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

Abstract

The present application relates to the field of communications, and discloses an information processing method and apparatus, a user equipment, and a network side device. The information processing method comprises: a user equipment receives first information, wherein the first information comprises at least one of the following: the reason for a failure of a target unit, the target unit being a unit used for processing channel state information (CSI); indication information for deactivating the target unit; indication information for switching the target unit; information related to target unit update; information related to a new target unit; first indication information, used for indicating update or optimization of the target unit; and second indication information, used for indicating a quantization level or an optimization level of the target unit.

Description

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

[0001] Cross-reference to Related Applications

[0002] This application claims priority to the Chinese patent application No. 202411094455.4, filed on August 9, 2024, and entitled "Information processing method and device, user equipment and network side equipment", the content of which is incorporated herein by reference in its entirety. TECHNICAL FIELD

[0003] The present application belongs to the field of communication technology, and specifically relates to an information processing method, device, user equipment and network side equipment. BACKGROUND

[0004] In related technologies, CSI information can be processed by an artificial intelligence (AI) method or a non-artificial intelligence method. When the AI method is used to process the CSI information, a user equipment (UE) processes target CSI information by using an AI model, and sends obtained CSI feedback information to a network side equipment (e.g., a serving base station). The network side equipment processes the CSI feedback information by using an AI model for the next step.

[0005] However, the AI model on the UE side and the AI model on the network side equipment side can fail. Related technologies do not provide a CSI information processing scheme in the case of model failure. SUMMARY

[0006] Embodiments of the present application provide an information processing method, device, user equipment and network side equipment. The user equipment can determine whether a target unit (AI model) is invalid according to first information, and can determine the cause of the invalidity of the target unit in the case of invalidity of the target unit, and can determine the subsequent behavior of the UE and the network side equipment after the invalidity of the target unit, thereby realizing the processing of the CSI information in the case of invalidity of the target unit.

[0007] In a first aspect, an information processing method is provided, which is executed by a user equipment, and the method comprises:

[0008] The user equipment UE receives first information, and the first information comprises at least one of the following:

[0009] a cause of invalidity of a target unit, wherein the target unit is a unit for processing channel state (CSI) information;

[0010] deactivating the target unit;

[0011] switching indication information of the target unit;

[0012] information related to updating of the target unit;

[0013] information related to a new target unit;

[0014] first indication information, used for indicating updating or optimization of the target unit;

[0015] second indication information, used for indicating a quantization level or an optimization level of the target unit.

[0016] In a second aspect, an information processing method is provided, executed by a network side device, and the method comprises:

[0017] The network side device receives auxiliary information reported by a user equipment (UE);

[0018] The network side device determines whether a target unit is valid or a reason for invalidation of the target unit according to the auxiliary information, the target unit being a unit used for processing of channel state information (CSI) information;

[0019] The auxiliary information comprises at least one of:

[0020] target CSI information;

[0021] monitoring information of the target unit estimated by a terminal;

[0022] a quantization value of the target CSI information;

[0023] second CSI feedback information obtained by the UE according to the quantization value of the target CSI information;

[0024] third CSI feedback information obtained by the UE using a reference model.

[0025] In a third aspect, an information processing apparatus is provided, and the apparatus comprises:

[0026] A first receiving module is configured to receive first information, the first information comprising at least one of:

[0027] a reason for invalidation of a target unit, the target unit being a unit used for processing of CSI information;

[0028] deactivating the target unit;

[0029] switching indication information of the target unit;

[0030] information related to updating of the target unit;

[0031] information related to a new target unit;

[0032] The first indication information is used for indicating whether the target unit is updated or optimized.

[0033] The second indication information is used for indicating a quantization level or an optimization level of the target unit.

[0034] In a fourth aspect, an information processing apparatus is provided, and the apparatus comprises:

[0035] The second receiving module is configured to receive auxiliary information reported by a user equipment (UE);

[0036] The first determining module is configured to determine, according to the auxiliary information, whether a target unit is valid or a reason for invalidity of the target unit or first information, the target unit being a unit used for processing CSI information.

[0037] The auxiliary information comprises at least one of:

[0038] Target CSI information;

[0039] Monitoring information of the target unit estimated by a terminal;

[0040] A quantization value of the target CSI information;

[0041] Second CSI feedback information obtained by the UE according to the quantization value of the target CSI information;

[0042] Third CSI feedback information obtained by the UE using a reference model.

[0043] In a fifth aspect, a user equipment is provided, and the user equipment comprises a processor and a memory, the memory storing programs or instructions executable on the processor, and the programs or instructions, when executed by the processor, implement steps of the information processing method according to the first aspect.

[0044] In a sixth aspect, a network side equipment is provided, and the network side equipment comprises a processor and a memory, the memory storing programs or instructions executable on the processor, and the programs or instructions, when executed by the processor, implement steps of the information processing method according to the second aspect.

[0045] In a seventh aspect, a readable storage medium is provided, and the readable storage medium stores programs or instructions, and the programs or instructions, when executed by a processor, implement steps of the information processing method according to the first aspect or implement steps of the information processing method according to the second aspect.

[0046] In an eighth aspect, a wireless communication system is provided, including a user equipment and a network side device, the user equipment being configured to perform the steps of the information processing method according to the first aspect, and the network side device being configured to perform the steps of the information processing method according to the second aspect.

[0047] In a ninth aspect, a chip is provided, including a processor and a communication interface, the communication interface being coupled to the processor, and the processor being configured to execute a program or an instruction to implement the information processing method according to the first aspect or the information processing method according to the second aspect.

[0048] In a tenth aspect, a computer program / program product is provided, stored in a storage medium, and executed by at least one processor to implement the steps of the information processing method according to the first aspect or the information processing method according to the second aspect.

[0049] In the embodiments of the present application, the user equipment receives first information, the first information including at least one of the following: a reason for invalidation of a target unit, the target unit being a unit for processing CSI information; indication information for deactivating the target unit; indication information for switching the target unit; information related to target unit updating; information related to a new target unit; first indication information for indicating updating or optimization of the target unit; and second indication information for indicating a quantization level or an optimization level of the target unit. In this way, the user equipment can determine whether the target unit (AI model) is invalid according to the first information, and can determine the reason for invalidation of the target unit in the case of invalidation of the target unit, and can determine subsequent behaviors of the UE and the network side device after invalidation of the target unit, thereby implementing CSI information processing in the case of invalidation of the target unit. BRIEF DESCRIPTION OF DRAWINGS

[0050] FIG. 1 is a block diagram of a wireless communication system to which embodiments of the present application can be applied;

[0051] FIG. 2 is a schematic diagram of a neural network in embodiments of the present application;

[0052] FIG. 3 is a schematic diagram of a neuron of a neural network in embodiments of the present application;

[0053] FIG. 4 is a schematic diagram of CSI information processing by a user equipment and a network side device in embodiments of the present application;

[0054] FIG. 5 is a flowchart of an information processing method in embodiments of the present application;

[0055] FIG. 6 is an implementation flowchart of an information processing method in embodiments of the present application;

[0056] FIG. 7 is an implementation flowchart of another information processing method in the embodiments of the present application;

[0057] FIG. 8 is an implementation flowchart of still another information processing method in the embodiments of the present application;

[0058] FIG. 9 is a flowchart of another information processing method in the embodiments of the present application;

[0059] FIG. 10 is a schematic diagram of an information processing apparatus in the embodiments of the present application;

[0060] FIG. 11 is a schematic diagram of another information processing apparatus in the embodiments of the present application;

[0061] FIG. 12 is a schematic diagram of a structure of a communication device in the embodiments of the present application;

[0062] FIG. 13 is a schematic diagram of a structure of a user equipment in the embodiments of the present application;

[0063] FIG. 14 is a schematic diagram of a structure of a network side device in the embodiments of the present application. DETAILED DESCRIPTION

[0064] The technical solutions in the embodiments of the present application will be clearly described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some of the embodiments of the present application, but not all of them. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art belong to the scope of protection of the present application.

[0065] The terms "first", "second", and the like in the present application are used to distinguish similar objects, and are not used to describe a specific order or sequence. It should be understood that the terms used in this way can be interchanged under appropriate circumstances, so that the embodiments of the present application can be implemented in an order other than that illustrated or described herein, and the objects distinguished by "first", "second" are usually a category, and are not limited to the number of objects, for example, the first object can be one or more. In addition, "or" in the present application means at least one of the connected objects. For example, the protection scope of "A or B" at least covers three schemes, namely, scheme one: including A and not including B; scheme two: including B and not including A; scheme three: including A and B. In addition, the terms "A and / or B", "at least one of A and B", "at least one of A or B" also at least cover the above three schemes, respectively. The character " / " generally represents that the objects before and after are in an "or" relationship.

[0066] The term "indication" in this application can be a direct indication (or explicit indication) or an indirect indication (or implicit indication). The direct indication can be understood as the sender explicitly informing the receiver of specific information, operations to be performed or requested results, etc. in the indication sent by the sender. The indirect indication can be understood as the receiver determining the corresponding information according to the indication sent by the sender, or making a judgment and determining the operations to be performed or the requested results according to the judgment result.

[0067] It is worth noting that the technology described in the embodiments of the present application is not limited to the Long Term Evolution (LTE) / LTE-Advanced (LTE-A) system, but can also be used in other wireless communication systems, such as Code Division Multiple Access (CDMA), Time Division Multiple Access (TDMA), Frequency Division Multiple Access (FDMA), Orthogonal Frequency Division Multiple Access (OFDMA), Single-carrier Frequency-Division Multiple Access (SC-FDMA) or other systems. The terms "system" and "network" in the embodiments of the present application are often used interchangeably, and the described technology can be used in the above-mentioned systems and radio technologies, as well as other systems and radio technologies. The following description describes a New Radio (NR) system for example purposes, and NR terminology is used in most of the following description, but these technologies can also be applied to systems other than the NR system, such as 6th Generation (6G) communication systems. th

[0068] ​FIG. 1 shows a block diagram of a wireless communication system to which embodiments of the present application can be applied. The wireless communication system includes a terminal 11 and a network-side device 12. The terminal 11 can also be referred to as a user equipment (UE). The terminal 11 can be a terminal-side device such as a mobile phone, a tablet personal computer, a laptop computer, a notebook computer, a personal digital assistant, a palm computer, a netbook, an ultra-mobile personal computer (UMPC), a mobile Internet device (MID), an augmented reality (AR) device, a virtual reality (VR) device, a robot, a wearable device, a flight vehicle, a vehicle user equipment (VUE), a shipboard device, a pedestrian user equipment (PUE), a smart home (a home device with a wireless communication function such as a refrigerator, a television, a washing machine, or furniture), a game console, a personal computer (PC), a kiosk, or a self-service machine. The wearable device includes a smart watch, a smart bracelet, a smart earphone, smart glasses, smart jewelry (a smart bracelet, a smart necklace, a smart ring, a smart necklace, a smart anklet, a smart necklace, and the like), a smart wristband, smart clothing, and the like. The vehicle-mounted device can also be referred to as a vehicle-mounted terminal, a vehicle-mounted controller, a vehicle-mounted module, a vehicle-mounted component, a vehicle-mounted chip, or a vehicle-mounted unit. It should be noted that the specific type of the terminal 11 is not limited in the embodiments of the present application. The network-side device 12 can include an access network device or a core network device. The access network device can also be referred to as a radio access network (RAN) device, a radio access network function, or a radio access network unit. The access network device can include a base station, a wireless local area network (WLAN) access point (AP), or a wireless fidelity (WiFi) node.The base station can be referred to as a Node B (NB), an evolved Node B (eNB), a next generation Node B (gNB), a New Radio Node B (NR Node B), an access point, a relay base station (RBS), a serving base station (SBS), a base transceiver station (BTS), a radio base station, a radio transceiver, a basic service set (BSS), an extended service set (ESS), a home Node B (HNB), a home evolved Node B, a transmit / receive point (TRP), a Non-Terrestrial Network (NTN) device (such as a satellite or a high altitude platform station, etc.), or some other suitable terminology in the art, so long as the same technical effect is achieved, and the base station is not limited to a specific technical term. It should be noted that in the embodiments of the present application, only the base station in the NR system is taken as an example for introduction, and the specific type of the base station is not limited.

[0069] The core network device can also be referred to as a core network node, a core network function, or a core network network element, etc., which includes but is not limited to at least one of the following: a mobility management entity (MME), an access and mobility management function (AMF), a session management function (SMF), a user plane function (UPF), a policy control function (PCF), a policy and charging rules function (PCRF), an edge application server discovery function (EASDF), a unified data management (UDM), a unified data repository (UDR), a home subscriber server (HSS), a centralized network configuration (CNC), a network repository function (NRF), a network exposure function (NEF), a local NEF (L-NEF), a binding support function (BSF), an application function (AF), a location management function (LMF), a gateway mobile location center (GMLC), a network data analytics function (NWDAF), a non-terrestrial network (NTN) device (such as a satellite or a high altitude platform station, etc.), and the like.It should be noted that, in the embodiments of the present application, only the core network device in the NR system is taken as an example for introduction, and the specific type of the core network device is not limited. If the name of the core network device mentioned in the embodiments of the present application changes in subsequent protocol versions (for example, 6G), it is also within the protection scope of the present application.

[0070] Optionally, the core network device can be implemented by one or more function modules in one device, or can be implemented by multiple devices together, and the embodiments of the present application do not make specific limitation thereto. It can be understood that the above function modules can be network elements in a hardware device, or software function modules running on a dedicated hardware, or virtualized function modules instantiated on a platform (for example, a cloud platform) and the like.

[0071] In order to facilitate understanding of the technical solutions provided in the present application, the main technical concepts related to the embodiments of the present application are briefly described below.

[0072] Artificial intelligence:

[0073] Artificial intelligence has been widely applied in various fields at present, and there are various implementation ways for AI models, for example, neural network, decision tree, support vector machine, Bayesian classifier and the like. The present application takes the neural network as an example for description, but the specific type of the AI model is not limited. FIG. 2 is a schematic diagram of a neural network, which includes an input layer, a hidden layer and an output layer. Among them, the input layer is responsible for directly receiving input data; the hidden layer is the most important part of the whole neural network, which is used for processing data; and the output layer is used to output the value processed by the whole network. In addition, the neural network is composed of neurons, and a schematic diagram of a neuron is shown in FIG. 3. In FIG. 3, a1, a2, … aK represent inputs, w represents a weight (i.e., a multiplicative coefficient), b represents a bias (i.e., an additive coefficient), z is an intermediate processing result, a is an output result of the neuron, and σ(.) represents an activation function. Common activation functions include Sigmoid (mapping a variable to 0, 1), tanh (translation and contraction of Sigmoid), Rectified Linear Unit (ReLU) and the like.

[0074] The parameters of the neural network are optimized by an optimization algorithm. An optimization algorithm is a class of algorithm that minimizes or maximizes an objective function (also called loss function sometimes). The objective function is usually a mathematical combination of the model parameters and the data. For example, given data X and its corresponding label Y, a neural network model f(.) can be constructed. After the model is obtained, the predicted output f(x) can be obtained according to the input x, and the difference between the predicted value and the true value (f(x)-Y) can be calculated, which is the loss function. The purpose of the optimization algorithm is to find the appropriate W and b to minimize the value of the above loss function. The smaller the loss value is, the closer the model is to the true situation.

[0075] At present, the common optimization algorithm is mainly based on the BP (error Back Propagation) algorithm. The basic idea of the BP algorithm is that the learning process consists of two processes of forward propagation of signals and backward propagation of errors. When the forward propagation is performed, the input sample is transmitted from the input layer to the output layer through the processing of each hidden layer. If the actual output of the output layer does not match the expected output, the backward propagation of errors is performed. The error back propagation is to transmit the output error to the input layer through the hidden layer in a certain form, and distribute the error to all units of each layer, so as to obtain the error signal of each unit, which is used as the basis for correcting the weights of each unit. The process of adjusting the weights of each layer through the forward propagation of signals and the backward propagation of errors is repeated. The process of continuously adjusting the weights is the learning and training process of the network. This process is performed until the error of the network output is reduced to an acceptable level, or until the preset learning times are reached.

[0076] In addition, the optimization algorithm can also include gradient descent (Gradient Descent), stochastic gradient descent (Stochastic Gradient Descent, SGD), mini-batch gradient descent (mini-batch gradient descent), momentum method (Momentum), Nesterov (one of the stochastic gradient descent algorithms with momentum), adaptive gradient descent (ADAptive GRADient descent, Adagrad), Adagrad extension algorithm Adadelta, root mean square prop (root mean square prop, RMSprop), adaptive momentum estimation (Adaptive Moment Estimation, Adam), etc.

[0077] These optimization algorithms, when back-propagating errors, are based on the errors / losses obtained from the loss function, the derivatives / partial derivatives of the current neurons, the learning rate, the previous gradients / derivatives / partial derivatives, and other influences to obtain the gradient, which is then passed to the previous layer.

[0078] Model lifecycle:

[0079] The lifecycle of a model (an AI model / ML model) includes at least one or more of model training, model deployment, model inference, model monitoring, and model updating. Related technologies use AI models to process CSI information, and in the lifecycle of a model, there are cases of model failure. However, related technologies do not provide solutions for determining the cause of model failure and for subsequent behavior of a terminal and a network-side device after model failure.

[0080] Therefore, embodiments of the present application provide an information processing method, apparatus, user equipment, and network-side device. The information processing method includes: receiving, by a user equipment, first information, the first information including at least one of: a cause of failure of a target unit, the target unit being a unit for processing CSI information; indication information for deactivating the target unit; indication information for switching the target unit; information related to updating of the target unit; information related to a new target unit; first indication information for indicating updating or optimization of the target unit; and second indication information for indicating a quantization level or an optimization level of the target unit. In this way, the user equipment can determine whether the target unit (AI model) is failed based on the first information, and can determine the cause of failure of the target unit in the case of failure of the target unit, and can determine subsequent behavior of the UE and the network-side device after failure of the target unit, thereby implementing processing of CSI information in the case of failure of the target unit.

[0081] The information processing method, apparatus, user equipment, and network-side device provided by embodiments of the present application will be described in detail below in conjunction with the accompanying drawings and some embodiments and application scenarios.

[0082] To facilitate understanding of the present application, first, the method for processing CSI information in embodiments of the present application is described. Referring to FIG. 4, FIG. 4 shows a process of processing CSI information by a user equipment and a network-side device. Specifically, an encoder is deployed on the UE side, and a decoder is deployed on the network-side device side. Optionally, the network-side device also has an encoder. The encoder on the UE side and the encoder and the decoder on the network-side device side are all AI-based models. Optionally, the encoder on the UE side can be obtained in the following way: independently acquired by the UE, trained based on the encoder on the network-side device, transmitted by the network-side device, and trained based on the decoder on the network-side device.

[0083] The target CSI information can be obtained based on reference signal measurement, and the target CSI information can be channel information, codebook information, precoding codebook information, or PMI information.

[0084] The UE processes the target CSI information by using an encoder to obtain first CSI feedback information, and the network-side device processes the first CSI feedback information by using a decoder to obtain first reconstructed CSI information. The network-side device can also process the target CSI information by using an encoder to obtain expected CSI feedback information, and process the expected CSI feedback information by using a decoder to obtain second reconstructed CSI information. In addition, the difference between the CSI information is measured based on the target CSI information and the first reconstructed CSI information, or the SGCS converted from the target CSI information and the second reconstructed CSI information.

[0085] When the target units of the UE and the network-side device (such as the encoder on the UE side and the decoder on the network-side device side) are not failed, 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, whether the target units are valid or the reason for failure can be determined based on the similarity (error) between the two CSI information.

[0086] In a first aspect, an information processing method is provided. The method is applied to a user equipment (UE). The method includes the following steps:

[0087] In step S510, the UE receives first information. The first information includes at least one of the following:

[0088] A-1: a reason for failure of a target unit, the target unit being a unit for processing channel state information (CSI) information;

[0089] A-2: indication information for deactivating the target unit;

[0090] A-3: indication information for switching the target unit;

[0091] A-4: information related to target unit updating;

[0092] A-5: information related to a new target unit;

[0093] A-6: first indication information for indicating updating or optimizing the target unit:

[0094] A-7: second indication information, used for indicating a quantization level or an optimization level of the target unit.

[0095] In the embodiments of the present application, the user equipment can be the terminal 11 in FIG. 1, and the example of the terminal 11 can be referred to the foregoing, which will not be described herein.

[0096] The first information can be sent by the network side device, and in some embodiments, the UE receives the first information sent by the network side device in the case that the target unit is invalid. The first information includes at least one of the A-1 to A-7, and the UE determines whether the target unit is invalid, the cause of the invalidity of the target unit, and / or the subsequent behavior of the UE and the network side device after the invalidity of the target unit according to the content included in the first information.

[0097] For the A-1, the UE can determine the cause of the invalidity of the target unit, wherein the target unit includes at least one of the following: an AI unit used by the UE or the network side device to process the CSI information, a reference AI unit of the AI unit used by the UE or the network side device, an AI unit used by the UE, the network side device or a test device in a test, and a reference AI unit of the AI unit used by the UE, the network side device or the test device. In some embodiments, the invalidity of the target unit can be caused by a failure of the target unit, an improper optimization of the target unit, or a data offset.

[0098] In an optional embodiment, the cause of the invalidity of the target unit includes at least one of the following: the invalidity of the target unit on the UE side, an error of the CSI feedback information being greater than a second threshold, and a data offset.

[0099] For the A-2, the state of the target unit includes one or more of the following: being activated, being in an activation pending state, being released, or being in an unusable state, and the network side device can send the UE the indication information for deactivating the target unit, so that the UE activates the target unit according to the indication information for deactivating the target unit, and the UE can process the CSI information based on the activated target unit. Alternatively, the state of the target unit includes an activated state or a deactivated state, so that once the network side device or the terminal determines that the target unit is invalid, the target unit can be deactivated.

[0100] In an optional embodiment, the indication information for deactivating the target unit is used for indicating the deactivation of the target unit. Optionally, 1 bit or X bits are used to indicate the activation or deactivation of the target unit. Optionally, the indication information for deactivating the target unit further includes identification information of the target unit.

[0101] For 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 to-be-processed data are not matched), the network-side device can send, to the UE through the first information, indication information of switching the target unit, and the UE switches the target unit according to the indication information of switching the target unit, so that the UE can subsequently process the CSI information based on the switched target unit.

[0102] In an optional embodiment, the indication information of switching the target unit is used to indicate the switched target unit. Optionally, the indication information of the target unit further includes identification information of the target unit.

[0103] For item A-4, the UE can update the target unit according to information related to target unit updating to obtain an updated target unit. In some embodiments, the information related to target unit updating can be model structure information or model parameter information of the target unit, or a data set, the data set being used to obtain or update the target unit at the terminal side, and optionally, the data set includes at least one or more pieces of expected CSI feedback information.

[0104] In an optional embodiment, the data set includes at least one or more pieces of expected CSI feedback information and target CSI information. When the target unit at the UE side fails due to a fault, the network-side device can send, to the UE through the first information, information related to target unit updating, such as a data set including expected CSI feedback information, and the UE updates the failed target unit based on the data set. In an optional embodiment, the data set includes multiple data, and the data set information includes: a number of data, a format of the data, and expected CSI feedback information and target CSI information corresponding to the number of data.

[0105] For item A-5, the UE can update the target unit according to information related to a new target unit. In some embodiments, the information related to the new target unit can be a new data set, and when the target unit at the UE side fails due to data drift, the network-side device can send, to the UE through the first information, the new data set, and the UE trains (i.e., updates) the target unit according to the new data.

[0106] In an optional embodiment, the information related to the new target unit includes identification information of the target unit, model structure information or model parameter information of the target unit, or data set information used to obtain the target unit, wherein the data set includes multiple data, and the data set information includes: a number of data, a format of the data, and expected CSI feedback information and target CSI information corresponding to the number of data.

[0107] For item A-6, the UE updates or optimizes the target unit according to the indication of the first indication information. For example, when the target unit on the UE side fails, the network side device can send the first indication information to the UE through the first information, and the UE updates or optimizes the target unit after receiving the first indication information.

[0108] For item A-7, the UE determines the quantization level or optimization level of the target unit according to 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 optimized based on a reference model, and 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, thereby obtaining the optimized target unit. For example, the CSI feedback information or the target CSI information is quantized, or the target unit is obtained based on the quantization of the reference model. However, excessive quantization may cause the target unit to fail. Therefore, the quantization level of the target unit is indicated by the second indication information.

[0109] Through the above implementation process, when the CSI information is processed by using the AI method, the user equipment can determine whether the target unit (AI model) fails according to the received first information, and can determine the reason for the failure of the target unit in the case of failure of the target unit, and can determine the subsequent behavior of the UE and the network side device after the failure of the target unit, thereby realizing the processing of the CSI information in the case of failure of the target unit.

[0110] Through the above implementation process, when the CSI information is processed by using the AI method, the user equipment can determine whether the target unit (AI model) fails based on the determination of the UE and the network side device whether the target unit (AI model) fails or the reason for the failure of the target unit (AI model).

[0111] Through the above implementation process, when the CSI information is processed by using the AI method, the user equipment can determine the subsequent behavior of the UE and the network side device based on the deactivation of the target unit, the indication information of the target unit, and the information related to the update of the target unit.

[0112] 1. The following describes the contents contained in the first information in different scenarios:

[0113] In a specific embodiment, the first information at least includes information related to the update of the target unit; the information related to the update of the target unit includes at least one of the following:

[0114] F-1: A third data set, the third data set includes expected CSI feedback information;

[0115] In one embodiment, the third data set includes a plurality of data, and the data set information includes a number of the data, a format of the data, expected CSI feedback information corresponding to the number of the data, and target CSI information.

[0116] In one embodiment, the third data set includes a plurality of data, and each data includes expected CSI feedback information, and optionally, the third data set includes target CSI information corresponding to the expected CSI feedback information.

[0117] F-2 item: a second threshold, the second threshold being an upper limit value of an error between the first CSI feedback information obtained by the UE using the updated first AI unit and the expected CSI feedback information;

[0118] In one embodiment, the information related to the target unit update includes the second threshold, the second threshold being an upper limit value of an error between the first CSI feedback information obtained by the UE using the first AI unit and the expected CSI feedback information.

[0119] In one embodiment, the information related to the target unit update includes the second threshold, the second threshold being an error threshold between the first CSI feedback information obtained by the UE using the first AI unit and the expected CSI feedback information.

[0120] F-3 item: an SGCS threshold, the SGCS threshold being a lower limit value of an SGCS between the first CSI feedback information obtained by the UE using the updated first AI unit and the expected CSI feedback information.

[0121] In one embodiment, the information related to the target unit update includes the SGCS threshold, the SGCS threshold being a lower limit value of an SGCS between the first CSI feedback information obtained by the UE using the first AI unit and the expected CSI feedback information.

[0122] In one embodiment, the information related to the target unit update includes the SGCS threshold, the SGCS threshold being a threshold value of an SGCS between the first CSI feedback information obtained by the UE using the first AI unit and the expected CSI feedback information.

[0123] In the embodiments of the present application, in the case that the first AI unit at the UE side is invalid, the first information at least includes information related to target unit updating, and the information related to target unit updating includes at least one of F-1 to F-3; thus, after the UE receives the first information, the UE updates the first AI unit by using the information related to target unit updating in the first information, and judges whether the updated first AI unit meets a condition, 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 an SGCS threshold.

[0124] For F-1, the expected CSI feedback information in the third data set is the expected CSI feedback information associated with the target CSI information, and the UE updates the first AI unit by using the target CSI information and the expected CSI feedback information in the third data set. For example, in the case that the first AI unit is invalid, the UE outputs the target CSI information to the first AI unit, and optimizes the first AI unit according to the error between the feedback information output by the first AI unit and the expected CSI feedback information.

[0125] For F-2, the first AI unit is updated, and 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 it is still considered that the updated first AI unit is still in the invalid state.

[0126] For F-3, the first AI unit is updated, and 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 it is still considered that the updated first AI unit is still in the invalid state.

[0127] In a specific embodiment, in the case that the reason for the target unit being invalid is that the target unit at the terminal side is invalid, the first information includes at least one of the following:

[0128] G-1: indication information of switching the target unit;

[0129] In an optional embodiment, the indication information of switching the target unit is used to indicate the target unit switched. Optionally, the indication information of the target unit further includes identification information of the target unit.

[0130] G-2: information related to a new target unit;

[0131] Specifically, the information related to the new target unit includes one or more of the following: identification information of the target unit, model structure information of the target unit, model parameter information, and dataset information used to obtain the target unit, wherein the dataset includes a plurality of data, and the dataset information includes the number of data, the format of data, expected CSI feedback information corresponding to the number of data, and target CSI information.

[0132] G-3: a second dataset used to obtain the target unit.

[0133] In one embodiment, the second dataset includes a plurality of data, and the dataset information includes the number of data, the format of data, expected CSI feedback information corresponding to the number of data, and target CSI information.

[0134] In the embodiments of the present application, when the target unit is invalid due to data offset, the network side device can directly send the indication information (i.e., G-1) of switching the target unit to the UE through the first information, and the UE switches the target unit (for example, switches to a target unit adapted to the dataset) according to the indication information of switching the target unit, so that the UE can process the CSI information based on the switched target unit subsequently.

[0135] The network side device can also send information related to a new target unit to the UE through the first information (i.e., G-2), wherein the new target unit is a target unit obtained by the network side device based on a new dataset, and the new target unit is adapted to the to-be-processed data on the UE side. After the network side device obtains the new target unit based on the new dataset, the information related to the new target unit is sent to the UE through the first information, and the UE can process the CSI information based on the new target unit subsequently.

[0136] The network side device can also send a second dataset (i.e., G-3) used to obtain the target unit to the UE through the first information, and the second dataset is a dataset adapted to the to-be-processed data on the UE side. The UE can train the target unit based on the second dataset, so as to obtain an effective target unit.

[0137] In the embodiments of the present application, when the target unit is invalid due to data offset, the first information includes at least one of the above G-1 to G-3, so that the UE can perform subsequent behaviors after the target unit is invalid according to at least one of G-1 to G-3 after receiving the first information, and the CSI information can be processed in the case of target unit invalidity.

[0138] In a specific embodiment, the first information further includes:

[0139] CSI reporting configuration information, the CSI reporting configuration information being used for instructing the UE to update the first AI unit on the UE side, or instructing the UE to return to non-AI CSI reporting.

[0140] In the embodiments of the present application, the UE processes the 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 the CSI reporting configuration information, so that the UE can process the CSI information based on the updated first AI unit subsequently. In addition, when the first AI unit fails, the network side device can also instruct the UE to return to non-AI CSI reporting through the CSI reporting configuration information, that is, the UE processes the CSI information in a non-AI manner.

[0141] In an optional embodiment, the CSI reporting configuration information includes indication information of the first AI unit, which is used for instructing the UE to update the first AI unit on the UE side, or instructing the UE to return to non-AI CSI reporting; or the CSI reporting configuration information includes configuration of CSI reporting based on AI or non-AI.

[0142] In a specific implementation, the first information further includes:

[0143] R-1 item: model identification information;

[0144] R-2 item: data set identification information;

[0145] R-3 item: CSI reporting identification information;

[0146] R-4 item: monitoring identification information.

[0147] In the embodiments of the present application, the model identification information is used to identify the target unit, the data set identification information is used to identify the data set, the CSI reporting identification information is used to identify the CSI reporting configuration, and the monitoring identification information is used to identify the monitoring reporting configuration.

[0148] 2. The following describes the execution before the UE receives the first information:

[0149] In a specific implementation, before receiving the first information, the UE further performs the following steps:

[0150] The UE reports auxiliary information, and the auxiliary information includes at least one of the following:

[0151] B-1 item: target CSI information;

[0152] B-2 item: monitoring information of the target unit estimated by the terminal;

[0153] B-3: a quantized value of the target CSI information;

[0154] B-4: second CSI feedback information obtained by the UE according to the quantized value of the target CSI information;

[0155] B-5: third CSI feedback information obtained by the UE using a reference model.

[0156] The assistance information is used by the network side device to determine the cause of the failure of the target unit or the first information, or the assistance information is used to trigger the network side device to send the first information to the UE.

[0157] In some embodiments, the assistance information is used by the network side device to determine the subsequent behavior of the UE in the case of failure of the target unit. For example, deactivating the target unit, updating the target unit, switching the target unit, and falling back to non-AI CSI reporting.

[0158] In the embodiments of the present application, the target CSI information in B-1 can be obtained by the UE by measuring the reference signal, and / or the target CSI information is the input of the first AI unit on the UE side. The UE can send the target CSI information to the network side device through the assistance information, so that the network side device determines the cause of the failure of the target unit or sends the first information to the UE according to the target CSI information.

[0159] For B-2, the terminal-estimated monitoring information of the target unit can include: the terminal-estimated SGCS, and the effectiveness and the degree of effectiveness of the target unit. In some embodiments, the UE itself has the estimation capability of the monitoring information, and when the target unit fails, the UE can estimate the monitoring information of the target unit based on the estimation capability of the monitoring information itself, to obtain the terminal-estimated monitoring information of the target unit. Therefore, the UE sends the terminal-estimated monitoring information of the target unit to the network side device through the assistance information, so that the network side device determines the cause of the failure of the target unit or sends the first information to the UE according to the terminal-estimated monitoring information of the target unit.

[0160] For B-3, the quantized value of the target CSI information represents the quantized information of the target CSI information. In some embodiments, the data amount of the target CSI information is large, and in order to facilitate reporting, the UE performs quantization processing on the target CSI information to reduce the data amount of the reported CSI information. Therefore, the UE also sends the quantized value of the target CSI information to the network side device through the assistance 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.

[0161] For the B-4 item, the second CSI feedback information is obtained by quantizing the target CSI information according to a quantized value of the target CSI information, and then performing target unit-based compression on the quantized value. It can be understood that the second CSI feedback information is a CSI information with a smaller data amount relative to the target CSI information.

[0162] For the B-5 item, 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 effective, the UE obtains third CSI feedback information using the reference model, and sends the third CSI feedback information to the network side device through the reported auxiliary information, so that the network side device can determine whether the reference model is effective according to the third CSI feedback information. If the reference model determined according to the third CSI feedback information is effective, the UE can be instructed to switch to the reference model.

[0163] In an optional embodiment, the UE obtains fourth CSI feedback information using a fifth model, and sends the fourth CSI feedback information to the network side device through the reported auxiliary information, so that the network side device can determine whether the reference model is effective according to the fourth CSI feedback information. If the fifth model determined according to the fourth CSI feedback information is effective, the UE can be instructed to switch to the fifth model.

[0164] Correspondingly, after the UE reports the auxiliary information, the network side device performs the following steps:

[0165] Step C1: The network side device receives the auxiliary information reported by the user equipment UE.

[0166] Step C2: The network side device determines whether the target unit is effective or the reason for the invalidation of the target unit or the first information according to the auxiliary information, the target unit being a unit used for processing CSI information.

[0167] In the embodiments of the present application, the UE reports the auxiliary information to the network side device, and the auxiliary information includes at least one of the B-1 item to the B-5 item, so that the network side device determines the reason for the invalidation of the target unit or sends the first information to the UE according to the auxiliary information after receiving the auxiliary information.

[0168] In a specific implementation, the network side device determines whether the target unit is effective or the reason for the invalidation of the target unit according to the auxiliary information, including:

[0169] In a case where an 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 value, and an 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 value, it is determined that the target unit is effective;

[0170] In a case that 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, it is determined that the cause of the invalidation of the target unit is that data offset occurs, which represents that the first data or the first data set obtained at time slot n is offset relative to the second data set used to obtain the target unit;

[0171] In a case that 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 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, it is determined that the cause of the invalidation of the target unit is that data offset occurs or the first AI unit on the UE side is invalid.

[0172] In the embodiments of the present application, the UE reports the target CSI information and the first CSI feedback information to the network side device through the assistance information, the network side device reconstructs to obtain the first reconstructed CSI information according to the first CSI feedback information, so as to determine whether the target unit is valid or the cause of the invalidation of the target unit according to the target CSI, the first CSI feedback information and the first reconstructed CSI information; wherein the first CSI feedback information is obtained by the UE using the first AI unit on the UE side.

[0173] In a case that the target unit is not invalid, the expected CSI feedback information and the first CSI feedback information are similar, and the similarity (or error) between the expected CSI feedback information and the first CSI feedback information can be used to determine whether the target unit is valid or the cause of the invalidation of the target unit; similarly, in a case that the target unit is not invalid, the first reconstructed CSI information and the target CSI information are also similar, and the similarity (or error) between the first reconstructed CSI information and the target CSI information can be used to determine whether the target unit is valid or the cause of the invalidation of the target unit.

[0174] In this way, the error between the expected CSI feedback information and the first CSI feedback is measured by the first threshold, and the error between the first reconstructed CSI information and the target CSI information is measured by the second threshold; and the cause of the invalidation of the target unit is determined according to the size relationship between the error between the expected CSI feedback information and the first CSI feedback and the first threshold, and according to the size relationship between the error between the first reconstructed CSI information and the target CSI information and the second threshold.

[0175] In some embodiments, when the first AI unit on the UE side is a plurality of models (for example, model 0, model 2, model 3 are deployed on the UE side), the network side device can determine whether the plurality of models are valid or the reason for invalidation.

[0176] In a specific implementation, the expected CSI feedback information is obtained by the network side device according to the target CSI information or the quantized value of the target CSI information.

[0177] In the embodiments of the present application, the UE reports the target CSI information and the quantized value of the target CSI information to the network side device as auxiliary information, and after receiving the auxiliary information, the network side device can obtain the expected CSI feedback information according to the target CSI information, or can obtain the expected CSI feedback information according to the quantized value of the target CSI information.

[0178] In a specific implementation, before receiving the first information, the UE further performs the following steps:

[0179] Step N1: The UE sends fourth indication information to the network side device at the first time, and the fourth indication information is used to instruct the network side device to send the first information, and the first information at least includes information related to target unit update.

[0180] In the embodiments of the present application, in the case that the first AI unit on the UE side is invalid, the UE sends fourth indication information to the network side device at the first time to instruct the network side device to send information at least including information related to target unit update; so that the UE can update the first AI unit based on the information related to target unit update in the first information after receiving the first information. The first time is the time when the UE and the network side device are both idle and communicable.

[0181] 3. The reasons for the invalidation of the target unit are described as follows:

[0182] In a specific implementation, the reasons for the invalidation of the target unit include at least one of the following:

[0183] D-1: The first artificial intelligence (AI) unit on the UE side is invalid;

[0184] D-2: The second AI unit on the network side device side is invalid;

[0185] D-3: Data offset occurs, which represents that the first data or the first data set obtained at time slot n is offset relative to the second data set used to obtain the target unit;

[0186] D-4: an error between expected CSI feedback information and first CSI feedback information obtained by the first AI unit on the UE side is greater than a first threshold value;

[0187] D-5: a quantization level or an optimization level of the target unit.

[0188] In the embodiments of the present application, the reason for the failure of the target unit in the first information includes at least one of the above D-1 to D-5, and the UE can know the reason for the failure of the target unit according to the received first information. The target unit includes the first AI unit on the UE side and the second AI unit on the device side of the network side, and therefore, the failure of the target unit can be the failure of the first AI unit on the UE side (i.e., D-1) or the failure of the second AI unit on the device side of the network side (i.e., D-2).

[0189] For D-3, the failure of the target unit can also be caused by data offset, for example, the target unit is obtained based on a second data set (e.g., trained based on the second data set), and the data corresponding to the data scene A in the second data set is the corresponding data in the training scene. The first data or the first data set is the data used by the terminal in inference, such as the first data or the first data set obtained by the terminal at the current time or at a plurality of time points before the current time. For example, the first data or the first data set obtained by the UE at time slot n is the data corresponding to scene B, and at this time, the first data or the first data set obtained at time slot n is offset relative to the second data set, thereby causing the failure of the target unit. That is, the corresponding data in the training scene and the data used in inference are offset, such as inconsistent or too large deviation, which causes the failure of the target model.

[0190] For D-4, the expected CSI feedback information is obtained by the second AI unit on the device side of the network side, and the first CSI feedback information is obtained by the first AI unit on the UE side. In the case where the target unit (the first AI unit or the second AI unit) is not failed, the expected CSI feedback information and the first CSI feedback information are similar, and therefore when the error between the expected CSI feedback information and the first CSI feedback information is greater than the first threshold value, it is considered that the target unit is failed. At this time, the failure of the target unit refers to the failure of the first AI unit and / or the failure of the second AI unit.

[0191] For D-5, the failure of the target unit can be caused by the quantization level or the optimization level of the target unit. For example, the target unit is obtained based on a reference model, and when the quantization level or the optimization level of the target unit does not meet the requirements, the target unit can be failed.

[0192] In a specific embodiment, the first AI unit on the UE side is determined to be failed in the case where at least one of the following conditions is met:

[0193] E-1: an error between the first CSI feedback information and the expected CSI feedback information is greater than a second threshold in the first information;

[0194] E-2: an SGCS between the first CSI feedback information and the expected CSI feedback information is less than a first SGCS threshold in the first information;

[0195] E-3: an error between first reconstructed CSI information obtained based on the first CSI feedback information and target CSI information is greater than a third threshold;

[0196] E-4: an SGCS between the first reconstructed CSI information obtained based on the first CSI feedback information and the target CSI information is less than a second SGCS threshold;

[0197] E-5: an 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 an error between second reconstructed CSI information obtained based on the expected CSI feedback information and the target CSI information is less than a fifth threshold;

[0198] E-6: an SGCS between the first reconstructed CSI information obtained based on the first CSI feedback information and the target CSI information is less than a third SGCS threshold, and an SGCS between the second reconstructed CSI information obtained based on the expected CSI feedback information and the target CSI information is greater than a fourth SGCS threshold;

[0199] E-7: an 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;

[0200] E-8: an SGCS 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 less than a fifth SGCS threshold.

[0201] In the embodiments of the present application, the first CSI feedback information is obtained based on the target CSI information by using a first AI unit at the UE side; the expected CSI feedback information is obtained based on the target CSI information by using a second AI unit at the network side device side; the first reconstructed CSI information is obtained based on the first CSI feedback information by using the second AI unit at the network side device side; and the second reconstructed CSI information is obtained based on the expected CSI feedback information by using the second AI unit at the network side device side.

[0202] In the case that the target unit (i.e. the first AI unit or the second AI unit) is not failed, 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, whether the first AI unit at the UE side is failed is determined based on the error between the two CSI information.

[0203] 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 means that the difference between the first CSI feedback information and the expected CSI feedback information is large, and it is considered that the first AI unit is failed. The error between the first CSI feedback information and the expected CSI feedback information greater 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 first SGCS threshold in the first information, 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 is less than the first SGCS threshold in the first information.

[0204] For item E-2, SGCS is used as a measure of the difference between the two CSI information. SGCS is an index parameter for measuring 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 means that the difference between the first CSI feedback information and the expected CSI feedback information is large, and it is considered that the first AI unit is failed. The SGCS between the first CSI feedback information and the expected CSI feedback information 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; the network side indicates, or the protocol specifies; optionally, X can be 5, 10, or 20 (2) The average SGCS between the first CSI feedback information and the expected CSI feedback information is less than the first SGCS threshold in the first information.

[0205] For item E-3, when the error between the first reconstructed CSI information and the target CSI information is greater than the third threshold, it means that the difference between the first reconstructed CSI information and the target CSI information is large, and it is considered that the first AI unit is failed.

[0206] 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 means that the difference between the first reconstructed CSI information and the target CSI information is large, and it is considered that the first AI unit of the UE side is invalid.

[0207] For item E-5, when the error of the first reconstructed CSI information and the target CSI information is greater than the fourth threshold, it means that the difference between the first reconstructed CSI information and the target CSI information is large, and it is possible that the first AI unit of the UE side or the second AI unit of the network side device is invalid. Since the error of the second reconstructed CSI information and the target CSI information is less than the fifth threshold, it means that the second AI unit of the network side device is valid, and thus it is determined that the first AI unit is invalid.

[0208] For item E-6, SGCS is used to measure the difference between two CSI information. The SGCS of the first reconstructed CSI information and the target CSI information is less than the third SGCS threshold, which means that the difference between the first reconstructed CSI information and the target CSI information is large, and it is possible that the first AI unit of the UE side or the second AI unit of the network side device is invalid. Since the SGCS of the second reconstructed CSI information and the target CSI information is greater than the fourth SGCS threshold, it means that the second AI unit of the network side device is valid, and thus it is determined that the first AI unit is invalid.

[0209] For item E-7, the error of the first reconstructed CSI information and the second reconstructed CSI information is greater than the sixth threshold, which means that the difference between the first reconstructed CSI information and the second reconstructed CSI information is large, and it is considered that the first AI unit is invalid.

[0210] 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 means that the difference between the first reconstructed CSI information and the second reconstructed CSI information is large, and it is considered that the first AI unit is invalid.

[0211] In a specific embodiment, the first AI unit of the UE side is determined to be invalid when at least one of the following conditions is met:

[0212] 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;

[0213] Item 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;

[0214] O-3: an error between the third reconstructed CSI information obtained based on the second CSI feedback information and the target CSI information is greater than a third threshold value;

[0215] O-4: a SGCS between the third reconstructed CSI information obtained based on the second CSI feedback information and the target CSI information is less than a second SGCS threshold value;

[0216] O-5: an error between the third reconstructed CSI information obtained based on the second CSI feedback information and the target CSI information is greater than a fourth threshold value, and an 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 value;

[0217] O-6: a SGCS between the third reconstructed CSI information obtained based on the second CSI feedback information and the target CSI information is less than a third SGCS threshold value, and a SGCS between the second reconstructed CSI information obtained based on the expected CSI feedback information and the target CSI information is greater than a fourth SGCS threshold value;

[0218] O-7: an 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 a sixth threshold value;

[0219] O-8: a SGCS 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 less than a fifth SGCS threshold value.

[0220] In the embodiments of the present application, the first CSI feedback information is obtained based on the target CSI information by using the first AI unit at the UE side; the expected CSI feedback information is obtained based on the target CSI information by using the second AI unit at the network side device; the first reconstructed CSI information is obtained based on the first CSI feedback information by using the second AI unit at the network side device; and the third reconstructed CSI information is obtained based on the second CSI feedback information by using the second AI unit at the network side device. The second CSI feedback information is obtained based on a quantized value of the target CSI information by using the first AI unit at the UE side.

[0221] In the case where the target unit (i.e. the first AI unit or the second AI unit) is not failed, 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, whether the first AI unit at the UE side is failed is determined based on an error between the two CSI information.

[0222] For 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 means that the difference between the second CSI feedback information and the expected CSI feedback information is large, and it is considered that the first AI unit is invalid. Wherein, the error between the second CSI feedback information and the expected CSI feedback information is greater than the second threshold in the first information includes the following two cases: (1) The error between the second CSI feedback information corresponding to more than X% of the data and the expected CSI feedback information is less than the first SGCS threshold in the first information, X% is set according to the actual situation, network side indication, or protocol stipulation; optionally, X can be 5, 10, or 20 (2) The average error between the corresponding second CSI feedback information and the expected CSI feedback information is less than the first SGCS threshold in the first information.

[0223] For O-2, SGCS is used as a measure of the difference between two CSI information, which is an index parameter for measuring 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 means that the difference between the second CSI feedback information and the expected CSI feedback information is large, and it is considered that the first AI unit is invalid. Wherein, 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 includes the following two cases: (1) The SGCS between the second CSI feedback information corresponding to more than X% of the data and the expected CSI feedback information is less than the first SGCS threshold in the first information; network side indication, or protocol stipulation; optionally, X can be 5, 10, or 20 (2) The average SGCS between the corresponding second CSI feedback information and the expected CSI feedback information is less than the first SGCS threshold in the first information.

[0224] For O-3, when the error between the third reconstructed CSI information and the target CSI information is greater than the third threshold, it means that the difference between the third reconstructed CSI information and the target CSI information is large, and it is considered that the first AI unit is invalid.

[0225] For O-4, SGCS is used as a measure of the difference between two CSI information, and when the SGCS between the third reconstructed CSI information and the target CSI information is less than the second SGCS threshold, it means that the difference between the third reconstructed CSI information and the target CSI information is large, and it is considered that the first AI unit is invalid.

[0226] For the O-5 item, 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, and the first AI unit at the UE side or the second AI unit at the network side device side is likely to be invalid; 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 at the network side device side is valid, and thus it is determined that the first AI unit is invalid.

[0227] For the O-6 item, the SGCS is used as a measure of the difference between two CSI information, and the SGCS between the third reconstructed CSI information and the target CSI information is less than the third SGCS threshold, which indicates that the difference between the third reconstructed CSI information and the target CSI information is large, and the first AI unit at the UE side or the second AI unit at the network side device side is likely to be invalid; since the SGCS between the second reconstructed CSI information and the target CSI information is greater than the fourth SGCS threshold, it indicates that the second AI unit at the network side device side is valid, and thus it is determined that the first AI unit is invalid.

[0228] For the E-7 item, the error between the third reconstructed CSI information and the second reconstructed CSI information is greater than the sixth threshold, which indicates that the difference between the third reconstructed CSI information and the second reconstructed CSI information is large, and it is considered that the first AI unit is invalid.

[0229] For the E-8 item, the SGCS is used as a measure of the difference between two CSI information, and when the SGCS between 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 it is considered that the first AI unit is invalid.

[0230] 4. The following describes the execution of the UE after receiving the first information:

[0231] In a specific embodiment, after receiving the first information, the UE further performs the following steps:

[0232] Step H1: The UE sends third indication information, which is used to represent that the first AI unit is updated or the updated first AI unit can be activated for use; or the third indication information is used to represent that the first AI unit is in an activation pending state; or the third indication information is used to represent that the first AI unit is updated or the updated first AI unit is released or in an unusable state.

[0233] In the embodiment of the present application, in the case that the first AI unit at the UE side is invalid, the UE updates the first AI unit invalidity and sends third indication information to the network side device to inform the network side device of the state of the current first AI unit (for example, the first AI unit is in an activation pending state).

[0234] In some embodiments, the third indication information is further used to represent that the first AI unit can be activated for use; or the third indication information is used to represent that the first AI unit is in a state of being activated; or the third indication information is used to represent that the first AI unit is released or in an unusable state. The state of the first AI unit includes one or more of being activated for use, being in a state of being activated, being released, or being in an unusable state, so that 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 performs the next step of processing according to the state of the first AI unit.

[0235] Correspondingly, the network side device performs the following steps:

[0236] Step J1: receiving the third indication information sent by the UE;

[0237] Step J2: determining, according to the third indication information, that the first AI unit is updated or the updated first AI unit can be activated for use, or determining that the first AI unit is in a state of being activated, or determining that the first AI unit is updated or the updated first AI unit is released or in an unusable state.

[0238] In the embodiments of the present application, the network side device can determine the state of the current first AI unit based on the third indication information, and perform the next step of operation according to the state of the current first AI unit, so that subsequent behaviors can be performed in the case of failure of the first AI unit, and the CSI information can still be processed in the case of failure of the first AI unit.

[0239] In a specific implementation, after receiving the first information, the UE further performs the following steps:

[0240] Step K1: the UE updates the first AI unit based on information related to target unit update;

[0241] Step K2: the UE sends the third indication information in the case that the first AI unit satisfies a first condition; the first condition is agreed by a protocol or indicated by the first information.

[0242] In the embodiments of the present application, the first information includes information related to target unit update, the UE updates the first AI unit based on the information related to target unit update, and sends the third indication information in the case that the first AI unit satisfies a first condition; wherein the first condition is used to judge whether the first AI unit is valid.

[0243] Optionally, the first condition includes at least one of the following:

[0244] M-1: the UE uses the third data set and the updated first AI unit, and the SGCS between the first CSI feedback information obtained and the expected CSI feedback information is greater than the SGCS threshold in the first information;

[0245] M-2: the UE uses the third data set and the updated first AI unit, and the error between the first CSI feedback information obtained and the expected CSI feedback information is less than the second threshold in the first information;

[0246] M-3: the updated first AI unit passes the backward test.

[0247] Specifically, for 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, and it is confirmed that the first AI unit is effective. Wherein, the SGCS between the first CSI feedback information and the expected CSI feedback information being 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 average SGCS between the first CSI feedback information and the expected CSI feedback information is greater than the first SGCS threshold in the first information.

[0248] For 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, and it is confirmed 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 average error between the first CSI feedback information and the expected CSI feedback information is less than the second threshold in the first information.

[0249] For M-3, the network side device or the protocol specifies the test data, and determines the effectiveness information or the monitoring information of the target unit 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.

[0250] In the embodiments of the present application, the effectiveness of the updated first AI unit is determined through at least one of M-1 to M-3, so that the UE feeds back the effective state of the updated first AI unit to the network side device, so that the network side device performs the next step of processing according to the state of the first AI unit.

[0251] The information processing method in the present application is described through the following examples.

[0252] Example One

[0253] Referring to FIG. 6, FIG. 6 is an implementation flowchart of an information processing method in an embodiment of the present application, and the specific steps are as follows:

[0254] Step 1: The UE reports auxiliary information, and the auxiliary information includes at least one of the following: target CSI information; monitoring information of the target unit estimated by the terminal; a quantized value of the target CSI information; second CSI feedback information obtained by the UE according to the quantized value of the target CSI information; third CSI feedback information obtained by the UE using a reference model.

[0255] Step 2: The network side device assists the information, and determines whether the target unit is valid or the reason for invalidation or first information according to the auxiliary information, wherein the target unit is a unit for processing CSI information.

[0256] Step 3: The network side device sends first information to the UE, and the first information includes at least one of the following: a reason for invalidation of the target unit, wherein the target unit is a unit for processing CSI information; indication information for deactivating the target unit; indication information for switching the target unit; information related to target unit updating; information related to a new target unit; first indication information for indicating updating or optimization of the target unit; and second indication information for indicating a quantization level or optimization level of the target unit.

[0257] In the embodiment of the present application, the UE reports auxiliary information to the network side device, so that the network side device can determine the reason for invalidation of the target unit based on the auxiliary information, or trigger the network side device to send first information to the UE. Therefore, the UE can determine whether the target unit is invalid according to the first information, and can determine the reason for invalidation of the target unit in the case of invalidation of the target unit, and can determine the subsequent behavior of the UE and the network side device after invalidation of the target unit, thereby realizing CSI information processing in the case of invalidation of the target unit.

[0258] Example Two

[0259] Referring to FIG. 7, FIG. 7 is an implementation flowchart of another information processing method in an embodiment of the present application, and the specific steps are as follows: It can be understood that when the information processing method is executed, it does not necessarily include all the following steps, and optionally includes one or more of the following steps:

[0260] Step 1: UE reports auxiliary information, the auxiliary information including at least one of the following: target CSI information; monitoring information of the target unit estimated by the terminal; a quantized value of the target CSI information; second CSI feedback information obtained by the UE according to the quantized value of the target CSI information; third CSI feedback information obtained by the UE using a reference model.

[0261] Step 2: the network side device assists the auxiliary information, and determines whether the target unit is valid or the reason for invalidation or first information according to the auxiliary information, the target unit being a unit for processing CSI information.

[0262] Step 3: the network side device sends a first AI unit to be updated indication to the UE.

[0263] Step 4: the UE sends fourth indication information to the network side device at a first time, the fourth indication information being used to indicate that the network side device sends the first information or requests to update the first AI unit, the first information including at least information related to target unit update.

[0264] Step 5: the network side device sends the first information to the UE.

[0265] Step 6: the UE updates the first AI unit based on the information related to target unit update, and sends third indication information in the case that the UE determines that the first AI unit meets a first condition; wherein the first condition is agreed by a protocol or indicated by the first information.

[0266] In the embodiments of the present application, the UE reports auxiliary information to the network side device, so that the network side device can determine the reason for invalidation of the target unit based on the auxiliary information, in the case that the UE determines that the first AI unit is invalid, the UE sends first information including at least information related to target unit update to the network side device, so that the UE updates the first AI unit based on the information related to target unit update, and the state of the updated first AI unit is informed to the network side device through third indication information, so that the network side device can determine the state of the current first AI unit based on the third indication information, and perform the next operation according to the state of the current first AI unit, so that in the case that the first AI unit is invalid, subsequent behaviors can be performed, and the CSI information can still be processed in the case that the first AI unit is invalid.

[0267] Embodiment three

[0268] Referring to the following figure, Fig. 8 is an implementation flowchart of another information processing method in the embodiments of the present application, and the specific steps are as follows:

[0269] Step 1, the UE receives second information, wherein the second information is used to assist the UE to determine the validity of the test or monitoring of the target unit, or to determine the reason for the failure of the target unit by the UE.

[0270] The second information includes at least one of the following Z-1 to Z-3:

[0271] Z-1: performance test data set information.

[0272] In one embodiment, the performance test data set includes a plurality of data, and the data set information includes: the number of data, the format of data, the expected CSI feedback information corresponding to the number of data, and the target CSI information. In one embodiment, the performance test data set includes a plurality of data, and each data includes expected CSI feedback information; optionally, each data includes target CSI information corresponding to the expected CSI feedback information.

[0273] Z-2: reference model information.

[0274] The reference model is used to determine the reconstructed CSI information at the UE side, or the monitoring information of the UE. For example, the validity information of the SGCS model, or the data offset information.

[0275] Z-3: feature information of the data set. The feature information includes: variance, SNR, SINR, etc.

[0276] Step 2, the UE reports the CSI feedback information and / or the first information, such as the reason for the failure of the target unit, the indication information for deactivating the target unit, the indication information for switching the target unit, and the update information of 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.

[0277] In a second aspect, another configuration information sending method is provided, which is applied to a network side device. Referring to FIG. 9, a flowchart of another information processing method provided by an embodiment of the present application is shown. The method can include the following steps:

[0278] Step S910: the network side device receives the auxiliary information reported by the user equipment (UE).

[0279] Step S920: the network side device determines whether the target unit is valid or the reason for the failure of the target unit or the first information according to the auxiliary information, wherein the target unit is a unit for processing CSI information.

[0280] The auxiliary information includes at least one of the following:

[0281] Target CSI information;

[0282] the monitoring information of the target unit estimated by the terminal;

[0283] a quantized value of the target CSI information;

[0284] second CSI feedback information obtained by the UE according to the quantized value of the target CSI information;

[0285] third CSI feedback information obtained by the UE using a reference model.

[0286] In the embodiments of the present application, the network side device can be the core network device or the access network device 12 in FIG. 1. For examples of the network side device 12, please refer to the foregoing description, which will not be repeated here.

[0287] Through the above steps, the network side device can determine whether the target unit is valid or the cause of invalidation of the target unit according to the assistance information, and determine the subsequent behavior of the UE and the network side device after the target unit is invalidated, so as to realize the processing of the CSI information in the case of invalidation of the target unit.

[0288] In a specific embodiment, the cause of invalidation of the target unit includes at least one of the following:

[0289] invalidation of the first AI unit on the UE side;

[0290] invalidation of the second AI unit of the network side device;

[0291] occurrence of data offset, wherein the occurrence of data offset represents that the first data or the first data set obtained at the time slot n is offset relative to the second data set used to obtain the target unit;

[0292] an 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 value;

[0293] a quantization level or an optimization level of the target unit.

[0294] In a specific embodiment, the network side device determines whether the target unit is valid or the cause of invalidation of the target unit according to the assistance information, including:

[0295] in a case where an 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 value, and an 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 value, it is determined that the target unit is valid;

[0296] in a case that an 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 value, and an 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 value, determining that a cause of failure of the target unit is that data offset occurs, the data offset indicating that first data or a first data set obtained at a time slot n is offset relative to a second data set used to obtain the target unit;

[0297] in a case that an 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 the first threshold value, and an 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 value, determining that a cause of failure of the target unit is that data offset occurs or the first AI unit on the UE side fails.

[0298] In a specific embodiment, the method further comprises:

[0299] The network side device sends first information to the UE, and the first information comprises at least one of the following:

[0300] a cause of failure of a target unit, the target unit being a unit for processing CSI information;

[0301] indication information for deactivating the target unit;

[0302] indication information for switching the target unit;

[0303] information related to target unit updating;

[0304] information related to a new target unit;

[0305] first indication information for indicating updating or optimizing the target unit:

[0306] second indication information for indicating a quantization level or an optimization level of the target unit.

[0307] In a specific embodiment, the first information at least comprises information related to target unit updating; the information related to target unit updating comprises at least one of the following:

[0308] a third data set, the third data set comprising expected CSI feedback information;

[0309] a second threshold value, the second threshold value being an upper limit value of an error between first CSI feedback information obtained by the UE using an updated first AI unit and expected CSI feedback information;

[0310] an SGCS threshold, the SGCS threshold being a lower limit value of an SGCS between the first CSI feedback information obtained by the UE using the updated first AI unit and the expected CSI feedback information.

[0311] In a specific implementation, in a case where the target unit fails due to data offset, the first information includes at least one of the following:

[0312] indication information of switching the target unit;

[0313] information related to a new target unit;

[0314] a second data set used to obtain the target unit.

[0315] In a specific implementation, the method further includes:

[0316] receiving third indication information sent by the UE;

[0317] determining, according to the third indication information, that the first AI unit is updated or the updated first AI unit can be activated for use, or determining that the first AI unit is in an activation pending state, or determining that the first AI unit is updated or the updated first AI unit is released or in an unusable state.

[0318] In a specific implementation, the method further includes:

[0319] receiving fourth indication information sent by the UE;

[0320] sending, to the UE, the first information according to the fourth indication information, the first information including at least information related to target unit updating.

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

[0322] CSI reporting configuration information, the CSI reporting configuration information being used to instruct the UE to update the first AI unit used by the UE, or instruct the UE to fall back to non-AI CSI reporting.

[0323] In a specific implementation, the first information further includes:

[0324] model identification information;

[0325] data set identification information;

[0326] CSI reporting identification information;

[0327] monitoring identification information.

[0328] In a specific implementation, the method further includes:

[0329] According to the target CSI information or the quantized value of the target CSI information, the expected CSI feedback information is obtained.

[0330] The information processing method provided in the embodiments of the present application can be executed by an information processing device. In the embodiments of the present application, the information processing device is taken as an example to illustrate the information processing device provided in the embodiments of the present application.

[0331] The information processing device provided in the embodiments of the present application can be a communication device or a component in a communication device, for example, a chip. The communication device can be a terminal, a network side device or a server, etc. For example, the terminal can include, but is not limited to, the types of the terminal 11 listed above, the network side device can include, but is not limited to, the types of the network side device 12 listed above, and the embodiments of the present application do not make specific limitations.

[0332] The information processing device includes a receiving module, a sending module and a processing module. The receiving module, the sending module and the processing module can be implemented by software or hardware. When implemented by hardware, the processing module can be implemented by a processor. For example, the processor can include a general processor, a special purpose processor, etc., such as a central processing unit (CPU), a microprocessor, a digital signal processor (DSP), an artificial intelligent (AI) processor, a graphics processing unit (GPU), an application specific integrated circuit (ASIC), a network processor (NP), a field programmable gate array (FPGA) or other programmable logic devices, a gate circuit, a transistor, a discrete hardware component, etc. The receiving module and the sending module can be implemented by a communication interface, which can include one or more of a transceiver, a pin, a circuit, a bus, a radio frequency unit, etc.

[0333] Specifically, referring to FIG. 10, when the information processing device is a terminal or a component in a terminal, the information processing device 1000 includes:

[0334] The first receiving module 1001 is configured to receive first information, wherein the first information comprises at least one of the following: a reason for failure of a target unit, wherein the target unit is a unit for processing CSI information; indication information for deactivating the target unit; indication information for switching the target unit; information related to target unit updating; information related to a new target unit; first indication information for indicating updating or optimization of the target unit; and second indication information for indicating a quantization level or an optimization level of the target unit.

[0335] The information processing apparatus can determine whether the target unit (AI model) fails according to the first information, and can determine a reason for failure of the target unit in the case of failure of the target unit, and can determine subsequent behaviors performed by the UE and the network-side device after failure of the target unit, thereby realizing CSI information processing in the case of failure of the target unit.

[0336] In a specific embodiment, the reason for failure of the target unit comprises at least one of the following:

[0337] The first artificial intelligence (AI) unit on the UE side fails;

[0338] The second AI unit on the network-side device side fails;

[0339] Data drift occurs, wherein the data drift indicates that first data or a first data set obtained at time slot n is offset relative to a second data set used to obtain the target unit;

[0340] An error between expected CSI feedback information and first CSI feedback information obtained by the first AI unit on the UE side is greater than a first threshold value;

[0341] A quantization level or an optimization level of the target unit.

[0342] In a specific embodiment, the first AI unit on the UE side is determined to fail in the case that at least one of the following is met:

[0343] The error between the first CSI feedback information and the expected CSI feedback information is greater than a second threshold value in the first information;

[0344] A SGCS between the first CSI feedback information and the expected CSI feedback information is less than a first SGCS threshold value in the first information;

[0345] An error between first reconstructed CSI information obtained based on the first CSI feedback information and target CSI information is greater than a third threshold value;

[0346] a first reconstructed CSI information obtained based on the first CSI feedback information has a SGCS with the target CSI information less than a second SGCS threshold value;

[0347] an error of a first reconstructed CSI information obtained based on the first CSI feedback information with the target CSI information is greater than a fourth threshold value, and an error of a second reconstructed CSI information obtained based on the expected CSI feedback information with the target CSI information is less than a fifth threshold value;

[0348] a SGCS of a first reconstructed CSI information obtained based on the first CSI feedback information with the target CSI information is less than a third SGCS threshold value, and a SGCS of a second reconstructed CSI information obtained based on the expected CSI feedback information with the target CSI information is greater than a fourth SGCS threshold value;

[0349] an error of a first reconstructed CSI information obtained based on the first CSI feedback information with a second reconstructed CSI information obtained based on the expected CSI feedback information is greater than a sixth threshold value;

[0350] a SGCS of a first reconstructed CSI information obtained based on the first CSI feedback information with a second reconstructed CSI information obtained based on the expected CSI feedback information is less than a fifth SGCS threshold value.

[0351] In a specific embodiment, the first information comprises at least information related to target unit update; the information related to target unit update comprises at least one of:

[0352] a third data set, the third data set comprising expected CSI feedback information;

[0353] a second threshold value, the second threshold value being an upper limit value of an error between the first CSI feedback information obtained by the UE using the updated first AI unit and the expected CSI feedback information;

[0354] a SGCS threshold value, the SGCS threshold value being a lower limit value of a SGCS between the first CSI feedback information obtained by the UE using the updated first AI unit and the expected CSI feedback information.

[0355] In a specific embodiment, in case that the cause of the target unit failure is that data drift occurs, the first information comprises at least one of:

[0356] indication information of switching the target unit;

[0357] information related to a new target unit;

[0358] a second data set for obtaining the target unit.

[0359] In a specific implementation, the information processing apparatus 1000 further includes:

[0360] The first sending module is configured to send third indication information, where the third indication information is used to represent that the first AI unit is updated or the updated first AI unit can be activated for use, or the third indication information is used to represent that the first AI unit is in an activation pending state, or the third indication information is used to represent that the first AI unit is updated or the updated first AI unit is released or in an unusable state.

[0361] In a specific implementation, the information processing apparatus 1000 further includes:

[0362] The updating module is configured to update the first AI unit based on the information related to the target unit update.

[0363] The first sending module is further configured to send the third indication information when the first AI unit meets a first condition, where the first condition is agreed in a protocol or indicated by the first information.

[0364] In a specific implementation, the first condition includes at least one of the following:

[0365] The SGCS between the first CSI feedback information obtained by the UE using the third data set and the updated first AI unit and the expected CSI feedback information is greater than the SGCS threshold in the first information;

[0366] The error between the first CSI feedback information obtained by the UE using the third data set and the updated first AI unit and the expected CSI feedback information is less than the second threshold in the first information.

[0367] The updated first AI unit passes a backward test.

[0368] In a specific implementation, the information processing apparatus 1000 further includes:

[0369] The second sending module is configured to send, to a network side device, fourth indication information at a first time, where the fourth indication information is used to instruct the network side device to send the first information, and the first information includes at least the information related to the target unit update.

[0370] In a specific implementation, the information processing apparatus 1000 further includes:

[0371] The first reporting module is configured to report auxiliary information, where the auxiliary information includes at least one of the following:

[0372] Target CSI information;

[0373] the target unit estimated by the terminal;

[0374] a quantized value of the target CSI information;

[0375] second CSI feedback information obtained by the UE according to the quantized value of the target CSI information;

[0376] third CSI feedback information obtained by the UE using a reference model.

[0377] In a specific implementation, the assistance information is used by the network-side device to determine a cause of failure of the target unit or the first information, or

[0378] the assistance information is used to trigger the network-side device to send the first information to the UE.

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

[0380] CSI reporting configuration information, the CSI reporting configuration information being used to instruct the UE to update the first AI unit on the UE side, or instruct the UE to fall back to non-AI CSI reporting.

[0381] In a specific implementation, the first information further includes:

[0382] model identification information;

[0383] data set identification information;

[0384] CSI reporting identification information;

[0385] monitoring identification information.

[0386] In a specific implementation, the expected CSI feedback information is obtained by the network-side device according to the target CSI information or the quantized value of the target CSI information.

[0387] The information processing apparatus provided by the embodiments of the present application can implement each process of the information processing method embodiments and achieve the same technical effects. To avoid repetition, the same will not be described here.

[0388] Another information processing method provided by the embodiments of the present application, the execution subject can be another information processing apparatus. In the embodiments of the present application, the information processing method is executed by another information processing apparatus, and the another information processing apparatus provided by the embodiments of the present application is described.

[0389] Embodiments of the present application provide another information processing device. As an example, the information processing device can be a communication device or a component in a communication device, such as a chip. The communication device can be a terminal, a network-side device, a server, or the like. For example, the terminal can include, but is not limited to, the types of terminal 11 listed above, the network-side device can include, but is not limited to, the types of network-side device 12 listed above, and embodiments of the present application do not make specific limitations.

[0390] The information processing device includes a receiving module, a sending module, and a processing module. The receiving module, the sending module, and the processing module can be implemented by software or by hardware. When implemented by hardware, the processing module can be implemented by a processor. For example, the processor can include a general-purpose processor, a special-purpose processor, or the like, such as a central processing unit (CPU), a microprocessor, a digital signal processor (DSP), an artificial intelligent (AI) processor, a graphics processing unit (GPU), an application specific integrated circuit (ASIC), a network processor (NP), a field programmable gate array (FPGA), or other programmable logic devices, a gate circuit, a transistor, a discrete hardware component, or the like. The receiving module and the sending module can be implemented by a communication interface. The communication interface can include one or more of a transceiver, a pin, a circuit, a bus, a radio frequency unit, or the like.

[0391] Referring to FIG. 11, when the information processing device is a network-side device or a component in a network-side device, the information processing device 1100 includes:

[0392] A second receiving module 1101 configured to receive auxiliary information reported by a user equipment (UE);

[0393] A first determining module 1102 configured to determine, according to the auxiliary information, whether a target unit is valid or a cause of invalidity or first information, the target unit being a unit configured to process channel state information (CSI) information;

[0394] The auxiliary information includes at least one of the following:

[0395] Target CSI information;

[0396] Monitoring information of the target unit estimated by the terminal;

[0397] a quantized value of the target CSI information;

[0398] second CSI feedback information obtained by the UE according to the quantized value of the target CSI information;

[0399] third CSI feedback information obtained by the UE using a reference model.

[0400] The information processing apparatus can determine whether the target unit is valid or the cause of invalidity of the target unit according to the assistance information, and determine subsequent behaviors performed by the UE and the network-side device after the target unit is invalid, to realize CSI information processing in the case of invalidity of the target unit.

[0401] In a specific implementation, the cause of invalidity of the target unit includes at least one of the following:

[0402] invalidity of the first AI unit on the UE side;

[0403] invalidity of the second AI unit on the network-side device;

[0404] data offset occurs, and the data offset indicates that first data or a first data set obtained at time slot n is offset relative to a second data set used to obtain the target unit;

[0405] an error between the expected CSI feedback information and first CSI feedback information obtained by the first AI unit on the UE side is greater than a first threshold value;

[0406] a quantized level or an optimization level of the target unit.

[0407] In a specific implementation, the network-side device determines whether the target unit is valid or the cause of invalidity of the target unit according to the assistance information, including:

[0408] in a case where an error between the expected CSI feedback information and first CSI feedback information obtained by the first AI unit on the UE side is greater than a first threshold value, and an error between first reconstructed CSI information obtained based on the first CSI feedback information and target CSI information is less than a second threshold value, it is determined that the target unit is valid;

[0409] in a case where an error between the expected CSI feedback information and first CSI feedback information obtained by the first AI unit on the UE side is less than the first threshold value, and an error between first reconstructed CSI information obtained based on the first CSI feedback information and target CSI information is greater than the second threshold value, it is determined that the cause of invalidity of the target unit is that data offset occurs, and the data offset indicates that first data or a first data set obtained at time slot n is offset relative to a second data set used to obtain the target unit;

[0410] In a case where an 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 the first threshold value, and an 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 value, it is determined that the cause of the target unit failure is that data drift occurs or the first AI unit on the UE side fails.

[0411] In a specific implementation, the information processing apparatus 1100 further includes:

[0412] The third sending module is configured to send first information to the UE, and the first information includes at least one of the following:

[0413] The cause of the target unit failure, the target unit being a unit for processing CSI information;

[0414] Indication information for deactivating the target unit;

[0415] Indication information for switching the target unit;

[0416] Information related to target unit updating;

[0417] Information related to a new target unit;

[0418] First indication information for indicating updating or optimizing the target unit:

[0419] Second indication information for indicating a quantization level or an optimization level of the target unit.

[0420] In a specific implementation, the first information at least includes information related to target unit updating, and the information related to target unit updating includes at least one of the following:

[0421] The third data set includes expected CSI feedback information;

[0422] The second threshold value is an upper limit value of an error between the first CSI feedback information obtained by the UE using the updated first AI unit and the expected CSI feedback information;

[0423] The SGCS threshold value is a lower limit value of SGCS between the first CSI feedback information obtained by the UE using the updated first AI unit and the expected CSI feedback information.

[0424] In a specific implementation, in a case where the cause of the target unit failure is that data drift occurs, the first information includes at least one of the following:

[0425] indicating information of the target unit;

[0426] information related to a new target unit;

[0427] a second data set for obtaining the target unit.

[0428] In a specific embodiment, the information processing apparatus 1100 further comprises:

[0429] a third receiving module configured to receive third indicating information sent by the UE;

[0430] a second determining module configured to determine, according to the third indicating information, that the first AI unit is updated or the updated first AI unit can be activated for use, or determine that the first AI unit is in a state of being activated, or determine that the first AI unit is updated or the updated first AI unit is released or in an unusable state.

[0431] In a specific embodiment, the information processing apparatus 1100 further comprises:

[0432] a fourth receiving module configured to receive fourth indicating information sent by the UE;

[0433] a fourth sending module configured to send, according to the fourth indicating information, the first information to the UE, wherein the first information at least comprises information related to target unit updating.

[0434] In a specific embodiment, the first information further comprises:

[0435] CSI reporting configuration information, wherein the CSI reporting configuration information is used to instruct the UE to update the first AI unit used by the UE, or instruct the UE to return to non-AI CSI reporting.

[0436] In a specific embodiment, the first information further comprises:

[0437] model identification information;

[0438] data set identification information;

[0439] CSI reporting identification information;

[0440] monitoring identification information.

[0441] In a specific embodiment, the information processing apparatus 1100 further comprises:

[0442] an obtaining module configured to obtain the expected CSI feedback information according to target CSI information or a quantized value of the target CSI information.

[0443] The information processing device provided in the embodiments of the present application can realize each process of the information processing method embodiments and achieve the same technical effects. To avoid repetition, details are not described herein.

[0444] As shown in FIG. 12, the embodiments of the present application further provide a communication device 1200, which includes a processor 1201 and a memory 1202. The memory 1202 stores programs or instructions executable on the processor 1201. For example, when the communication device 1200 is a terminal, the programs or instructions, when executed by the processor 1201, realize each step of the above information processing method embodiments and achieve the same technical effects. When the communication device 1200 is a network side device, the programs or instructions, when executed by the processor 1201, realize each step of the above information processing method embodiments and achieve the same technical effects. To avoid repetition, details are not described herein.

[0445] The embodiments of the present application further provide a user device, which includes a processor and a communication interface. The communication interface is coupled to the processor. The processor is configured to execute programs or instructions to realize the steps in the method embodiments of the information processing method shown in FIG. 5. The user device embodiments correspond to the above user device side method embodiments. Each implementation process and implementation manner of the above method embodiments can be applicable to the user device embodiments and achieve the same technical effects. The user device can be the information processing device shown in FIG. 10. Specifically, FIG. 13 is a schematic diagram of a hardware structure of a user device for implementing the embodiments of the present application.

[0446] The user device 13200 includes, but is not limited to, at least part of the components such as a radio frequency unit 1301, a network module 1302, an audio output unit 1303, an input unit 1304, a sensor 1305, a display unit 1306, a user input unit 1307, an interface unit 1308, a memory 1309, and a processor 1310.

[0447] Those skilled in the art can understand that the user device 1300 can further include a power supply (such as a battery) for supplying power to each component. The power supply can be logically connected to the processor 1310 through a power management system, so as to realize functions such as power management, discharge management, and power consumption management through the power management system. The structure of the user device shown in FIG. 13 does not constitute a limitation on the user device. The user device can include more or fewer components than those shown, or combine certain components, or have different arrangement of components, which are not described herein.

[0448] It should be understood that in the embodiments of the present application, the input unit 1304 can include a graphics processor 13041 and a microphone 13042, and the graphics processor 13041 processes image data of a still picture or a video obtained by an image capture device (such as a camera) in a video capture mode or an image capture mode. The display unit 1306 can include a display panel 13061, which can be configured in the form of a liquid crystal display, an organic light-emitting diode, etc. The user input unit 1307 includes at least one of a touch panel 13071 and other input devices 13072. The touch panel 13071 is also called a touch screen. The touch panel 13071 can include two parts of a touch detection device and a touch controller. The other input devices 13072 can include, but are not limited to, a physical keyboard, function keys (such as volume control keys, on-off keys, etc.), a trackball, a mouse, a joystick, and the like, which will not be described here.

[0449] In the embodiments of the present application, after the radio frequency unit 1301 receives the downlink data from the network side device, it can be transmitted to the processor 1310 for processing. In addition, the radio frequency unit 1301 can send uplink data to the network side device. Generally, the radio frequency unit 1301 includes, but is not limited to, an antenna, an amplifier, a transceiver, a coupler, a low noise amplifier, a duplexer, etc.

[0450] The memory 1309 can be used to store software programs or instructions and various data. The memory 1309 can mainly include a first storage area storing programs or instructions and a second storage area storing data, wherein the first storage area can store an operating system, application programs or instructions required by at least one function (such as a sound playing function, an image playing function, etc.), and the like. In addition, the memory 1309 can include a volatile memory or a non-volatile memory. The non-volatile memory can be a Read-Only Memory (ROM), a Programmable ROM (PROM), an Erasable PROM (EPROM), an Electrically EPROM (EEPROM), or a flash memory. The volatile memory can be a Random Access Memory (RAM), a Static RAM (SRAM), a Dynamic RAM (DRAM), a Synchronous DRAM (SDRAM), a Double Data Rate SDRAM (DDR SDRAM), an Enhanced SDRAM (ESDRAM), a Synch link DRAM (SLDRAM), and a Direct Rambus RAM (DRRAM). The memory 1309 in the embodiments of the present application includes but is not limited to these and any other suitable types of memory.

[0451] The processor 1310 can include one or more processing units; optionally, the processor 1310 integrates an application processor and a modem processor, wherein the application processor mainly processes operations related to an operating system, a user interface, and an application program, and the modem processor mainly processes wireless communication signals, such as a baseband processor. It can be understood that the above-mentioned modem processor can also not be integrated into the processor 1310.

[0452] The radio frequency unit 1301 is configured to receive first information, wherein the first information includes at least one of the following: a reason for invalidation of a target unit, the target unit being a unit for processing CSI information; indication information for deactivating the target unit; indication information for switching the target unit; information related to target unit updating; information related to a new target unit; first indication information for indicating updating or optimization of the target unit; second indication information for indicating a quantization level or an optimization level of the target unit.

[0453] In this way, the user equipment can determine whether the target unit (AI model) is invalid according to the first information, and determine the cause of the invalidation of the target unit in the case of invalidation of the target unit, and determine the subsequent behavior of the UE and the network side equipment after the invalidation of the target unit, to realize the CSI information processing in the case of invalidation of the target unit.

[0454] It can be understood that the implementation process of each implementation manner mentioned in the embodiment can refer to the related description of the information processing method of the method embodiment, and achieve the same or corresponding technical effects. To avoid repetition, it will not be repeated here.

[0455] The embodiment of the application also provides a network side equipment, which comprises a processor and a communication interface, the communication interface is coupled with the processor, and the processor is used to run programs or instructions to realize the steps of the method embodiment as shown in FIG. 9. The network side equipment embodiment corresponds to the network side equipment method embodiment described above, and each implementation process and implementation manner of the method embodiment described above can be applied to the network side equipment embodiment, and the same technical effects can be achieved.

[0456] Specifically, the embodiment of the application also provides a network side equipment. As shown in FIG. 14, the network side equipment 1400 comprises a processor 1401, a network interface 1402 and a memory 1403. The network side equipment can be the information processing device shown in FIG. 11. Wherein, the network interface 1402 is, for example, a common public radio interface (common public radio interface, CPRI).

[0457] Specifically, the network side equipment 1400 of the embodiment of the application further comprises instructions or programs stored on the memory 1403 and executable on the processor 1401. The processor 1401 invokes the instructions or programs in the memory 1403 to execute the functions of each module of the information processing device shown in FIG. 11, and achieve the same technical effects. To avoid repetition, it will not be repeated here.

[0458] The embodiment of the application also provides a readable storage medium, which stores programs or instructions. When the programs or instructions are executed by the processor, each process of the above-mentioned information processing method embodiment is realized, and the same technical effects can be achieved. To avoid repetition, it will not be repeated here.

[0459] The processor is the processor in the terminal described in the above embodiments. The readable storage medium includes a computer readable storage medium, such as a computer readable memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc. In some examples, the readable storage medium can be a non-transitory readable storage medium.

[0460] The chip provided by the embodiment of the present application comprises a processor and a communication interface, the communication interface is coupled with the processor, the processor is used to run programs or instructions, realizes the processes of the information processing method embodiments, and can achieve the same technical effects. To avoid repetition, details are not described here.

[0461] It should be understood that the chip mentioned in the embodiment of the present application can also be referred to as a system chip, a system chip, a chip system or a system on chip, etc.

[0462] The embodiment of the present application further provides a computer program / program product stored in a storage medium, which is executed by at least one processor to realize the processes of the information processing method embodiments and can achieve the same technical effects. To avoid repetition, details are not described here.

[0463] The embodiment of the present application further provides a wireless communication system, comprising: a user equipment and a network side equipment, the user equipment can be used to execute the steps of the information processing method of the user equipment side as described above, and the network side equipment can be used to execute the steps of the information processing method of the network equipment side as described above.

[0464] It should be noted that in this paper, the terms "include", "contain" or any other variants thereof are intended to cover non-exclusive inclusion, so that the process, method, article or device including a series of elements not only includes those elements, but also includes other elements not explicitly listed or inherent to such process, method, article or device. Without more limitations, the element defined by the statement "includes a" does not exclude the presence of another identical element in the process, method, article or device including the element. In addition, it should be pointed out that the scope of the method and device in the present application is not limited to the order of functions shown or discussed, but can also include functions performed in a substantially simultaneous manner or in reverse order according to the functions involved, for example, the described method can be performed in an order different from that described, and various steps can also be added, omitted or combined. In addition, the features described with reference to certain examples can be combined in other examples.

[0465] From the above description of the embodiments, those skilled in the art can clearly understand that the above embodiment method can be realized by means of computer software product and general hardware platform, of course, it can also be realized by hardware. The computer software product is stored in a storage medium (such as ROM, RAM, magnetic disc, optical disc, etc.), which includes a plurality of instructions for making terminal or network side equipment execute the method described in each embodiment of the present application.

[0466] The embodiments of the present application are described above with reference to the accompanying drawings, but the present application is not limited to the above-described specific embodiments, and the above-described specific embodiments are merely illustrative, but not restrictive, and a person of ordinary skill in the art can make many forms of embodiments under the inspiration of the present application without departing from the purpose of the present application and the scope protected by the claims, and these embodiments all belong to the protection of the present application.

Claims

1. An information processing method comprising: receiving, by a user equipment (UE), first information, the first information comprising at least one of: a cause of a failure of a target unit for processing channel state information (CSI) information; indication information to deactivate the target unit; indication information to switch the target unit; information related to a target unit update; information related to a new target unit; first indication information to indicate an update or optimization of the target unit; and second indication information to indicate a quantization level or an optimization level of the target unit.

2. The method of claim 1, wherein, The cause of the failure of the target unit comprises at least one of: a failure of a first artificial intelligence (AI) unit at a UE side; a failure of a second AI unit at a network side device side; an occurrence of a data drift, the occurrence of the data drift indicating that first data or a first data set obtained at a time slot n is drifted relative to a second data set used to obtain the target unit; an error between expected CSI feedback information and first CSI feedback information obtained by the first AI unit at the UE side is greater than a first threshold value; a quantization level or an optimization level of the target unit.

3. The method of claim 1 or 2, wherein, The first AI unit at the UE side is determined to fail when at least one of: the error between the first CSI feedback information and the expected CSI feedback information is greater than a second threshold value in the first information; a signal to geometry channel state (SGCS) between the first CSI feedback information and the expected CSI feedback information is less than a first SGCS threshold value in the first information; an error between first reconstructed CSI information obtained based on the first CSI feedback information and target CSI information is greater than a third threshold value; an SGCS between the first reconstructed CSI information obtained based on the first CSI feedback information and the target CSI information is less than a second SGCS threshold value; 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 value, and an error between second reconstructed CSI information obtained based on the expected CSI feedback information and the target CSI information is less than a fifth threshold value; the SGCS between the first reconstructed CSI information obtained based on the first CSI feedback information and the target CSI information is less than a third SGCS threshold value, and an SGCS between the second reconstructed CSI information obtained based on the expected CSI feedback information and the target CSI information is greater than a fourth SGCS threshold value; an 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 value; and an SGCS 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 less than a fifth SGCS threshold value.

4. The method of claim 1, wherein, The first information comprises at least information related to a target unit update, and the information related to the target unit update comprises at least one of: a third data set comprising the expected CSI feedback information. a second threshold, the second threshold being an upper limit value of an error between the first CSI feedback information obtained by the UE using the updated first AI unit and the expected CSI feedback information; an SGCS threshold, the SGCS threshold being a lower limit value of an 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 of claim 1, wherein, In a case where the target unit failure is caused by data offset, the first information comprises at least one of the following: indication information of switching the target unit; information related to a new target unit; a second data set used to obtain the target unit.

6. The method of claim 1, wherein, The method further comprises: The UE sends third indication information, the third indication information being used to represent that the first AI unit is updated or that the updated first AI unit can be activated for use; or the third indication information being used to represent that the first AI unit is in an activation pending state; or the third indication information being used to represent that the first AI unit is updated or that the updated first AI unit is released or in an unusable state.

7. The method of claim 6, wherein, Before the UE sends the third indication information, the method further comprises: The UE updates the first AI unit based on the information related to the target unit update; The UE sending the third indication information comprises: The UE sends the third indication information in a case where the first AI unit satisfies a first condition. The first condition is agreed by a protocol or indicated by the first information.

8. The method of claim 7, wherein, The first condition comprises at least one of the following: an SGCS between the first CSI feedback information obtained by the UE using a third data set and the updated first AI unit and the expected CSI feedback information is greater than the SGCS threshold in the first information; an error between the first CSI feedback information obtained by the UE using the third data set 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 passes a backward test.

9. The method of claim 1, wherein, The method further comprises: The UE sends fourth indication information to a network side device at a first time, the fourth indication information being used to instruct the network side device to send the first information, the first information comprising at least the information related to the target unit update.

10. The method of claim 1, wherein, The method further comprises: The UE reports auxiliary information, the auxiliary information comprising at least one of the following: target CSI information; monitoring information of the target unit estimated by the terminal; a quantized value of the target CSI information; second CSI feedback information obtained by the UE according to the quantized value of the target CSI information; third CSI feedback information obtained by the UE using a reference model.

11. The method of claim 10, wherein, The auxiliary information is used for the network side device to determine a 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.

12. The method of any one of claims 1-11, wherein, The first information further comprises: CSI reporting configuration information, the CSI reporting configuration information being used to instruct the UE to update the first AI unit on the UE side, or instruct the UE to fall back to non-AI CSI reporting.

13. The method of any one of claims 1-12, wherein, The first information further comprises: Model identification information; Dataset identification information; CSI reporting identification information; Monitoring identification information.

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

15. An information processing method, comprising: a network side device receiving auxiliary information reported by a user equipment (UE); the network side device determining whether a target unit is valid or a cause of invalidity of the target unit or first information according to the auxiliary information, the target unit being a unit for processing CSI information; the auxiliary information comprising at least one of: target CSI information; monitoring information of the target unit estimated by a terminal; a quantized value of the target CSI information; second CSI feedback information obtained by the UE according to the quantized value of the target CSI information; third CSI feedback information obtained by the UE using a reference model.

16. The method of claim 15, wherein, The cause of invalidity of the target unit comprises at least one of: invalidity of a first AI unit on the UE side; invalidity of a second AI unit on the network side device; data offset, the data offset indicating that first data or a first dataset obtained at a time slot n is offset relative to a second dataset used to obtain the target unit; an error between expected CSI feedback information and first CSI feedback information obtained by the first AI unit on the UE side is greater than a first threshold value; a quantization level or an optimization level of the target unit.

17. The method of claim 15 or 16, wherein, The network side device determining whether the target unit is valid or the cause of invalidity of the target unit according to the auxiliary information comprises: in a case where an error between expected CSI feedback information and first CSI feedback information obtained by the first AI unit on the UE side is greater than a first threshold value, and an error between first reconstructed CSI information obtained based on the first CSI feedback information and target CSI information is less than a second threshold value, determining that the target unit is valid; in a case where an error between expected CSI feedback information and first CSI feedback information obtained by the first AI unit on the UE side is less than the first threshold value, and an error between first reconstructed CSI information obtained based on the first CSI feedback information and target CSI information is greater than the second threshold value, determining that a cause of invalidity of the target unit is data offset, the data offset indicating that first data or a first dataset obtained at a time slot n is offset relative to a second dataset used to obtain the target unit; in a case where an error between expected CSI feedback information and first CSI feedback information obtained by the first AI unit on the UE side is greater than the first threshold value, and an error between first reconstructed CSI information obtained based on the first CSI feedback information and target CSI information is greater than the second threshold value, determining that a cause of invalidity of the target unit is data offset or invalidity of the first AI unit on the UE side.

18. The method of claim 15, wherein, The method further comprises: the network side device sending first information to the UE, the first information comprising at least one of: a cause of invalidity of the target unit, the target unit being a unit for processing CSI information; indication information for deactivating the target unit; indication information for switching the target unit; information related to target unit updating; information related to a new target unit; first indication information for indicating updating or optimizing the target unit; second indication information for indicating a quantization level or an optimization level of the target unit.

19. The method of claim 18, wherein, The first information at least includes information related to target unit updating, and the information related to target unit updating includes at least one of: a third data set including expected CSI feedback information; a second threshold value, which is an upper limit value of an error between first CSI feedback information obtained by the UE using the updated first AI unit and the expected CSI feedback information; an SGCS threshold value, which is a lower limit value of an 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 of claim 18, wherein, In a case where a reason for target unit failure is data drift, the first information includes at least one of: indication information for switching the target unit; information related to a new target unit; a second data set for obtaining the target unit.

21. The method of claim 15, wherein, The method further includes: receiving third indication information sent by the UE; determining, according to the third indication information, that the first AI unit is updated or the updated first AI unit can be activated for use, or determining that the first AI unit is in an activation pending state, or determining that the first AI unit is updated or the updated first AI unit is released or in an unusable state.

22. The method of claim 18, wherein, The method further includes: receiving fourth indication information sent by the UE; sending, to the UE, the first information including at least information related to target unit updating, according to the fourth indication information.

23. The method of claim 18, wherein, The first information further includes: CSI reporting configuration information for indicating the UE to update the first AI unit used by the UE or to fall back to non-AI CSI reporting.

24. The method of any one of claims 18-23, wherein, The first information further includes: model identification information; data set identification information; CSI reporting identification information; monitoring identification information.

25. The method of any one of claims 16-24, wherein, The method further includes: obtaining the expected CSI feedback information according to target CSI information or a quantized value of the target CSI information.

26. An information processing apparatus, comprising: a first receiving module configured to receive first information, the first information including at least one of: a reason for target unit failure, the target unit being a unit for processing CSI information; indication information for deactivating the target unit; indication information for switching the target unit; information related to target unit updating; information related to a new target unit; first indication information for indicating updating or optimizing the target unit; second indication information for indicating a quantization level or an optimization level of the target unit.

27. The apparatus of claim 26, wherein, The apparatus further includes: The first sending module is configured to send third indication information, where the third indication information is used to represent that the first AI unit is updated or that the updated first AI unit can be activated for use, or the third indication information is used to represent that the first AI unit is in an activated state, or the third indication information is used to represent that the first AI unit is updated or that the updated first AI unit is released or in an unusable state.

28. The apparatus of claim 26, wherein, The apparatus further includes: The second sending module is configured to send fourth indication information to a network side device at a first time, where the fourth indication information is used to instruct the network side device to send the first information, and the first information at least includes information related to target unit updating.

29. The apparatus of claim 26, wherein, The apparatus further includes: The first reporting module is configured to report auxiliary information, where the auxiliary information at least includes one of the following: Target CSI information; Monitoring information of the target unit estimated by a terminal; A quantized value of the target CSI information; Second CSI feedback information obtained by the UE according to the quantized value of the target CSI information; Third CSI feedback information obtained by the UE using a reference model. 30.An information processing apparatus, comprising: The second receiving module is configured to receive auxiliary information reported by a user equipment (UE); The first determining module is configured to determine, according to the auxiliary information, whether a target unit is valid or a reason for invalidity of the target unit or first information, where the target unit is a unit used to process CSI information. The auxiliary information at least includes one of the following: Target CSI information; Monitoring information of the target unit estimated by a terminal; A quantized value of the target CSI information; Second CSI feedback information obtained by the UE according to the quantized value of the target CSI information; Third CSI feedback information obtained by the UE using a reference model.

31. The apparatus of claim 30, wherein, The apparatus further includes: The third sending module is configured to send first information to the UE, where the first information at least includes one of the following: A reason for invalidity of a target unit, where 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 updating; Information related to a new target unit; First indication information used to instruct to update or optimize the target unit; Second indication information used to instruct a quantization level or an optimization level of the target unit.

32. The apparatus of claim 30, wherein, The apparatus further includes: The third receiving module is configured to receive third indication information sent by the UE; The second determining module is configured to determine, according to the third indication information, that the first AI unit is updated or that the updated first AI unit can be activated for use, or to determine that the first AI unit is in an activated state, or to determine that the first AI unit is updated or that the updated first AI unit is released or in an unusable state.

33. The apparatus of claim 31, wherein, The apparatus further includes: The fourth receiving module is configured to receive fourth indication information sent by the UE; The fourth sending module is configured to send, according to the fourth indication information, the first information to the UE, where the first information at least includes information related to target unit updating. 34.A user equipment comprising a processor and a memory, the memory storing programs or instructions executable on the processor, the programs or instructions, when executed by the processor, implement the steps of the information processing method according to any one of claims 1 to 14. 35.A network side equipment comprising a processor and a memory, the memory storing programs or instructions executable on the processor, the programs or instructions, when executed by the processor, implement the steps of the information processing method according to any one of claims 15 to 25. 36.A readable storage medium, the readable storage medium storing programs or instructions, the programs or instructions, when executed by a processor, implement the steps of the information processing method according to any one of claims 1 to 14, or implement the steps of the information processing method according to any one of claims 15 to 25.

Images