSI information; the first reconstructed CSI information is obtained using the second AI unit on the network side based on the first CSI feedback information; and the third reconstructed CSI information is obtained using the second AI unit on the network side based on the second CSI feedback information. The second CSI feedback information is obtained using the first AI unit on the UE side based on the quantized value of the target CSI information.

[0219] If the target unit (i.e., the first AI unit or the second AI unit) is not faulty, the first CSI feedback information is similar to the expected CSI feedback information, the first reconstructed CSI information is similar to the target CSI information, and the second reconstructed CSI information is also similar to the target CSI information. Therefore, the error between the two CSI information is used to determine whether the first AI unit on the UE side is faulty.

[0220] For item O-1, when the error between the second CSI feedback information and the expected CSI feedback information is greater than the second threshold in the first information, it indicates that the difference between the second CSI feedback information and the expected CSI feedback information is large, and the first AI unit is considered to be ineffective. Among them, the error between the second CSI feedback information and the expected CSI feedback information being greater than the second threshold in the first information includes the following two situations: (1) The error between the second CSI feedback information and the expected CSI feedback information corresponding to more than X% of the data is less than the first SGCS threshold in the first information, where X% is set according to the actual situation, indicated by the network side, or specified by the protocol; optionally, X can be 5, 10, or 20. (2) The average error between the second CSI feedback information and the expected CSI feedback information is the first SGCS threshold in the first information.

[0221] For item O-2, SGCS is used as a measure of the difference between two CSI information. SGCS is an indicator parameter that measures the difference between two CSI information. When the SGCS between the second CSI feedback information and the expected CSI feedback information is less than the first SGCS threshold in the first information, it indicates that the difference between the second CSI feedback information and the expected CSI feedback information is large, and the first AI unit is considered to be ineffective. Among them, the SGCS between the second CSI feedback information and the expected CSI feedback information being less than the first SGCS threshold in the first information includes the following two cases: (1) The SGCS between the second CSI feedback information and the expected CSI feedback information corresponding to more than X% of the data is less than the first SGCS threshold in the first information; indicated by the network side or specified by the protocol; optionally, X can be 5, 10, or 20 (2) The SGCS between the second CSI feedback information and the expected CSI feedback information corresponding to the average is less than the first SGCS threshold in the first information.

[0222] For item O-3, if the error between the third reconstructed CSI information and the target CSI information is greater than the third threshold, it indicates that the difference between the third reconstructed CSI information and the target CSI information is large, and the first AI unit is considered to be ineffective.

[0223] For item O-4, SGCS is used to measure the difference between two CSI information. When the SGCS of the third reconstructed CSI information and the target CSI information is less than the second SGCS threshold, it indicates that the difference between the third reconstructed CSI information and the target CSI information is large, and the first AI unit is considered to be ineffective.

[0224] Regarding item O-5, when the error between the third reconstructed CSI information and the target CSI information is greater than the fourth threshold, it indicates that the difference between the third reconstructed CSI information and the target CSI information is large, which may be due to the failure of the first AI unit on the UE side or the second AI unit on the network side device side; since the error between the second reconstructed CSI information and the target CSI information is less than the fifth threshold, it indicates that the second AI unit on the network side device side is effective, and therefore the first AI unit is determined to be ineffective.

[0225] For item O-6, SGCS is used to measure the difference between two CSI information. The SGCS of the third reconstructed CSI information and the target CSI information is less than the third SGCS threshold, indicating that the difference between the third reconstructed CSI information and the target CSI information is large. This may be due to the failure of the first AI unit on the UE side or the failure of the second AI unit on the network side device side. Since the SGCS of the second reconstructed CSI information and the target CSI information is greater than the fourth SGCS threshold, it indicates that the second AI unit on the network side device side is effective. Therefore, the first AI unit is determined to be ineffective.

[0226] For item E-7, if the error between the third reconstructed CSI information and the second reconstructed CSI information is greater than the sixth threshold, it indicates that the difference between the third reconstructed CSI information and the second reconstructed CSI information is large, and therefore the first AI unit is considered to be ineffective.

[0227] For item E-8, SGCS is used to measure the difference between two CSI information. When the SGCS of the third reconstructed CSI information and the second reconstructed CSI information is less than the fifth SGCS threshold, it indicates that the difference between the third reconstructed CSI information and the second reconstructed CSI information is large, and the first AI unit is considered to be ineffective.

[0228] 4. The following describes the execution process after the UE receives the first information:

[0229] In one specific implementation, after receiving the first information, the UE further performs the following steps:

[0230] Step H1: The UE sends a third indication information, which indicates that the first AI unit has been updated or the updated first AI unit can be activated; or the third indication information indicates that the first AI unit is in a pending activation state; or the third indication information indicates that the first AI unit has been updated or the updated first AI unit has been released or is in an unavailable state.

[0231] In this embodiment of the application, when the first AI unit on the UE side fails, the UE updates the failure status of the first AI unit and sends a third indication message to the network-side device to inform the network-side device of the current status of the first AI unit (e.g., the first AI unit is in an inactive state).

[0232] In some embodiments, the third indication information is further used to indicate that the first AI unit can be activated and used; or the third indication information is used to indicate that the first AI unit is in a pending activation state; or the third indication information is used to indicate that the first AI unit is released or in an unavailable state. The state of the first AI unit includes one or more of the following: can be activated and used, in a pending activation state, released, or in an unavailable state. Therefore, the UE can inform the network-side device of the state of the first AI unit through the third indication information, so that the network-side device can perform the next step of processing according to the state of the first AI unit.

[0233] Correspondingly, the network-side device performs the following steps:

[0234] Step J1: Receive the third indication information sent by the UE;

[0235] Step J2: Based on the third indication information, determine that the first AI unit has been updated or the updated first AI unit can be activated and used, or determine that the first AI unit is in a pending activation state, or determine that the first AI unit has been updated or the updated first AI unit has been released or is in an unavailable state.

[0236] In this embodiment, the network-side device can determine the current state of the first AI unit based on the third indication information, and perform the next operation according to the current state of the first AI unit. Thus, even if the first AI unit fails, subsequent actions can be performed, and CSI information can still be processed even if the first AI unit fails.

[0237] In one specific implementation, after receiving the first information, the UE further performs the following steps:

[0238] Step K1: The UE updates the first AI unit based on information related to the target unit update;

[0239] Step K2: When the first AI unit satisfies the first condition, the UE sends third indication information; the first condition is agreed upon by the protocol or indicated by the first information.

[0240] In this embodiment of the application, the first information includes information related to the update of the target unit. The UE updates the first AI unit based on the information related to the update of the target unit, and sends third indication information when the first AI unit meets the first condition. The first condition is used to determine whether the first AI unit is valid.

[0241] Optionally, the first condition includes at least one of the following:

[0242] M-1 item: The SGCS between the first CSI feedback information and the expected CSI feedback information obtained by the UE using the third dataset and the updated first AI unit is greater than the SGCS threshold in the first information;

[0243] M-2 item: The error between the first CSI feedback information obtained by the UE using the third dataset and the updated first AI unit and the expected CSI feedback information is less than the second threshold in the first information;

[0244] M-3: The updated first AI unit passed the backward test.

[0245] Specifically, for item M-1, when the SGCS between the first CSI feedback information and the expected CSI feedback information is greater than the SGCS threshold in the first information, it indicates that the difference between the first CSI feedback information and the expected CSI feedback information is small, confirming that the first AI unit is effective. The situation where the SGCS between the first CSI feedback information and the expected CSI feedback information is greater than the SGCS threshold in the first information includes the following two cases: (1) the SGCS between the first CSI feedback information and the expected CSI feedback information corresponding to more than X% of the data is greater than the first SGCS threshold in the first information; (2) the SGCS between the average first CSI feedback information and the expected CSI feedback information is greater than the first SGCS threshold in the first information.

[0246] For item M-2, when the error between the first CSI feedback information and the expected CSI feedback information is less than the second threshold in the first information, it indicates that the difference between the first CSI feedback information and the expected CSI feedback information is small, confirming that the first AI unit is effective. Similarly, the error between the first CSI feedback information and the expected CSI feedback information being less than the second threshold in the first information includes the following two cases: (1) the error between the first CSI feedback information and the expected CSI feedback information corresponding to more than X% of the data is less than the second threshold in the first information; (2) the error between the average first CSI feedback information and the expected CSI feedback information is less than the second threshold in the first information.

[0247] For item M-3, the network-side device or protocol specifies test data, and the validity information or monitoring information of the target unit is determined based on the test data and the first AI unit. If the updated first AI unit passes the backward test, it indicates that the updated first AI unit is effective.

[0248] In this embodiment, the updated first AI unit is determined to be valid based on at least one of the conditions from M-1 to M-3. The UE then feeds back the valid status of the updated first AI unit to the network-side device, so that the network-side device can perform the next step of processing based on the status of the first AI unit.

[0249] The information processing method in this application will be described through the following embodiments.

[0250] Example 1

[0251] Reference Figure 6 As shown, Figure 6 This is a flowchart illustrating an implementation of an information processing method according to an embodiment of this application. The specific steps are as follows:

[0252] Step 1: The UE reports auxiliary information, which includes at least one of the following: target CSI information; monitoring information of the target unit estimated by the terminal; quantized value of the target CSI information; second CSI feedback information obtained by the UE based on the quantized value of the target CSI information; and third CSI feedback information obtained by the UE using a reference model.

[0253] Step 2: Network-side device auxiliary information, and based on the auxiliary information, determine the reason or first information for whether the target unit is valid or invalid, wherein the target unit is a unit used to process CSI information.

[0254] Step 3: The network-side device sends first information to the UE, the first information including at least one of the following: the reason for the failure of the target unit, the target unit being a unit used to process CSI information; indication information for deactivating the target unit; indication information for switching the target unit; information related to target unit updates; information related to a new target unit; first indication information for indicating that the target unit should be updated or optimized; and second indication information for indicating the quantization level or optimization level of the target unit.

[0255] In this embodiment, the UE reports auxiliary information to the network-side device so that the network-side device can determine the cause of the target unit failure based on the auxiliary information, or trigger the network-side device to send first information to the UE. Thus, the UE can determine whether the target unit has failed based on the first information, and if the target unit fails, determine the cause of the failure, and determine the subsequent actions performed by the UE and the network-side device after the target unit fails, thereby realizing CSI information processing in the case of target unit failure.

[0256] Example 2

[0257] Reference Figure 7 As shown, Figure 7 This is a flowchart illustrating another information processing method in this application. The specific steps are as follows. It should be understood that the information processing method may not necessarily include all of the following steps; one or more of the following steps may be optional:

[0258] Step 1: The UE reports auxiliary information, which includes at least one of the following: target CSI information; monitoring information of the target unit estimated by the terminal; quantized value of the target CSI information; second CSI feedback information obtained by the UE based on the quantized value of the target CSI information; and third CSI feedback information obtained by the UE using a reference model.

[0259] Step 2: Network-side device auxiliary information, and based on the auxiliary information, determine the reason or first information for whether the target unit is valid or invalid, wherein the target unit is a unit used to process CSI information.

[0260] Step 3: The network-side device sends the first AI unit update instruction to the UE.

[0261] Step 4: The UE sends a fourth indication information to the network-side device at the first moment. The fourth indication information is used to instruct the network-side device to send the first information or request to update the first AI unit. The first information includes at least information related to the update of the target unit.

[0262] Step 5: The network-side device sends the first information to the UE.

[0263] Step 6: The UE updates the first AI unit based on information related to the target unit update, and sends third indication information when the first AI unit meets the first condition; wherein the first condition is agreed upon by the protocol or indicated by the first information.

[0264] In this embodiment, the UE reports auxiliary information to the network-side device so that the network-side device can determine the cause of the target unit failure based on the auxiliary information. When the UE determines that the first AI unit has failed, the UE sends first information to the network-side device, which includes at least information related to the target unit update. The UE updates the first AI unit based on the information related to the target unit update, and informs the network-side device of the state satisfied by the updated first AI unit through third indication information. This enables the network-side device to determine the current state of the first AI unit based on the third indication information and to perform the next operation based on the current state of the first AI unit. Thus, even when the first AI unit fails, subsequent actions can be performed, and CSI information can still be processed even when the first AI unit fails.

[0265] Example 3

[0266] Refer to the image below. Figure 8 This is a flowchart illustrating another information processing method in this application, with specific steps 1 and 2 as follows:

[0267] Step 1: The UE receives second information, wherein the second information is used to assist the UE in determining the effectiveness of testing or monitoring the target unit, or to help the UE determine the cause of the target unit failure.

[0268] The second information includes at least one of the following Z-1 to Z-3 items:

[0269] Z-1 item: Performance test dataset information.

[0270] In one embodiment, the performance test dataset includes multiple data sets, and the dataset information includes: the number of data sets, the format of the data sets, expected CSI feedback information corresponding to the number of data sets, and target CSI information. In one embodiment, the performance test dataset includes multiple data sets, each data set including expected CSI feedback information; optionally, each data set includes target CSI information corresponding to the expected CSI feedback information.

[0271] Z-2: Reference model information.

[0272] The reference model is used to determine the reconstructed CSI information or the UE's monitoring information on the UE side. For example, SGCS, model validity information, or data offset information.

[0273] Z-3: Feature information of the dataset. Feature information includes: variance, SNR, SINR, etc.

[0274] Step 2: The UE reports the CSI feedback information and / or the first information, such as the reason for the target unit's failure, deactivates the target unit's indication information, switches the target unit's indication information, and requests updated information for the target unit. The CSI feedback information can be the first CSI feedback information, the second CSI feedback information, or the third CSI feedback information.

[0275] A second aspect of this application provides another method for sending configuration information, which is applied to a network-side device. See [link to relevant documentation]. Figure 9 The diagram shown is a flowchart of another information processing method provided in an embodiment of this application. The method may include the following steps:

[0276] Step S910: The network-side device receives auxiliary information reported by the user equipment (UE);

[0277] Step S920: The network-side device determines the reason or first information for whether the target unit is valid or invalid based on the auxiliary information, wherein the target unit is a unit used to process CSI information;

[0278] The auxiliary information includes at least one of the following:

[0279] Target CSI information;

[0280] The monitoring information of the target unit estimated by the terminal;

[0281] The quantized value of the target CSI information;

[0282] The second CSI feedback information obtained by the UE based on the quantized value of the target CSI information;

[0283] The UE uses the third CSI feedback information obtained from the reference model.

[0284] In this embodiment of the application, the network-side device may be Figure 1 The core network device or access network device 12 in the network can be found in the previous text for examples of network-side devices 12, and will not be repeated here.

[0285] Through the above steps, the network-side device can determine whether the target unit is valid or the reason for its failure based on the auxiliary information, and can determine the subsequent actions performed by the UE and the network-side device after the target unit fails, thereby realizing CSI information processing in the case of target unit failure.

[0286] In one specific implementation, the cause of target unit failure includes at least one of the following:

[0287] The first AI unit on the UE side failed;

[0288] The second AI unit of the network-side device failed.

[0289] A data offset occurs, which indicates that the first data or first dataset obtained in time slot n is offset relative to the second dataset used to obtain the target unit;

[0290] The error between the expected CSI feedback information and the first CSI feedback information obtained by the first AI unit on the UE side is greater than a first threshold.

[0291] The quantization level or optimization level of the target unit.

[0292] In one specific implementation, the network-side device determines the reason for whether the target unit is valid or invalid based on the auxiliary information, including:

[0293] If the error between the expected CSI feedback information and the first CSI feedback information obtained by the first AI unit on the UE side is greater than a first threshold, and the error between the first reconstructed CSI information obtained based on the first CSI feedback information and the target CSI information is less than a second threshold, the target unit is determined to be valid.

[0294] If the error between the expected CSI feedback information and the first CSI feedback information obtained by the first AI unit on the UE side is less than the first threshold, and the error between the first reconstructed CSI information obtained based on the first CSI feedback information and the target CSI information is greater than the second threshold, the cause of the target unit failure is determined to be: data offset occurs, wherein the data offset indicates that the first data or the first dataset obtained in time slot n is offset relative to the second dataset used to obtain the target unit;

[0295] If the error between the expected CSI feedback information and the first CSI feedback information obtained through the first AI unit on the UE side is greater than the first threshold, and the error between the first reconstructed CSI information obtained based on the first CSI feedback information and the target CSI information is greater than the second threshold, the cause of the target unit failure is determined to be: data offset or failure of the first AI unit on the UE side.

[0296] In one specific implementation, the method further includes:

[0297] The network-side device sends first information to the UE, the first information including at least one of the following:

[0298] The reason for the failure of the target unit, which is a unit used to process CSI information;

[0299] Deactivate the instruction information of the target unit;

[0300] Switch the indication information of the target unit;

[0301] Information related to the update of the target unit;

[0302] Information related to the new target unit;

[0303] The first instruction information is used to instruct the target unit to be updated or optimized:

[0304] The second indication information is used to indicate the quantization level or optimization level of the target unit.

[0305] In one specific implementation, the first information includes at least information related to the target unit update; the information related to the target unit update includes at least one of the following:

[0306] A third dataset, which includes expected CSI feedback information;

[0307] The second threshold is the upper limit of the error between the first CSI feedback information obtained by the UE using the updated first AI unit and the expected CSI feedback information;

[0308] The SGCS threshold is the lower limit of the SGCS between the first CSI feedback information obtained by the UE using the updated first AI unit and the expected CSI feedback information.

[0309] In one specific implementation, when the cause of the target unit failure is a data offset, the first information includes at least one of the following:

[0310] Switch the indication information of the target unit;

[0311] Information related to the new target unit;

[0312] Used to obtain the second dataset of the target unit.

[0313] In one specific implementation, the method further includes:

[0314] Receive the third indication information sent by the UE;

[0315] Based on the third indication information, it is determined that the first AI unit has been updated or the updated first AI unit can be activated and used, or that the first AI unit is in a pending activation state, or that the first AI unit has been updated or the updated first AI unit has been released or is in an unavailable state.

[0316] In one specific implementation, the method further includes:

[0317] Receive the fourth indication information sent by the UE;

[0318] According to the fourth instruction information, the first information is sent to the UE, and the first information includes at least information related to the target unit update.

[0319] In one specific implementation, the first information further includes:

[0320] CSI reporting configuration information is used to instruct the UE to update the first AI unit used by the UE, or to instruct the UE to return to non-AI CSI reporting.

[0321] In one specific implementation, the first information further includes:

[0322] Model recognition information;

[0323] Data set identification information;

[0324] CSI reports identification information;

[0325] Monitoring and identification information.

[0326] In one specific implementation, the method further includes:

[0327] The desired CSI feedback information is obtained based on the target CSI information or the quantized value of the target CSI information.

[0328] The information processing method provided in this application can be executed by an information processing device. This application uses an information processing device executing the information processing method as an example to illustrate the information processing device provided in this application.

[0329] This application provides an information processing apparatus. As an example, the information processing apparatus may be a communication device or a component within a communication device, such as a chip. The communication device may be a terminal, a network-side device, or a server, etc. Exemplarily, the terminal may include, but is not limited to, the type of terminal 11 listed above, and the network-side device may include, but is not limited to, the type of network-side device 12 listed above. This application does not impose specific limitations.

[0330] The information processing device includes a receiving module, a transmitting module, and a processing module. These modules can be implemented in software or hardware. When implemented in hardware, the processing module can be implemented by a processor. For example, the processor can include general-purpose processors, special-purpose processors, such as a Central Processing Unit (CPU), microprocessor, Digital Signal Processor (DSP), Artificial Intelligence (AI) processor, Graphics Processing Unit (GPU), Application Specific Integrated Circuit (ASIC), Network Processor (NP), Field Programmable Gate Array (FPGA), or other programmable logic devices, gate circuits, transistors, discrete hardware components, etc. The receiving and transmitting modules can be implemented by a communication interface, which can include one or more of the following: transceiver, pins, circuits, bus, radio frequency unit, etc.

[0331] For details, see Figure 10 When the information processing device is a terminal or a component within a terminal, the information processing device 1000 includes:

[0332] The first receiving module 1001 is configured to receive first information, the first information including at least one of the following: the reason for the failure of the target unit, the target unit being a unit used for processing CSI information; indication information for deactivating the target unit; indication information for switching the target unit; information related to target unit updates; information related to a new target unit; first indication information for indicating that the target unit should be updated or optimized; and second indication information for indicating the quantization level or optimization level of the target unit.

[0333] The information processing device can determine whether the target unit (AI model) has failed based on the first information, and can determine the cause of the target unit failure if the target unit fails, and can determine the subsequent actions performed by the UE and network-side equipment after the target unit fails, thereby realizing CSI information processing in the case of target unit failure.

[0334] In one specific implementation, the cause of target unit failure includes at least one of the following:

[0335] The first artificial intelligence (AI) unit on the UE side has failed.

[0336] The second AI unit on the network-side device side failed.

[0337] A data offset occurs, which indicates that the first data or first dataset obtained in time slot n is offset relative to the second dataset used to obtain the target unit;

[0338] The error between the expected CSI feedback information and the first CSI feedback information obtained by the first AI unit on the UE side is greater than a first threshold.

[0339] The quantization level or optimization level of the target unit.

[0340] In one specific implementation, the first AI unit on the UE side is determined to be faulty if at least one of the following conditions is met:

[0341] The error between the first CSI feedback information and the expected CSI feedback information is greater than the second threshold in the first information;

[0342] The SGCS between the first CSI feedback information and the expected CSI feedback information is less than the first SGCS threshold in the first information;

[0343] The error between the first reconstructed CSI information obtained based on the first CSI feedback information and the target CSI information is greater than the third threshold.

[0344] The SGCS of the first reconstructed CSI information and the target CSI information obtained based on the first CSI feedback information is less than the second SGCS threshold;

[0345] The error between the first reconstructed CSI information obtained based on the first CSI feedback information and the target CSI information is greater than a fourth threshold, and the error between the second reconstructed CSI information obtained based on the expected CSI feedback information and the target CSI information is less than a fifth threshold;

[0346] The SGCS of the first reconstructed CSI information obtained based on the first CSI feedback information and the target CSI information is less than the third SGCS threshold, and the SGCS of the second reconstructed CSI information obtained based on the expected CSI feedback information and the target CSI information is greater than the fourth SGCS threshold.

[0347] The error between the first reconstructed CSI information obtained based on the first CSI feedback information and the second reconstructed CSI information obtained based on the expected CSI feedback information is greater than a sixth threshold.

[0348] The SGCS of the first reconstructed CSI information obtained based on the first CSI feedback information and the second reconstructed CSI information obtained based on the expected CSI feedback information are less than the fifth SGCS threshold.

[0349] In one specific implementation, the first information includes at least information related to the target unit update; the information related to the target unit update includes at least one of the following:

[0350] A third dataset, which includes expected CSI feedback information;

[0351] The second threshold is the upper limit of the error between the first CSI feedback information obtained by the UE using the updated first AI unit and the expected CSI feedback information;

[0352] The SGCS threshold is the lower limit of the SGCS between the first CSI feedback information obtained by the UE using the updated first AI unit and the expected CSI feedback information.

[0353] In one specific implementation, when the cause of the target unit failure is a data offset, the first information includes at least one of the following:

[0354] Switch the indication information of the target unit;

[0355] Information related to the new target unit;

[0356] Used to obtain the second dataset of the target unit.

[0357] In one specific embodiment, the information processing device 1000 further includes:

[0358] The first sending module is used to send third indication information, which indicates that the first AI unit has been updated or the updated first AI unit can be activated and used; or the third indication information indicates that the first AI unit is in a pending activation state; or the third indication information indicates that the first AI unit has been updated or the updated first AI unit has been released or is in an unavailable state.

[0359] In one specific embodiment, the information processing device 1000 further includes:

[0360] An update module is used to update the first AI unit based on information related to the update of the target unit;

[0361] The first sending module is further configured to send third indication information when the first AI unit satisfies the first condition; the first condition is agreed upon by the protocol or indicated by the first information.

[0362] In one specific implementation, the first condition includes at least one of the following:

[0363] The SGCS between the first CSI feedback information and the expected CSI feedback information obtained by the UE using the third dataset and the updated first AI unit is greater than the SGCS threshold in the first information.

[0364] The error between the first CSI feedback information obtained by the UE using the third dataset and the updated first AI unit and the expected CSI feedback information is less than the second threshold in the first information;

[0365] The updated first AI unit passed the backward testing.

[0366] In one specific embodiment, the information processing device 1000 further includes:

[0367] The second sending module is used to send fourth indication information to the network-side device at a first moment. The fourth indication information is used to instruct the network-side device to send the first information. The first information includes at least information related to the update of the target unit.

[0368] In one specific embodiment, the information processing device 1000 further includes:

[0369] The first reporting module is used to report auxiliary information, which includes at least one of the following:

[0370] Target CSI information;

[0371] The monitoring information of the target unit estimated by the terminal;

[0372] The quantized value of the target CSI information;

[0373] The second CSI feedback information obtained by the UE based on the quantized value of the target CSI information;

[0374] The UE uses the third CSI feedback information obtained from the reference model.

[0375] In one specific implementation, the auxiliary information is used by the network-side device to determine the cause of the target unit's failure or as first information, or...

[0376] The auxiliary information is used to trigger the network-side device to send first information to the UE.

[0377] In one specific implementation, the first information further includes:

[0378] CSI reporting configuration information is used to instruct the UE to update the first AI unit on the UE side, or to instruct the UE to return to non-AI CSI reporting.

[0379] In one specific implementation, the first information further includes:

[0380] Model recognition information;

[0381] Data set identification information;

[0382] CSI reports identification information;

[0383] Monitoring and identification information.

[0384] In one specific implementation, the expected CSI feedback information is obtained by the network-side device based on the target CSI information or the quantized value of the target CSI information.

[0385] The information processing apparatus provided in this application embodiment can implement the various processes implemented in the information processing method embodiment and achieve the same technical effect. To avoid repetition, it will not be described again here.

[0386] The information processing method provided in this application can be executed by another information processing device. This application uses an example of another information processing device executing the information processing method to illustrate the other information processing device provided in this application.

[0387] This application provides another information processing apparatus. As an example, the information processing apparatus may be a communication device or a component within a communication device, such as a chip. The communication device may be a terminal, a network-side device, or a server, etc. Exemplarily, the terminal may include, but is not limited to, the type of terminal 11 listed above, and the network-side device may include, but is not limited to, the type of network-side device 12 listed above. This application does not impose specific limitations.

[0388] The information processing device includes a receiving module, a transmitting module, and a processing module. These modules can be implemented in software or hardware. When implemented in hardware, the processing module can be implemented by a processor. For example, the processor can include general-purpose processors, special-purpose processors, such as a Central Processing Unit (CPU), microprocessor, Digital Signal Processor (DSP), Artificial Intelligence (AI) processor, Graphics Processing Unit (GPU), Application Specific Integrated Circuit (ASIC), Network Processor (NP), Field Programmable Gate Array (FPGA), or other programmable logic devices, gate circuits, transistors, discrete hardware components, etc. The receiving and transmitting modules can be implemented by a communication interface, which can include one or more of the following: transceiver, pins, circuits, bus, radio frequency unit, etc.

[0389] See Figure 11 When the information processing device is a network-side device or a component of a network-side device, the information processing device 1100 includes:

[0390] The second receiving module 1101 is used to receive auxiliary information reported by the user equipment (UE).

[0391] The first determining module 1102 is used to determine, based on the auxiliary information, whether the target unit is effective or the reason for its failure or the first information, wherein the target unit is a unit used to process CSI information;

[0392] The auxiliary information includes at least one of the following:

[0393] Target CSI information;

[0394] The monitoring information of the target unit estimated by the terminal;

[0395] The quantized value of the target CSI information;

[0396] The second CSI feedback information obtained by the UE based on the quantized value of the target CSI information;

[0397] The UE uses the third CSI feedback information obtained from the reference model.

[0398] The information processing device can determine the reason for whether the target unit is valid or invalid based on auxiliary information, and can determine the subsequent actions performed by the UE and network-side equipment after the target unit fails, thereby realizing CSI information processing in the case of target unit failure.

[0399] In one specific implementation, the cause of target unit failure includes at least one of the following:

[0400] The first AI unit on the UE side failed;

[0401] The second AI unit of the network-side device failed.

[0402] A data offset occurs, which indicates that the first data or first dataset obtained in time slot n is offset relative to the second dataset used to obtain the target unit;

[0403] The error between the expected CSI feedback information and the first CSI feedback information obtained by the first AI unit on the UE side is greater than a first threshold.

[0404] The quantization level or optimization level of the target unit.

[0405] In one specific implementation, the network-side device determines the reason for whether the target unit is valid or invalid based on the auxiliary information, including:

[0406] If the error between the expected CSI feedback information and the first CSI feedback information obtained by the first AI unit on the UE side is greater than a first threshold, and the error between the first reconstructed CSI information obtained based on the first CSI feedback information and the target CSI information is less than a second threshold, the target unit is determined to be valid.

[0407] If the error between the expected CSI feedback information and the first CSI feedback information obtained by the first AI unit on the UE side is less than the first threshold, and the error between the first reconstructed CSI information obtained based on the first CSI feedback information and the target CSI information is greater than the second threshold, the cause of the target unit failure is determined to be: data offset occurs, wherein the data offset indicates that the first data or the first dataset obtained in time slot n is offset relative to the second dataset used to obtain the target unit;

[0408] If the error between the expected CSI feedback information and the first CSI feedback information obtained through the first AI unit on the UE side is greater than the first threshold, and the error between the first reconstructed CSI information obtained based on the first CSI feedback information and the target CSI information is greater than the second threshold, the cause of the target unit failure is determined to be: data offset or failure of the first AI unit on the UE side.

[0409] In one specific embodiment, the information processing device 1100 further includes:

[0410] The third transmitting module is configured to transmit first information to the UE, the first information including at least one of the following:

[0411] The reason for the failure of the target unit, which is a unit used to process CSI information;

[0412] Deactivate the instruction information of the target unit;

[0413] Switch the indication information of the target unit;

[0414] Information related to the update of the target unit;

[0415] Information related to the new target unit;

[0416] The first instruction information is used to instruct the target unit to be updated or optimized:

[0417] The second indication information is used to indicate the quantization level or optimization level of the target unit.

[0418] In one specific implementation, the first information includes at least information related to the target unit update; the information related to the target unit update includes at least one of the following:

[0419] A third dataset, which includes expected CSI feedback information;

[0420] The second threshold is the upper limit of the error between the first CSI feedback information obtained by the UE using the updated first AI unit and the expected CSI feedback information;

[0421] The SGCS threshold is the lower limit of the SGCS between the first CSI feedback information obtained by the UE using the updated first AI unit and the expected CSI feedback information.

[0422] In one specific implementation, when the cause of the target unit failure is a data offset, the first information includes at least one of the following:

[0423] Switch the indication information of the target unit;

[0424] Information related to the new target unit;

[0425] Used to obtain the second dataset of the target unit.

[0426] In one specific embodiment, the information processing device 1100 further includes:

[0427] The third receiving module is used to receive the third indication information sent by the UE;

[0428] The second determining module is configured to determine, based on the third indication information, whether the first AI unit has been updated or the updated first AI unit can be activated, or whether the first AI unit is in a pending activation state, or whether the first AI unit has been updated or the updated first AI unit has been released or is in an unavailable state.

[0429] In one specific embodiment, the information processing device 1100 further includes:

[0430] The fourth receiving module is used to receive the fourth indication information sent by the UE;

[0431] The fourth sending module is configured to send the first information to the UE according to the fourth indication information, wherein the first information includes at least information related to the target unit update.

[0432] In one specific implementation, the first information further includes:

[0433] CSI reporting configuration information is used to instruct the UE to update the first AI unit used by the UE, or to instruct the UE to return to non-AI CSI reporting.

[0434] In one specific implementation, the first information further includes:

[0435] Model recognition information;

[0436] Data set identification information;

[0437] CSI reports identification information;

[0438] Monitoring and identification information.

[0439] In one specific embodiment, the information processing device 1100 further includes:

[0440] The acquisition module is used to obtain the expected CSI feedback information based on the target CSI information or the quantized value of the target CSI information.

[0441] The information processing apparatus provided in this application embodiment can implement the various processes implemented in the information processing method embodiment and achieve the same technical effect. To avoid repetition, it will not be described again here.

[0442] like Figure 12 As shown in the illustration, this application also provides a communication device 1200, including a processor 1201 and a memory 1202. The memory 1202 stores programs or instructions that can run on the processor 1201. For example, when the communication device 1200 is a terminal, the program or instructions executed by the processor 1201 implement the various steps of the above-described information processing method embodiments and achieve the same technical effect. When the communication device 1200 is a network-side device, the program or instructions executed by the processor 1201 implement the various steps of the above-described information processing method embodiments and achieve the same technical effect. To avoid repetition, further details are omitted here.

[0443] This application embodiment also provides a user equipment, including a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is used to run programs or instructions to implement, for example... Figure 5 The steps in the method embodiment shown in the information processing method are described above. This user equipment embodiment corresponds to the above-described user equipment-side method embodiment. All implementation processes and methods of the above-described method embodiments can be applied to this user equipment embodiment and achieve the same technical effect. The user equipment can be... Figure 10 The information processing device shown. Specifically, Figure 13 A schematic diagram of the hardware structure of a user equipment to implement an embodiment of this application.

[0444] The user equipment 13200 includes, but is not limited to, at least some of the following components: radio frequency unit 1301, network module 1302, audio output unit 1303, input unit 1304, sensor 1305, display unit 1306, user input unit 1307, interface unit 1308, memory 1309, and processor 1310.

[0445] Those skilled in the art will understand that the user equipment 1300 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 1310 through a power management system, thereby enabling functions such as managing charging, discharging, and power consumption through the power management system. Figure 13 The user equipment structure shown in the figure does not constitute a limitation on the user equipment. The user equipment may include more or fewer components than shown, or combine certain components, or have different component arrangements, which will not be elaborated here.

[0446] It should be understood that, in this embodiment, the input unit 1304 may include a graphics processor 13041 and a microphone 13042. The graphics processor 13041 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 1306 may include a display panel 13061, which may be configured in the form of a liquid crystal display, an organic light-emitting diode, or the like. The user input unit 1307 includes a touch panel 13071 and at least one of other input devices 13072. The touch panel 13071 is also called a touch screen. The touch panel 13071 may include a touch detection device and a touch controller. Other input devices 13072 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.

[0447] In this embodiment, after receiving downlink data from the network-side device, the radio frequency unit 1301 can transmit it to the processor 1310 for processing; in addition, the radio frequency unit 1301 can send uplink data to the network-side device. Typically, the radio frequency unit 1301 includes, but is not limited to, antennas, amplifiers, transceivers, couplers, low-noise amplifiers, duplexers, etc.

[0448] The memory 1309 can be used to store software programs or instructions, as well as various data. The memory 1309 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 1309 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 1309 in this embodiment includes, but is not limited to, these and any other suitable types of memory.

[0449] Processor 1310 may include one or more processing units; optionally, processor 1310 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 1310.

[0450] The radio frequency unit 1301 is used to receive first information, which includes at least one of the following: the reason for the failure of the target unit, wherein the target unit is a unit used to process CSI information; indication information for deactivating the target unit; indication information for switching the target unit; information related to target unit updates; information related to a new target unit; first indication information for indicating that the target unit should be updated or optimized; and second indication information for indicating the quantization level or optimization level of the target unit.

[0451] In this way, the user equipment can determine whether the target unit (AI model) has failed based on the first information, and can determine the cause of the target unit failure if the target unit fails, and can determine the subsequent actions performed by the UE and network-side equipment after the target unit fails, thus realizing CSI information processing in the case of target unit failure.

[0452] It is understood that the implementation process of each implementation method mentioned in this embodiment can refer to the relevant description of the information processing method in the method embodiment and achieve the same or corresponding technical effect. To avoid repetition, it will not be described again here.

[0453] This application embodiment also provides a network-side device, including a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is used to run programs or instructions to implement, for example... Figure 9 The steps of the method embodiment shown are illustrated. This network-side device embodiment corresponds to the above-described network-side device method embodiment. All implementation processes and methods of the above-described method embodiments can be applied to this network-side device embodiment and can achieve the same technical effect.

[0454] Specifically, embodiments of this application also provide a network-side device. For example... Figure 14 As shown, the network-side device 1400 includes: a processor 1401, a network interface 1402, and a memory 1403. This network-side device can be... Figure 11 The information processing device shown. The network interface 1402 is, for example, a common public radio interface (CPRI).

[0455] Specifically, the network-side device 1400 in this application embodiment further includes: instructions or programs stored in memory 1403 and executable on processor 1401, wherein processor 1401 calls the instructions or programs in memory 1403 to execute the above-mentioned... Figure 11 The functions of each module of the information processing device shown are the same and achieve the same technical effect. To avoid repetition, they will not be described in detail here.

[0456] 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 information processing method embodiments and achieve the same technical effects. To avoid repetition, they will not be described again here.

[0457] The processor mentioned above is the processor in the terminal described in the above embodiments. The readable storage medium includes computer-readable storage media, such as computer read-only memory (ROM), random access memory (RAM), magnetic disk, or optical disk. In some examples, the readable storage medium may be a non-transient readable storage medium.

[0458] 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 information processing method embodiments and can achieve the same technical effect. To avoid repetition, it will not be described again here.

[0459] 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.

[0460] 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 information processing method embodiments, and can achieve the same technical effect. To avoid repetition, it will not be described again here.

[0461] This application also provides a wireless communication system, including: a user equipment and a network-side device, wherein the user equipment can be used to execute the steps of the user equipment-side information processing method described above, and the network-side device can be used to execute the steps of the network-side information processing method described above.

[0462] 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.

[0463] From the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of computer software products plus necessary general-purpose hardware platforms, and of course, they can also be implemented by hardware. The computer software product is stored in a storage medium (such as ROM, RAM, magnetic disk, optical disk, etc.) and includes several instructions to cause the terminal or network-side device to execute the methods described in the various embodiments of this application.

[0464] 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. An information processing method, characterized in that, include: User equipment (UE) receives first information, the first information including at least one of the following: The reason for the failure of the target unit is that the target unit is a unit used to process channel state (CSI) information; Deactivate the instruction information of the target unit; Switch the indication information of the target unit; Information related to the update of the target unit; Information related to the new target unit; The first instruction information is used to instruct the target unit to be updated or optimized: The second indication information is used to indicate the quantization level or optimization level of the target unit.

2. The method according to claim 1, characterized in that, The causes of target cell failure include at least one of the following: The first artificial intelligence (AI) unit on the UE side has failed. The second AI unit on the network-side device side failed. A data offset occurs, which indicates that the first data or first dataset obtained in time slot n is offset relative to the second dataset used to obtain the target unit; The error between the expected CSI feedback information and the first CSI feedback information obtained by the first AI unit on the UE side is greater than a first threshold. The quantization level or optimization level of the target unit.

3. The method according to claim 1 or 2, characterized in that, The first AI unit on the UE side is determined to be faulty if at least one of the following conditions is met: The error between the first CSI feedback information and the expected CSI feedback information is greater than the second threshold in the first information; The SGCS between the first CSI feedback information and the expected CSI feedback information is less than the first SGCS threshold in the first information; The error between the first reconstructed CSI information obtained based on the first CSI feedback information and the target CSI information is greater than the third threshold. The SGCS of the first reconstructed CSI information and the target CSI information obtained based on the first CSI feedback information is less than the second SGCS threshold; The error between the first reconstructed CSI information obtained based on the first CSI feedback information and the target CSI information is greater than a fourth threshold, and the error between the second reconstructed CSI information obtained based on the expected CSI feedback information and the target CSI information is less than a fifth threshold; The SGCS of the first reconstructed CSI information obtained based on the first CSI feedback information and the target CSI information is less than the third SGCS threshold, and the SGCS of the second reconstructed CSI information obtained based on the expected CSI feedback information and the target CSI information is greater than the fourth SGCS threshold. The error between the first reconstructed CSI information obtained based on the first CSI feedback information and the second reconstructed CSI information obtained based on the expected CSI feedback information is greater than a sixth threshold. The SGCS of the first reconstructed CSI information obtained based on the first CSI feedback information and the second reconstructed CSI information obtained based on the expected CSI feedback information are less than the fifth SGCS threshold.

4. The method according to claim 1, characterized in that, The first information includes at least information related to the target unit update; the information related to the target unit update includes at least one of the following: A third dataset, which includes expected CSI feedback information; The second threshold is the upper limit of the error between the first CSI feedback information obtained by the UE using the updated first AI unit and the expected CSI feedback information; The SGCS threshold is the lower limit of the SGCS between the first CSI feedback information obtained by the UE using the updated first AI unit and the expected CSI feedback information.

5. The method according to claim 1, characterized in that, If the cause of the target cell failure is a data offset, the first information includes at least one of the following: Switch the indication information of the target unit; Information related to the new target unit; Used to obtain the second dataset of the target unit.

6. The method according to claim 1, characterized in that, The method further includes: The UE sends a third indication message, which indicates that the first AI unit has been updated or the updated first AI unit can be activated; or the third indication message indicates that the first AI unit is in a pending activation state; or the third indication message indicates that the first AI unit has been updated or the updated first AI unit has been released or is in an unavailable state.

7. The method according to claim 6, characterized in that, Before the UE sends the third indication information, the following is also included: The UE updates the first AI unit based on information related to the target unit update; The UE sends third indication information, including: The UE sends a third indication message when the first AI unit meets the first condition; The first condition is either stipulated in the agreement or indicated by the first information.

8. The method according to claim 7, characterized in that, The first condition includes at least one of the following: The SGCS between the first CSI feedback information and the expected CSI feedback information obtained by the UE using the third dataset and the updated first AI unit is greater than the SGCS threshold in the first information. The error between the first CSI feedback information obtained by the UE using the third dataset and the updated first AI unit and the expected CSI feedback information is less than the second threshold in the first information; The updated first AI unit passed the backward testing.

9. The method according to claim 1, characterized in that, The method further includes: The UE sends a fourth indication information to the network-side device at a first moment. The fourth indication information is used to instruct the network-side device to send the first information. The first information includes at least information related to the target unit update.

10. The method according to claim 1, characterized in that, The method further includes: The UE reports auxiliary information, which includes at least one of the following: Target CSI information; The monitoring information of the target unit estimated by the terminal; The quantized value of the target CSI information; The second CSI feedback information obtained by the UE based on the quantized value of the target CSI information; The UE uses the third CSI feedback information obtained from the reference model.

11. The method according to claim 10, characterized in that, The auxiliary information is used by the network-side device to determine the cause of the target unit's failure or as primary information, or... The auxiliary information is used to trigger the network-side device to send first information to the UE.

12. The method according to any one of claims 1-11, characterized in that, The first information also includes: CSI reporting configuration information is used to instruct the UE to update the first AI unit on the UE side, or to instruct the UE to return to non-AI CSI reporting.

13. The method according to any one of claims 1-12, characterized in that, The first information also includes: Model recognition information; Data set identification information; CSI reports identification information; Monitoring and identification information.

14. The method according to any one of claims 2-13, characterized in that, The expected CSI feedback information is obtained by the network-side device based on the target CSI information or the quantized value of the target CSI information.

15. An information processing method, characterized in that, include: The network-side equipment receives auxiliary information reported by the user equipment (UE); The network-side device determines the reason or first information for whether the target unit is valid or invalid based on the auxiliary information, wherein the target unit is a unit used to process CSI information; The auxiliary information includes at least one of the following: Target CSI information; The monitoring information of the target unit estimated by the terminal; The quantized value of the target CSI information; The second CSI feedback information obtained by the UE based on the quantized value of the target CSI information; The UE uses the third CSI feedback information obtained from the reference model.

16. The method according to claim 15, characterized in that, The causes of target cell failure include at least one of the following: The first AI unit on the UE side failed; The second AI unit of the network-side device failed. A data offset occurs, which indicates that the first data or first dataset obtained in time slot n is offset relative to the second dataset used to obtain the target unit; The error between the expected CSI feedback information and the first CSI feedback information obtained by the first AI unit on the UE side is greater than a first threshold. The quantization level or optimization level of the target unit.

17. The method according to claim 15 or 16, characterized in that, Based on the auxiliary information, the network-side device determines the reason for whether the target unit is valid or invalid, including: If the error between the expected CSI feedback information and the first CSI feedback information obtained by the first AI unit on the UE side is greater than a first threshold, and the error between the first reconstructed CSI information obtained based on the first CSI feedback information and the target CSI information is less than a second threshold, the target unit is determined to be valid. If the error between the expected CSI feedback information and the first CSI feedback information obtained by the first AI unit on the UE side is less than the first threshold, and the error between the first reconstructed CSI information obtained based on the first CSI feedback information and the target CSI information is greater than the second threshold, the cause of the target unit failure is determined to be: data offset occurs, wherein the data offset indicates that the first data or the first dataset obtained in time slot n is offset relative to the second dataset used to obtain the target unit; If the error between the expected CSI feedback information and the first CSI feedback information obtained through the first AI unit on the UE side is greater than the first threshold, and the error between the first reconstructed CSI information obtained based on the first CSI feedback information and the target CSI information is greater than the second threshold, the cause of the target unit failure is determined to be: data offset or failure of the first AI unit on the UE side.

18. The method according to claim 15, characterized in that, The method further includes: The network-side device sends first information to the UE, the first information including at least one of the following: The reason for the failure of the target unit, which is a unit used to process CSI information; Deactivate the instruction information of the target unit; Switch the indication information of the target unit; Information related to the update of the target unit; Information related to the new target unit; The first instruction information is used to instruct the target unit to be updated or optimized: The second indication information is used to indicate the quantization level or optimization level of the target unit.

19. The method according to claim 18, characterized in that, The first information includes at least information related to the target unit update; the information related to the target unit update includes at least one of the following: A third dataset, which includes expected CSI feedback information; The second threshold is the upper limit of the error between the first CSI feedback information obtained by the UE using the updated first AI unit and the expected CSI feedback information; The SGCS threshold is the lower limit of the SGCS between the first CSI feedback information obtained by the UE using the updated first AI unit and the expected CSI feedback information.

20. The method according to claim 18, characterized in that, If the cause of the target cell failure is a data offset, the first information includes at least one of the following: Switch the indication information of the target unit; Information related to the new target unit; Used to obtain the second dataset of the target unit.

21. The method according to claim 15, characterized in that, The method further includes: Receive the third indication information sent by the UE; Based on the third indication information, it is determined that the first AI unit has been updated or the updated first AI unit can be activated and used, or that the first AI unit is in a pending activation state, or that the first AI unit has been updated or the updated first AI unit has been released or is in an unavailable state.

22. The method according to claim 18, characterized in that, The method further includes: Receive the fourth indication information sent by the UE; According to the fourth instruction information, the first information is sent to the UE, and the first information includes at least information related to the target unit update.

23. The method according to claim 18, characterized in that, The first information also includes: CSI reporting configuration information is used to instruct the UE to update the first AI unit used by the UE, or to instruct the UE to return to non-AI CSI reporting.

24. The method according to any one of claims 18-23, characterized in that, The first information also includes: Model recognition information; Data set identification information; CSI reports identification information; Monitoring and identification information.

25. The method according to any one of claims 16-24, characterized in that, The method further includes: The desired CSI feedback information is obtained based on the target CSI information or the quantized value of the target CSI information.

26. An information processing device, characterized in that, include: A first receiving module is configured to receive first information, the first information including at least one of the following: The reason for the failure of the target unit, which is a unit used to process CSI information; Deactivate the instruction information of the target unit; Switch the indication information of the target unit; Information related to the update of the target unit; Information related to the new target unit; The first instruction information is used to instruct the target unit to be updated or optimized: The second indication information is used to indicate the quantization level or optimization level of the target unit.

27. The apparatus according to claim 26, characterized in that, The device further includes: The first sending module is used to send third indication information, which indicates that the first AI unit has been updated or the updated first AI unit can be activated and used; or the third indication information indicates that the first AI unit is in a pending activation state; or the third indication information indicates that the first AI unit has been updated or the updated first AI unit has been released or is in an unavailable state.

28. The apparatus according to claim 26, characterized in that, The device further includes: The second sending module is used to send fourth indication information to the network-side device at a first moment. The fourth indication information is used to instruct the network-side device to send the first information. The first information includes at least information related to the update of the target unit.

29. The apparatus according to claim 26, characterized in that, The device further includes: The first reporting module is used to report auxiliary information, which includes at least one of the following: Target CSI information; The monitoring information of the target unit estimated by the terminal; The quantized value of the target CSI information; The second CSI feedback information obtained by the UE based on the quantized value of the target CSI information; The UE uses the third CSI feedback information obtained from the reference model.

30. An information processing device, characterized in that, include: The second receiving module is used to receive auxiliary information reported by the user equipment (UE). The first determining module is used to determine, based on the auxiliary information, the reason for or first information of whether the target unit is effective or ineffective, wherein the target unit is a unit used to process CSI information; The auxiliary information includes at least one of the following: Target CSI information; The monitoring information of the target unit estimated by the terminal; The quantized value of the target CSI information; The second CSI feedback information obtained by the UE based on the quantized value of the target CSI information; The UE uses the third CSI feedback information obtained from the reference model.

31. The apparatus according to claim 30, characterized in that, The device further includes: The third transmitting module is configured to transmit first information to the UE, the first information including at least one of the following: The reason for the failure of the target unit, which is a unit used to process CSI information; Deactivate the instruction information of the target unit; Switch the indication information of the target unit; Information related to the update of the target unit; Information related to the new target unit; The first instruction information is used to instruct the target unit to be updated or optimized: The second indication information is used to indicate the quantization level or optimization level of the target unit.

32. The apparatus according to claim 30, characterized in that, The device further includes: The third receiving module is used to receive the third indication information sent by the UE; The second determining module is configured to determine, based on the third indication information, whether the first AI unit has been updated or the updated first AI unit can be activated, or whether the first AI unit is in a pending activation state, or whether the first AI unit has been updated or the updated first AI unit has been released or is in an unavailable state.

33. The apparatus according to claim 31, characterized in that, The device further includes: The fourth receiving module is used to receive the fourth indication information sent by the UE; The fourth sending module is configured to send the first information to the UE according to the fourth indication information, wherein the first information includes at least information related to the target unit update.

34. A user equipment, characterized in that, It includes a processor and a memory, the memory storing a program or instructions that can run on the processor, the program or instructions being executed by the processor to implement the steps of the information processing method as described in any one of claims 1 to 14.

35. A network-side device, characterized in that, It includes a processor and a memory, the memory storing a program or instructions that can run on the processor, the program or instructions being executed by the processor to implement the steps of the information processing method as described in any one of claims 15 to 25.

36. 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 information processing method as described in any one of claims 1-14, or implement the steps of the information processing method as described in any one of claims 15-25.

Images