Model processing method and apparatus, and terminal and network-side device

Abstract

The present application belongs to the technical field of communications. Disclosed are a model processing method and apparatus, and a terminal and a network-side device. The model processing method in the embodiments of the present application comprises: when a terminal meets a first condition, the terminal performing a target operation on a stored first artificial intelligence (AI) model, wherein the first condition comprises at least one of the following: a subscriber identity module (SIM) of the terminal is changed; and the SIM configuration of the terminal is changed.

Description

Model processing method, device, terminal and network side equipment

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This application claims priority to Chinese Patent Application No. 202410360869.0 filed in China on March 27, 2024, the entire contents of which are incorporated herein by reference. Technical Field

[0003] The present application belongs to the field of communication technology, and specifically relates to a model processing method, apparatus, terminal and network-side equipment. Background Art

[0004] Artificial Intelligence (AI) is currently gaining widespread application across various fields. Integrating AI into wireless communication networks to improve technical indicators such as throughput, latency, and user capacity is a key task for future wireless communication networks. Related technologies deploy AI models on the terminal side to enhance the terminal's data processing capabilities. However, AI models deployed on the terminal are always available, making them less secure. Summary of the Invention

[0005] The embodiments of the present application provide a model processing method, apparatus, terminal, and network-side equipment, which can solve the problem of poor security of AI models deployed on terminals.

[0006] In a first aspect, a model processing method is provided, comprising:

[0007] When the terminal meets the first condition, the terminal performs a target operation on the stored first artificial intelligence AI model;

[0008] The first condition includes at least one of the following:

[0009] The subscriber identity module (SIM) of the terminal is changed; the SIM configuration of the terminal is changed.

[0010] In a second aspect, a model processing method is provided, comprising:

[0011] The network-side device receives a first message sent by the terminal, where the first message carries information about an AI model that can be used by the terminal;

[0012] The network side device sends a second message to the terminal, where the second message carries first indication information, and the first indication information is used to indicate the operation of the AI ​​model that can be used by the terminal.

[0013] In a third aspect, a model processing device is provided, comprising:

[0014] An operation module, configured to perform a target operation on the stored first artificial intelligence (AI) model when the terminal meets a first condition;

[0015] The first condition includes at least one of the following:

[0016] The subscriber identity module (SIM) of the terminal is changed; the SIM configuration of the terminal is changed.

[0017] In a fourth aspect, a model processing device is provided, comprising:

[0018] a receiving module, configured to receive a first message sent by a terminal, where the first message carries information about an AI model that can be used by the terminal;

[0019] A sending module is used to send a second message to the terminal, where the second message carries first indication information, and the first indication information is used to indicate the operation of the AI ​​model that can be used by the terminal.

[0020] In a fifth aspect, a terminal is provided, comprising a processor and a memory, wherein the memory stores a program or instruction that can be run on the processor, and when the program or instruction is executed by the processor, the steps of the method described in the first aspect are implemented.

[0021] In a sixth aspect, a network side device is provided, which includes a processor and a memory, wherein the memory stores programs or instructions that can be run on the processor, and when the program or instructions are executed by the processor, the steps of the method described in the second aspect are implemented.

[0022] In a seventh aspect, a terminal is provided, including a processor and a communication interface, wherein the processor is configured to:

[0023] When the terminal meets the first condition, performing a target operation on the stored first artificial intelligence AI model;

[0024] The first condition includes at least one of the following:

[0025] The subscriber identity module (SIM) of the terminal is changed; the SIM configuration of the terminal is changed.

[0026] In an eighth aspect, a network-side device is provided, including a processor and a communication interface, wherein the communication interface is configured to:

[0027] receiving a first message sent by a terminal, where the first message carries information about an AI model that can be used by the terminal;

[0028] A second message is sent to the terminal, where the second message carries first indication information, where the first indication information is used to indicate an operation of the AI ​​model that can be used by the terminal.

[0029] In the ninth aspect, a model processing system is provided, comprising: a terminal and a network-side device, wherein the terminal can be used to execute the steps of the method described in the first aspect, and the network-side device can be used to execute the steps of the method described in the second aspect.

[0030] In the tenth aspect, a readable storage medium is provided, on which a program or instruction is stored. When the program or instruction is executed by a processor, the steps of the method described in the first aspect or the steps of the method described in the second aspect are implemented.

[0031] In the eleventh aspect, a chip is provided, which includes a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is used to run programs or instructions to implement the method as described in the first aspect, or to implement the method as described in the second aspect.

[0032] In the twelfth aspect, a computer program / program product is provided, which is stored in a storage medium and executed by at least one processor to implement the steps of the method described in the first aspect, or to implement the steps of the method described in the second aspect.

[0033] In an embodiment of the present application, when a terminal satisfies a first condition, the terminal performs a target operation on a stored first artificial intelligence (AI) model; wherein the first condition includes at least one of the following: a change in the terminal's subscriber identity module (SIM) or a change in the terminal's SIM configuration. In this way, when the terminal's SIM or SIM configuration is changed, the target operation is performed on the stored first AI model, thereby enabling the first AI model to be processed even if there is a security risk, thereby improving the security of the first AI model stored in the terminal. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] FIG1 is a block diagram of a wireless communication system to which embodiments of the present application may be applied;

[0035] FIG2 is a schematic diagram of a neural network in the related art;

[0036] FIG3 is a schematic diagram of a neuron in the related art;

[0037] FIG4 is a flow chart of a model processing method provided in an embodiment of the present application;

[0038] FIG5 is a second flow chart of a model processing method provided in an embodiment of the present application;

[0039] FIG6 is a third flow chart of a model processing method provided in an embodiment of the present application;

[0040] FIG7 is a fourth flow chart of a model processing method provided in an embodiment of the present application;

[0041] FIG8 is a structural diagram of a model processing device according to an embodiment of the present application;

[0042] FIG9 is a second structural diagram of a model processing device provided in an embodiment of the present application;

[0043] FIG10 is a schematic structural diagram of a communication device provided in an embodiment of the present application;

[0044] FIG11 is a schematic structural diagram of a terminal provided in an embodiment of the present application;

[0045] FIG12 is a schematic structural diagram of a network-side device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0046] The following will be combined with the accompanying drawings in the embodiments of this application to clearly describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field are within the scope of protection of this application.

[0047] The terms "first", "second", etc. in this 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 are interchangeable where appropriate, so that the embodiments of the present application can be implemented in an order other than those illustrated or described herein, and the objects distinguished by "first" and "second" are generally of the same type, and do not limit the number of objects, for example, the first object can be one or more. In addition, "or" in this application represents at least one of the connected objects. For example, "A or B" covers three options, namely, Option 1: including A but not including B; Option 2: including B but not including A; Option 3: including both A and B. The character " / " generally indicates that the objects associated before and after are in an "or" relationship.

[0048] The term "indication" in this application can be either a direct indication (or explicit indication) or an indirect indication (or implicit indication). A direct indication can be understood as the sender explicitly informing the receiver of specific information, the operation to be performed, or the requested result, etc. in the instruction sent; an indirect indication can be understood as the receiver determining the corresponding information based on the instruction sent by the sender, or making a judgment and determining the operation to be performed or the requested result, etc. based on the judgment result.

[0049] 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 technology described can be used for the systems and radio technologies mentioned above, as well as for other systems and radio technologies. The following description describes a New Radio (NR) system for illustrative purposes, and NR terminology is used in most of the following description, but these technologies can also be applied to systems other than NR systems, such as 6th generation (6G) systems. th Generation, 6G) communication system.

[0050] FIG1 shows a block diagram of a wireless communication system applicable to an embodiment of the present application. The wireless communication system includes a terminal 11 and a network-side device 12. The terminal 11 can be a mobile phone, a tablet computer (Tablet Personal Computer), a laptop computer (Laptop Computer), a notebook computer, a personal digital assistant (PDA), a handheld 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 (Wearable Device), an aircraft (flight vehicle), a vehicle user equipment (VUE), a ship-borne device, a pedestrian user equipment (PUE), a smart home (home appliances with wireless communication capabilities, such as refrigerators, televisions, washing machines, or furniture), a game console, a personal computer (PC), a teller machine, or a self-service machine, or other terminal-side devices. Wearable devices include: smart watches, smart bracelets, smart headphones, smart glasses, smart jewelry (smart bracelets, smart bracelets, smart rings, smart necklaces, smart anklets, smart anklets, etc.), smart wristbands, smart clothing, etc. Among them, the vehicle-mounted device can also be called a vehicle-mounted terminal, a vehicle-mounted controller, a vehicle-mounted module, a vehicle-mounted component, a vehicle-mounted chip or a vehicle-mounted unit, etc. It should be noted that the specific type of the terminal 11 is not limited in the embodiment of the present application. The network side device 12 may include an access network device or a core network device, wherein the access network device may also be called a radio access network (Radio Access Network, RAN) device, a radio access network function or a radio access network unit. The access network device may include a base station, a wireless local area network (WLAN) access point (AS) or a wireless fidelity (WiFi) node, etc.Among them, the base station can be referred to as Node B (NB), Evolved Node B (eNB), the next generation Node B (gNB), New Radio Node B (NR Node B), access point, relay base station (RBS), serving base station (SBS), base transceiver station (BTS), radio base station, radio transceiver, basic service set (BSS), extended service set (ESS), home Node B (HNB), home evolved Node B (home evolved Node B), transmission reception point (TRP) or other appropriate terms in the relevant field. As long as the same technical effect is achieved, the base station is not limited to specific technical vocabulary. It should be noted that in the embodiment of the present application, only the base station in the NR system is used as an example to introduce, and the specific type of the base station is not limited.

[0051] The core network equipment may include but is not limited to at least one of the following: core network node, core network function, mobility management entity (MME), access mobility management function (AMF), session management function (SMF), user plane function (UPF), policy control function (PCF), policy and charging rules function unit (PCRF), edge application service discovery function (EASDF), unified data management (UDM), unified data repository (UDR), home user server (HSS), centralized network configuration (CNC), network storage function (NRF), network exposure function (NEF), local NEF (L-NEF), binding support function (BSF), application function ( Function, AF), Location Management Function (LMF), Gateway Mobile Location Centre (GMLC), Network Data Analytics Function (NWDAF), etc. It should be noted that in the embodiment of the present application, only the core network equipment in the NR system is taken as an example to introduce, and the specific type of the core network equipment is not limited.

[0052] For ease of understanding, some terms involved in the embodiments of this application are explained below:

[0053] 1. Artificial Intelligence (AI)

[0054] Artificial intelligence (AI) is currently being widely used in various fields. Integrating AI into wireless communication networks to significantly improve technical indicators such as throughput, latency, and user capacity is a key task for future wireless communication networks. AI modules can be implemented in a variety of ways, such as neural networks, decision trees, support vector machines, and Bayesian classifiers. This application uses neural networks as an example for illustration, but does not limit the specific type of AI module.

[0055] A neural network diagram is shown in Figure 2:

[0056] A neural network is composed of neurons, as shown in Figure 3. Here, a1, a2, …, aK are inputs, w is the weight (multiplicative coefficient), b is the bias (additive coefficient), and σ(.) is the activation function. Common activation functions include sigmoid, tanh, linear rectification function, and rectified linear unit (ReLU).

[0057] Neural network parameters are optimized using a gradient optimization algorithm. Gradient optimization algorithms are a class of algorithms that minimize or maximize an objective function (also known as a loss function). This objective function is often a mathematical combination of model parameters and data. For example, given data X and its corresponding label Y, we construct a neural network model f(.). With this model, we can obtain the predicted output f(x) based on the input x, and calculate the difference between the predicted value and the true value (f(x) - Y). This is the loss function. We find the appropriate values ​​W and b that minimize the loss function. The smaller the loss value, the closer the model is to the true value.

[0058] Currently, most common optimization algorithms are based on the back propagation (BP) algorithm. The basic idea of ​​the BP algorithm is that the learning process consists of two steps: forward propagation of signals and back propagation of errors. During forward propagation, input samples are passed from the input layer, processed layer by layer through each hidden layer, and then transmitted to the output layer. If the actual output of the output layer does not match the expected output, the error begins back propagation. Back propagation involves propagating the output error back through the hidden layers to the input layer layer by layer in some form, distributing the error to all units in each layer. This error signal is then generated for each unit in each layer, which serves as the basis for adjusting the weights of each unit. This process of adjusting the weights of each layer, through forward propagation of signals and back propagation of errors, is repeated over and over again. This process of continuous weight adjustment is the network's learning and training process. This process continues until the error in the network output is reduced to an acceptable level, or until a pre-set number of learning cycles is reached.

[0059] Common optimization algorithms include gradient descent, stochastic gradient descent (SGD), mini-batch gradient descent, momentum method (Momentum), stochastic gradient descent with momentum (Nesterov), adaptive gradient descent (Adagrad), Adadelta, root mean square error (RMSprop), adaptive momentum estimation (Adam), etc.

[0060] When these optimization algorithms backpropagate errors, they all calculate the derivative / partial derivative of the current neuron based on the error / loss obtained by the loss function, add the influence of the learning rate, the previous gradient / derivative / partial derivative, etc., obtain the gradient, and pass the gradient to the previous layer.

[0061] 2. AI Unit / AI Model

[0062] The AI ​​unit / AI model described in this application may also be referred to as an AI unit, an AI model, a machine learning (ML) model, an ML unit, an AI structure, an AI function, an AI feature, a machine learning model, a neural network, a neural network function, a neural network function, etc., or the AI ​​unit / AI model may also refer to a processing unit that can implement specific algorithms, formulas, processing procedures, capabilities, etc. related to AI, or the AI ​​unit / AI model may be a processing method, algorithm, function, module or unit for a specific data set, or the AI ​​unit / AI model may be a processing method, algorithm, function, module or unit running on AI / ML related hardware such as a graphics processing unit (GPU), a neural network processor (NPU), a tensor processing unit (TPU), an application specific integrated circuit (ASIC), etc., and the embodiments of this application do not specifically limit this. Optionally, the specific data set includes the input or output of the AI ​​unit / AI model.

[0063] Optionally, the identifier of the AI ​​unit / AI model may be an AI model identifier, an AI structure identifier, an AI algorithm identifier, or an identifier of a specific data set associated with the AI ​​unit / AI model, or an identifier of a specific scenario, environment, channel feature, or device related to the AI / ML, or an identifier of a function, feature, capability, or module related to the AI / ML. This embodiment of the present application does not specifically limit this.

[0064] AI functionality: an AI algorithm function that can be associated with multiple AI models.

[0065] AI models are primarily deployed on the network side. With the continuous integration of AI and communications technologies and the increasing computing power on the device side, AI models are increasingly being deployed on the device side to improve communication capabilities and meet real-time requirements. These AI models may be provided by various device manufacturers or network operators. When AI models are provided by network operators, deployment involves a series of signaling and model transmission processes. Signaling processes primarily control model transmission and may include restrictions on model usage scenarios, such as enabling a model within a certain channel quality range, or directly controlling the activation and deactivation of a model. The model transmission process is strongly correlated with model size. Complex models are larger, requiring more resources for transmission and potentially taking longer. Furthermore, some AI models require simultaneous deployment and activation on both the device and network sides to function as intended.

[0066] 3. USIM and eUICC

[0067] The Universal Subscriber Identity Module (USIM) is an advanced version of the Subscriber Identity Module (SIM) card and is widely used in 5G systems. Compared to traditional SIM cards, the USIM card provides higher security and more storage space to support new mobile communication features. The USIM card stores user identity information, keys, contact lists, and other information, and provides stronger security features.

[0068] An embedded SIM (eSIM) is a digital, non-removable SIM card. It has the same functions as a USIM, but it is physically integrated on the motherboard of the device, i.e. it cannot be removed from the device and replaced with another SIM card. The two main elements of an eSIM are an embedded Universal Integrated Circuit Card (eUICC, commonly referred to as an eSIM chip) and a Profile, which is an eSIM configuration file. A Profile refers to data related to an operator subscription, including its credentials, configuration, and any SIM card-based applications. In the case of an eSIM, it exists in digital form and must be downloaded by the user to the eSIM on their device. The eUICC can provide Profile management and security assurance, including remote downloading, activation, deactivation and other processes. Multiple Profiles can be accommodated in an eUICC.

[0069] The model processing method, apparatus, terminal, and network-side equipment provided in the embodiments of the present application are described in detail below with reference to some embodiments and their application scenarios in conjunction with the accompanying drawings.

[0070] Referring to FIG4 , FIG4 is a flow chart of a model processing method provided in an embodiment of the present application. As shown in FIG4 , the model processing method includes the following steps:

[0071] Step 101: When a terminal satisfies a first condition, the terminal performs a target operation on a stored first artificial intelligence (AI) model;

[0072] The first condition includes at least one of the following:

[0073] The subscriber identity module (SIM) of the terminal is changed; the SIM configuration of the terminal is changed.

[0074] Performing a target operation on the first AI model can be understood as managing the first AI model. Methods for managing the first AI model include, but are not limited to, retaining, deleting, using AI context management and switching context states, or combining AI context state switching and deletion. For example, the target operation may include retaining or deleting the AI ​​model context; or processing the AI ​​model context, performing secure processing based on key information, such as updating the AI ​​model context state or deleting the AI ​​model context. This embodiment does not limit the target operation.

[0075] In one embodiment, the context state of the first AI model may be an activated state.

[0076] In one embodiment, the SIM may be a Universal Subscriber Identity Module (USIM), and the SIM change of the terminal may refer to a change of the USIM of the terminal. The first condition may include: a change of the USIM of the terminal.

[0077] In one embodiment, the SIM may be an eSIM, and the SIM configuration change of the terminal may refer to a configuration change of the eSIM of the terminal. The first condition may include: a configuration change of the eSIM of the terminal. The configuration change of the eSIM of the terminal may refer to a profile change of the eSIM of the terminal. Profile change may be understood as or replaced by profile deactivation.

[0078] In one embodiment, the first condition includes:

[0079] In the case where the SIM card of the terminal is a USIM, the USIM card of the terminal is changed; or

[0080] In the case where the SIM of the terminal is an eSIM, the eSIM configuration of the terminal is changed.

[0081] It should be noted that the SIM change of the terminal may refer to the change of the SIM (such as USIM) of the terminal from the first SIM to the second SIM, and the current SIM of the terminal after the change is the second SIM, and the first AI model may be an AI model associated with the first SIM. After the SIM of the terminal is changed, there may be security risks in the storage or use of the first AI model. For example, the first SIM and the second SIM may belong to different networks, and the first AI model is the AI ​​model sent to the terminal by the network to which the first SIM belongs. After the network is changed, the first AI model is in a usable state by default under the network to which the second SIM belongs, which will cause the first AI model to be leaked. In an embodiment of the present application, by performing target operations on the first AI model, the security risks that may exist in the storage or use of the first AI model can be reduced.

[0082] In addition, the SIM configuration change of the terminal may refer to that the SIM (such as eSIM) configuration of the terminal is changed from the first SIM configuration to the second SIM configuration, and the current SIM configuration of the terminal after the change is the second SIM configuration, and the first AI model may be an AI model associated with the first SIM configuration. After the SIM configuration of the terminal is changed, there may be security risks in the storage or use of the first AI model. For example, the first SIM configuration and the second SIM configuration may belong to different networks. The first AI model is the AI ​​model sent to the terminal under the network to which the first SIM configuration belongs. After the network is changed, the first AI model is in a usable state by default under the network to which the second SIM configuration belongs, which will cause the first AI model to have a leakage risk. In an embodiment of the present application, by performing target operations on the first AI model, the security risks that may exist in the storage or use of the first AI model can be reduced.

[0083] It should be noted that for terminals using USIM, the terminal can sense the USIM insertion and removal behavior during hot plugging; when the terminal is powered off and plugged in, the terminal can determine whether there has been a USIM change by comparing the IMSI stored in the non-volatile memory with the IMSI of the current USIM after powering on again. For terminals using eSIM, through user operations or operators operating the profile in the eUICC, which contains identifiers such as IMSI, the terminal can sense profile changes and determine whether there has been a profile change by comparing the IMSI stored in the non-volatile memory with the IMSI in the current profile.

[0084] In the embodiment of the present application, the first AI model for performing the target operation may include: an AI model sent by a network-side device to the terminal for use; or include, an AI model downloaded to the terminal by the terminal user from the terminal manufacturer, and the downloaded AI model may be contracted with the terminal's SIM card.

[0085] In the related art, when a terminal using a USIM replaces the USIM, or when a terminal using an eSIM deactivates the current profile and activates another profile, it may cause the network to which it belongs to to be different from the original one, or even change the operator. In this case, the AI ​​model sent by the network to the terminal for use may have security issues in storage or use, posing potential dangers to the terminal. When a terminal using a USIM has the USIM plugged in or out, or when a terminal using an eSIM has the profile changed, if there is no reasonable way to manage the AI ​​model provided to the terminal by the network side or the equipment manufacturer, the security of the model may not be guaranteed, and the private model of the operator or equipment manufacturer may be leaked. Through the embodiments of the present application, the terminal is supported to manage the AI ​​model when the above scenarios occur, which can improve the security of the AI ​​model.

[0086] In an embodiment of the present application, when a terminal satisfies a first condition, the terminal performs a target operation on a stored first artificial intelligence (AI) model; wherein the first condition includes at least one of the following: a change in the terminal's subscriber identity module (SIM) or a change in the terminal's SIM configuration. In this way, when the terminal's SIM or SIM configuration is changed, the target operation is performed on the stored first AI model, thereby enabling the first AI model to be processed even if there is a security risk, thereby improving the security of the first AI model stored in the terminal.

[0087] Optionally, the target operation includes at least one of the following:

[0088] Retention or deletion;

[0089] Update the state of the AI ​​model context, or delete the AI ​​model context;

[0090] Secure processing based on key information.

[0091] Among them, the AI ​​model context includes but is not limited to the following: IMSI; context status (active or inactive); public land mobile network (PLMN); model list; AI model identification; model storage path; model life cycle parameters; model usage status; model information.

[0092] In the case where the target operation includes retention processing, the terminal performing the target operation on the stored first AI model may include: the terminal retaining the first AI model; the terminal sending a first message to a network-side device, the first message being used to report information about AI models available to the terminal, the AI ​​models available to the terminal including the first AI model; and the terminal receiving a second message sent by the network-side device, the second message carrying first indication information, the first indication information being used to indicate an operation of the AI ​​model available to the terminal. The terminal may then perform subsequent operations on the first AI model based on the second message.

[0093] Additionally, key information can be understood or replaced with model key information. The key information can include a numeric code for identity authentication, such as a PIN code. For example, the first AI model can be associated with first key information, which can be a PIN code for a user who is authorized to use the first AI model. The terminal's SIM card is associated with second key information, allowing the terminal to use the first AI model only if the second key information matches the first key information. Matching the second key information with the first key information can mean that the second key information is identical to the first key information, or that the second key information and the first key information conform to a preset rule, etc., which is not limited in this embodiment. The first key information can be configured to the terminal by the provider of the first AI model when the terminal obtains the first AI model. The second key information is bound to the SIM card or SIM configuration and can be carried in the SIM card or SIM configuration. Alternatively, when the SIM card is changed, the network-side device can configure the second key information associated with the changed SIM card to the terminal. Alternatively, when the SIM configuration is changed, the network-side device can configure the second key information associated with the changed SIM card to the terminal.

[0094] In this embodiment, the target operation includes retention processing or deletion processing, thereby supporting the terminal to decide whether to retain or delete the first AI model when there is a risk of leakage of the first AI model, reducing the risk of leakage of the AI ​​model due to the default retention of the first AI model, and improving the security of the first AI model deployed on the terminal.

[0095] In this embodiment, the target operation includes updating the state of the AI ​​model context, or deleting the AI ​​model context, thereby supporting the terminal to update the state of the context of the first AI model, or deleting the context of the first AI model when there is a risk of leakage of the first AI model, so that the terminal cannot use the first AI model stored before the SIM change or SIM configuration change, thereby improving the security of the first AI model deployed on the terminal.

[0096] In this embodiment, the target operation includes performing security processing based on key information, thereby supporting the terminal to improve the security of the first AI model deployed on the terminal by performing security processing on the first AI model based on key information when there is a risk of leakage of the first AI model.

[0097] Optionally, the deletion process includes any one of the following:

[0098] Deleting the first AI model;

[0099] A first timer is started, and when the first timer times out, the first AI model is deleted.

[0100] In one embodiment, taking the case where the first condition includes a SIM change of the terminal as an example, the SIM of the terminal (such as a USIM) is changed from a first SIM to a second SIM. After the change, the current SIM of the terminal is the second SIM. The first timer can be stopped or turned off when switching back to the first SIM, so that the first AI model can be deleted only when no event of switching back to the first SIM occurs during the operation of the first timer, thereby avoiding accidental deletion caused by frequent SIM changes.

[0101] In one embodiment, taking the case where the first condition includes a change in the SIM configuration of the terminal as an example, the SIM (such as an eSIM) configuration of the terminal is changed from the first SIM configuration to the second SIM configuration. After the change, the current SIM configuration of the terminal is the second SIM configuration. The first timer can be stopped or turned off when switching back to the first SIM configuration, so that the first AI model can be deleted only when no event of switching back to the first SIM configuration occurs during the operation of the first timer, thereby avoiding accidental deletion caused by frequent changes of SIM configurations.

[0102] In this implementation, when the SIM card of the terminal is changed or the SIM configuration is changed, the first AI model is deleted; or, when the SIM card of the terminal is changed or the SIM configuration is changed, a first timer is started, and when the first timer times out, the first AI model is deleted; thereby, the risk of AI model leakage due to the default retention of the first AI model can be reduced, and the security of the first AI model deployed on the terminal can be improved; and the problem of occupying terminal resources due to not deleting the AI ​​models after downloading a large number of AI models can be solved.

[0103] Optionally, updating the state of the AI ​​model context includes:

[0104] When the context state of the first AI model is an activated state, updating the context state of the first AI model to an inactivated state;

[0105] When the context state of the second AI model stored in the terminal is in an inactive state, if the International Mobile Subscriber Identity (IMSI) contained in the context of the second AI model is the same as the IMSI of the SIM of the terminal, the context state of the second AI model is updated to an active state.

[0106] In this implementation, when the context state of the first AI model is in an activated state, the context state of the first AI model is updated to an inactivated state, so that the terminal cannot use the first AI model stored before the SIM change or SIM configuration change, thereby improving the security of the first AI model deployed on the terminal; when the context state of the second AI model stored in the terminal is in an inactivated state, if the IMSI included in the context of the second AI model is the same as the IMSI of the terminal's SIM, the context state of the second AI model is updated to an activated state, so that when the terminal's SIM is changed or the SIM configuration is changed, the terminal can use the second AI model with the same IMSI, thereby improving the flexibility of the terminal in using AI models.

[0107] Optionally, deleting the AI ​​model context includes:

[0108] When the context state of the first AI model changes to an inactive state, starting a second timer;

[0109] When the second timer times out, the context of the first AI model is deleted.

[0110] Among them, the second timer can be stopped or turned off when the context state of the first AI model changes from an inactive state to an active state, so that the first AI model can be deleted only when no event occurs during the operation of the second timer that the context state of the first AI model switches back to an active state, thereby avoiding accidental deletion caused by frequent changes in the context state.

[0111] In this implementation, when the context state of the first AI model changes to an inactive state, a second timer is started; when the second timer times out, the context of the first AI model is deleted. Thus, when the SIM card of the terminal is changed or the SIM configuration is changed, the terminal cannot use the first AI model stored before the SIM card is changed or the SIM configuration is changed, thereby improving the security of the first AI model deployed on the terminal.

[0112] Optionally, the performing security processing based on the key information includes:

[0113] In a case where the first AI model is associated with the first key information, the terminal matches the first key information associated with the first AI model with the second key information associated with the SIM of the terminal;

[0114] When the first key information matches the second key information successfully, the terminal retains the first AI model.

[0115] In which, the first key information and the second key information may be model keys, and the first key information associated with the first AI model may only match the second key information associated with one SIM, that is, after the SIM is changed or the SIM configuration is changed, the first key information associated with the first AI model cannot successfully match the second key information associated with the changed SIM; or, the first key information associated with the first AI model may match multiple second key information, that is, the first key information associated with the first AI model may successfully match the second key information associated with the changed SIM.

[0116] In addition, when the first key information fails to match the second key information, the terminal may delete the first AI model, or delete the context of the first AI model, or update the context state of the first AI model to an inactive state.

[0117] In this implementation, when the first AI model is associated with first key information, the terminal matches the first key information associated with the first AI model with the second key information associated with the terminal's SIM; when the first key information successfully matches the second key information, the terminal retains the first AI model; in this way, by securely processing the first AI model based on the key information, the security of the first AI model deployed on the terminal can be improved.

[0118] Optionally, the method further includes:

[0119] In a case where the terminal retains the first AI model, the terminal stores the model information of the first AI model in the AI ​​model context corresponding to the IMSI of the SIM of the terminal.

[0120] The SIM card of the terminal may be understood as the current SIM card of the terminal. When the terminal retains the first AI model, the terminal stores the model information of the first AI model in the AI ​​model context corresponding to the IMSI of the current SIM card of the terminal.

[0121] In this implementation, when the terminal retains the first AI model, the terminal stores the model information of the first AI model in the AI ​​model context corresponding to the IMSI of the terminal's SIM, so that when the terminal determines to retain the first AI model, the terminal can use the retained first AI model for data processing.

[0122] Optionally, the terminal performs a target operation on the stored first AI model, including:

[0123] When the terminal satisfies the second condition, if the terminal obtains first configuration information, the terminal performs a target operation on the stored first AI model based on the first configuration information, where the first configuration information is configuration information configured by a network-side device for the terminal to manage the first AI model;

[0124] The second condition includes at least one of the following:

[0125] The Home Public Land Mobile Network (HPLMN) of the terminal's SIM is the same as the HPLMN corresponding to the IMSI stored in the terminal;

[0126] The HPLMN corresponding to the IMSI stored in the terminal is in an Equivalent Home Public Land Mobile Network (EHPLMN) list corresponding to the SIM of the terminal.

[0127] The IMSI stored in the terminal may refer to the IMSI stored in the non-volatile memory of the terminal.

[0128] The SIM card of the terminal can be understood as the current SIM card of the terminal. In the case of a change in the SIM card of the terminal or a change in the SIM card configuration, if the HPLMN of the SIM card of the terminal is the same as the HPLMN corresponding to the IMSI stored in the terminal, it can be considered that the network to which the current SIM card of the terminal or the current SIM card configuration belongs is the same as the network to which the SIM card or the SIM card configuration before the change belonged.

[0129] In addition, when the SIM or SIM configuration of the terminal is changed, the HPLMN corresponding to the IMSI stored in the terminal is in the EHPLMN list corresponding to the SIM of the terminal. It can be considered that the network to which the current SIM of the terminal or the current SIM configuration belongs is equivalent to the network to which the SIM or SIM configuration before the change belongs.

[0130] In one embodiment, when the HPLMN of the terminal's SIM is the same as the HPLMN corresponding to the IMSI stored in the terminal, if the terminal obtains first configuration information, the terminal performs a target operation on the stored first AI model based on the first configuration information.

[0131] In one embodiment, when the HPLMN corresponding to the IMSI stored in the terminal is in the EHPLMN list corresponding to the SIM of the terminal, if the terminal obtains first configuration information, the terminal performs a target operation on the stored first AI model based on the first configuration information.

[0132] In one embodiment, it is determined whether the HPLMN of the terminal's SIM is the same as the HPLMN corresponding to the IMSI stored in the terminal. If the HPLMN of the terminal's SIM is not the same as the HPLMN corresponding to the IMSI stored in the terminal, it is determined whether the HPLMN corresponding to the IMSI stored in the terminal is in the EHPLMN list corresponding to the SIM of the terminal; if the HPLMN corresponding to the IMSI stored in the terminal is in the EHPLMN list corresponding to the SIM of the terminal, if the terminal obtains first configuration information, the terminal performs a target operation on the stored first AI model based on the first configuration information.

[0133] In one embodiment, it is determined whether the HPLMN corresponding to the IMSI stored in the terminal is in the EHPLMN list corresponding to the SIM of the terminal; if the HPLMN corresponding to the IMSI stored in the terminal is not in the EHPLMN list corresponding to the SIM of the terminal, it is determined whether the HPLMN of the SIM of the terminal is the same as the HPLMN corresponding to the IMSI stored in the terminal; if the HPLMN of the SIM of the terminal is the same as the HPLMN corresponding to the IMSI stored in the terminal, if the terminal obtains first configuration information, the terminal performs a target operation on the stored first AI model based on the first configuration information.

[0134] It should be noted that the network side device configures the terminal with first configuration information for managing the first AI model. It can be understood that the network side device configures the terminal with a lifecycle management method of the first AI model.

[0135] In addition, when the terminal meets the second condition, if the terminal does not obtain the first configuration information, the terminal determines the target operation; and the terminal performs the target operation on the stored first AI model.

[0136] In this implementation, when the SIM or SIM configuration of the terminal is changed, if the network to which the current SIM or current SIM configuration of the terminal belongs is the same as or equivalent to the network to which the SIM or SIM configuration before the change belongs, the terminal uses the first configuration information configured by the network side device to perform target operations on the stored first AI model, thereby improving the security of the first AI model deployed on the terminal.

[0137] Optionally, the terminal performs a target operation on the stored first AI model, further comprising:

[0138] If the terminal does not meet the second condition, the terminal determines a target operation;

[0139] The terminal performs the target operation on the stored first AI model.

[0140] In one implementation, the terminal satisfies the second condition, which may include: the HPLMN of the terminal's SIM is the same as the HPLMN corresponding to the IMSI stored in the terminal; the terminal does not satisfy the second condition, which may include: the HPLMN of the terminal's SIM is different from the HPLMN corresponding to the IMSI stored in the terminal.

[0141] In one implementation, the terminal satisfies the second condition, which may include: the HPLMN corresponding to the IMSI stored in the terminal is in the EHPLMN list corresponding to the SIM of the terminal; the terminal does not satisfy the second condition, which may include: the HPLMN corresponding to the IMSI stored in the terminal is not in the EHPLMN list corresponding to the SIM of the terminal.

[0142] In one embodiment, the terminal satisfies the second condition, which may include: the HPLMN of the terminal's SIM is the same as the HPLMN corresponding to the IMSI stored in the terminal, or the HPLMN corresponding to the IMSI stored in the terminal is in the EHPLMN list corresponding to the SIM of the terminal; the terminal does not satisfy the second condition, which may include: the HPLMN of the terminal's SIM is different from the HPLMN corresponding to the IMSI stored in the terminal, and the HPLMN corresponding to the IMSI stored in the terminal is not in the EHPLMN list corresponding to the SIM of the terminal.

[0143] Among them, when the SIM of the terminal is changed or the SIM configuration is changed, the HPLMN of the SIM of the terminal is different from the HPLMN corresponding to the IMSI stored in the terminal. It can be considered that the network to which the current SIM of the terminal or the current SIM configuration belongs is different from the network to which the SIM or SIM configuration before the change belongs.

[0144] In addition, when the SIM or SIM configuration of the terminal is changed, the HPLMN corresponding to the IMSI stored in the terminal is not in the EHPLMN list corresponding to the SIM of the terminal. It can be considered that the network to which the current SIM or current SIM configuration of the terminal belongs is not equivalent to the network to which the SIM or SIM configuration before the change belongs.

[0145] In one embodiment, when the HPLMN of the terminal's SIM is different from the HPLMN corresponding to the IMSI stored in the terminal, the terminal determines a target operation; and the terminal performs the target operation on the stored first AI model.

[0146] In one embodiment, when the HPLMN corresponding to the IMSI stored in the terminal is not in the EHPLMN list corresponding to the SIM of the terminal, the terminal determines a target operation; and the terminal performs the target operation on the stored first AI model.

[0147] In one embodiment, it is determined whether the HPLMN of the terminal's SIM is the same as the HPLMN corresponding to the IMSI stored in the terminal. If the HPLMN of the terminal's SIM is not the same as the HPLMN corresponding to the IMSI stored in the terminal, it is determined whether the HPLMN corresponding to the IMSI stored in the terminal is in the EHPLMN list corresponding to the SIM of the terminal; if the HPLMN corresponding to the IMSI stored in the terminal is not in the EHPLMN list corresponding to the SIM of the terminal, the terminal determines a target operation; and the terminal performs the target operation on the stored first AI model.

[0148] In one embodiment, it is determined whether the HPLMN corresponding to the IMSI stored in the terminal is in the EHPLMN list corresponding to the SIM of the terminal; if the HPLMN corresponding to the IMSI stored in the terminal is not in the EHPLMN list corresponding to the SIM of the terminal, it is determined whether the HPLMN of the SIM of the terminal is the same as the HPLMN corresponding to the IMSI stored in the terminal; if the HPLMN of the SIM of the terminal is not the same as the HPLMN corresponding to the IMSI stored in the terminal, the terminal determines the target operation; the terminal performs the target operation on the stored first AI model.

[0149] In this embodiment, if the terminal does not meet the second condition, the terminal determines a target operation; the terminal performs the target operation on the stored first AI model. In this way, when the network to which the terminal's current SIM or current SIM configuration belongs is different from or not equivalent to the network to which the SIM or SIM configuration before the change belonged, the terminal determines the target operation on the stored first AI model; when the network to which the terminal's current SIM or current SIM configuration belongs is the same as or equivalent to the network to which the SIM or SIM configuration before the change belonged, the target operation is determined by the configuration of the network-side device. This improves the security of the first AI model deployed on the terminal while increasing the flexibility of managing the first AI model.

[0150] Optionally, the method further includes:

[0151] The terminal sends a first message to the network-side device, where the first message is used to report information about an AI model that can be used by the terminal;

[0152] The terminal receives a second message sent by the network side device, where the second message carries first indication information, and the first indication information is used to indicate the operation of the AI ​​model that can be used by the terminal.

[0153] In one embodiment, when a terminal satisfies a first condition, the terminal may send a first message to a network-side device. The AI ​​model available to the terminal may include a first AI model, and performing a target operation on the stored first AI model by the terminal may include performing the target operation on the stored first AI model based on the second message. Thus, the network-side device can instruct the target operation on the first AI model.

[0154] In one embodiment, when the terminal registers, the terminal can send a first message to the network side device, so that the network side device can determine the AI ​​model currently available to the terminal through the information of the available AI models reported by the terminal, thereby avoiding repeated air interface transmission of the AI ​​model and improving efficiency.

[0155] The first indication information may be an action indication or an operation indication.

[0156] In this implementation, the terminal reports information about the AI ​​model that can be used by the terminal to the network side, and the network side instructs the operation of the AI ​​model that can be used by the terminal. The network side manages the AI ​​model on the terminal side through the terminal's reporting, which can improve the security of the AI ​​model deployed on the terminal.

[0157] Optionally, the first message further carries at least one of the following: a terminal identifier; a model identifier; a message type indication;

[0158] or,

[0159] The second message also carries at least one of the following: a terminal identifier; a model identifier; and a message type indication.

[0160] The model identifier may be a model identifier of an AI model that can be used by the terminal. The message type indication may be used to indicate a message type of the first message.

[0161] Optionally, the SIM card is a pluggable SIM card, and the method further includes:

[0162] When the terminal is powered on or a SIM card is detected to be inserted or removed, determining whether the IMSI of the SIM card of the terminal is the same as the IMSI stored in the terminal;

[0163] If the IMSI of the SIM of the terminal is different from the stored IMSI, determining that the SIM of the terminal has been changed;

[0164] Among them, the SIM corresponding to the IMSI stored in the terminal is associated with the first AI model.

[0165] In addition, the SIM card of the terminal can be understood as the current SIM card of the terminal. If the IMSI of the SIM card of the terminal is the same as the stored IMSI, it can be determined that the SIM card of the terminal has not been changed. The pluggable SIM card can include a USIM card.

[0166] In this embodiment, by determining whether the IMSI of the terminal's SIM is the same as the IMSI stored in the terminal, it is possible to determine whether the terminal's SIM has changed, and then the first AI model associated with the SIM corresponding to the IMSI stored in the terminal can be processed to improve the security of the first AI model deployed on the terminal.

[0167] Optionally, the SIM card is a non-pluggable SIM card, and the method further includes:

[0168] If the terminal satisfies a third condition, the terminal determines a SIM configuration change;

[0169] The third condition includes at least one of the following:

[0170] When the first SIM configuration of the terminal is in an activated state, the terminal deactivates the first SIM configuration;

[0171] When the first SIM configuration of the terminal is in a deactivated state, the terminal activates the second SIM configuration;

[0172] The terminal deletes the first SIM configuration;

[0173] The first SIM configuration is associated with the first AI model.

[0174] The non-pluggable SIM may include an eSIM.

[0175] In one implementation, when the first SIM configuration of the terminal is in an activated state, if the terminal deactivates the first SIM configuration, it can be considered that the SIM configuration of the terminal has been changed.

[0176] In one implementation, when the first SIM configuration of the terminal is in a deactivated state, the terminal activates the second SIM configuration, which may be considered as a change in the SIM configuration of the terminal.

[0177] In one implementation, if the terminal deletes the first SIM configuration, it can be considered that the SIM configuration of the terminal has been changed.

[0178] In one implementation, when the first SIM configuration of the terminal is in an activated state, the terminal deactivates the first SIM configuration and activates the second SIM configuration, which may be considered as a change in the SIM configuration of the terminal.

[0179] In one implementation, if the terminal deletes the first SIM configuration and activates the second SIM configuration, it can be considered that the SIM configuration of the terminal has been changed.

[0180] In this implementation, by judging whether the terminal satisfies the third condition, it is possible to determine whether the SIM configuration of the terminal has changed, and then the first AI model associated with the first SIM configuration before the SIM configuration change can be processed to improve the security of the first AI model deployed on the terminal.

[0181] 5 , which is a flow chart of a model processing method provided in an embodiment of the present application. As shown in FIG5 , the model processing method includes the following steps:

[0182] Step 201: A network-side device receives a first message sent by a terminal, where the first message carries information about an AI model that can be used by the terminal.

[0183] Step 202: The network side device sends a second message to the terminal, where the second message carries first indication information, and the first indication information is used to indicate the operation of the AI ​​model that can be used by the terminal.

[0184] In an embodiment of the present application, the terminal reports information about the AI ​​model that can be used by the terminal to the network side device, and the network side device instructs operations on the AI ​​model that can be used by the terminal. The network side device manages the AI ​​model on the terminal side through the terminal's reporting, which can improve the security of the AI ​​model deployed on the terminal.

[0185] Optionally, the network-side device receiving a first message sent by a terminal includes:

[0186] When the terminal meets the first condition, the network side device receives the first message sent by the terminal;

[0187] The first condition includes at least one of the following:

[0188] The SIM card of the terminal is changed; the SIM card configuration of the terminal is changed.

[0189] Optionally, the first message further carries at least one of the following: a terminal identifier; a model identifier; a message type indication;

[0190] or

[0191] The second message also carries at least one of the following: a terminal identifier; a model identifier; and a message type indication.

[0192] It should be noted that this embodiment is an implementation of the network side device corresponding to the embodiment shown in Figure 4. Its specific implementation can refer to the relevant description of the embodiment shown in Figure 4. To avoid repetition, this embodiment will not be repeated.

[0193] The following describes the model processing method provided by the embodiments of the present application through several specific examples:

[0194] Example 1:

[0195] As shown in Figure 6, the model processing method includes the following steps:

[0196] During the transmission and deployment of the AI ​​model, the network side can configure the lifecycle management method of the AI ​​model through signaling. The specific content includes but is not limited to the model activation conditions, model discontinuation conditions, model validity period, and the handling method when it stops being used or becomes invalid. Optionally, it also includes the handling method of the AI ​​model when the terminal meets the first condition.

[0197] Step (1): When the terminal is hot-swapped or powered on (USIM hot-swapped), the IMSI of the current USIM of the terminal is compared with the IMSI stored in the non-volatile memory.

[0198] When the IMSI of the current USIM of the terminal is consistent with the IMSI stored in the non-volatile memory, there is no need to process the locally stored AI model, and step (5) is optionally performed;

[0199] When the IMSI of the current USIM of the terminal is inconsistent with the IMSI stored in the non-volatile memory, proceed to step (2).

[0200] Step (2) determines whether the HPLMN of the current USIM is consistent with the HPLMN corresponding to the IMSI stored in the non-volatile memory.

[0201] When the HPLMN of the current USIM is consistent with the HPLMN corresponding to the IMSI stored in the non-volatile memory, it can be considered that the network to which the locally stored AI model belongs has not changed. If the network side has configured the lifecycle management method of the AI ​​model for the terminal, the network side configuration is used to perform step (4); if the network side has not configured the lifecycle management method of the AI ​​model for the terminal, the terminal decides which method to use to perform step (4).

[0202] When the HPLMN of the current USIM is inconsistent with the HPLMN corresponding to the IMSI stored in the non-volatile memory, proceed to step (3).

[0203] Step (3) compares whether the HPLMN corresponding to the IMSI stored in the non-volatile memory is in the EHPLMN list of the current USIM.

[0204] When the HPLMN corresponding to the IMSI stored in the non-volatile memory is in the EHPLMN list of the current USIM, the network to which the locally stored AI model belongs can be considered equivalent to the current network. If the network side configures the lifecycle management method of the AI ​​model for the terminal, the network side configuration is used to perform step (4); if the network side does not configure the lifecycle management method of the AI ​​model for the terminal, the terminal decides which method to use to perform step (4).

[0205] When the HPLMN corresponding to the IMSI stored in the non-volatile memory is not in the EHPLMN list of the current USIM, the terminal decides which method to use to perform step (4).

[0206] It should be noted that step (2) and step (3) are optional solutions. You can only perform step (2), or only perform step (3), or not perform step (2) and step (3). The embodiment of the present application does not limit the order in which step (2) and step (3) are performed. You can perform step (2) first and then step (3), or perform step (3) first and then step (2).

[0207] Step (4): Process the AI ​​model. Methods for obtaining the processing method for the AI ​​model include, but are not limited to: configuration via signaling on the network side, default processing methods on the network side and the terminal side, and customized behavior on the terminal side. The AI ​​model can be processed at a (per)PLMN level or a per AI model level.

[0208] Step (5): During the registration process, the terminal may optionally report the AI ​​model, so that the network side can further decide whether it is necessary to process the AI ​​model stored locally on the terminal. The message sent by the terminal to report the AI ​​model may carry at least one of the terminal identifier, model identifier, and message type; the message sent by the network side to the terminal may carry at least one of the terminal identifier, model identifier, message type, and action indication. The action indication includes but is not limited to: deletion, backup, and use. When the action indication includes use, the message sent by the network side to the terminal may also carry the use key and validity period; when the action indication includes backup, the message sent by the network side to the terminal may also carry the AI ​​model context.

[0209] It should be noted that the USIM can be equipped with a model key, which represents the model usage rights issued by the operator to the USIM for the AI ​​model. A USIM equipped with a model key can match the unlocking key required by the AI ​​model when the card is first inserted. This is similar to the model's PIN code, and the model key can protect the security of the model.

[0210] In one implementation, a USIM that is not set with a model key corresponding to the AI ​​model cannot use the AI ​​model.

[0211] In one embodiment, when the USIM cannot access the AI ​​model through the model key, it can also obtain the right to use the AI ​​model by interacting with the network. For example, the terminal sends a request message (such as a registration request) to the network side, carrying information such as the model identifier (model ID), the terminal identifier (such as the Subscription Permanent Identifier (SUPI)), etc.; after the network side sends the request message, the AMF requests the UDM for the model usage permission of the SUPI, and sends a response message to the terminal, which carries the key to allow the terminal to use the AI ​​model; if the terminal is not allowed to use the AI ​​model, the response message can carry indication information to indicate that the terminal is denied use of the AI ​​model, and can also instruct the terminal to delete the AI ​​model, so as to protect the security of the AI ​​model.

[0212] Example 2:

[0213] As shown in Figure 7, the model processing method includes the following steps:

[0214] If the eSIM of the terminal changes its profile, events 1 and 2 in FIG7 will occur. Therefore, the processing when event 2 occurs is the same as steps (1) to (5) in embodiment 1.

[0215] Optionally, event 3 may occur at the terminal, and event 3 may occur between event 1 and event 2, or may occur after event 2.

[0216] Optionally, when event 1 or event 3 occurs at the terminal, the terminal may process the AI ​​model.

[0217] Processing of the AI ​​model includes but is not limited to retaining, deleting, using AI model context management and switching, or combining AI context switching with deletion.

[0218] Example 3:

[0219] The methods for processing the AI ​​model in Example 1 and Example 2 include the following methods:

[0220] Method 1: Delete

[0221] To delete an AI model, you can use the following methods:

[0222] Direct deletion; or

[0223] Start the timer and delete it when the timer expires.

[0224] Method 2: Backup

[0225] The terminal determines the number of AI model contexts based on its own storage capacity. Optionally, the terminal can report the number of supported contexts during the access process.

[0226] When backing up the AI ​​model,

[0227] The terminal sets the current AI model context to the INACTIVE state and switches the AI ​​model context;

[0228] Traverse all AI model contexts in the INACTIVE state. If there is an AI model context whose IMSI is the same as the IMSI of the current SIM, set the AI ​​model context state to ACTIVE.

[0229] The AI ​​model context includes but is not limited to the following:

[0230] IMSI; context status (ACTIVE or INACTIVE); PLMN; model list; AI model identifier; model storage path; model lifecycle parameters; model usage status; model information.

[0231] Method 3: Combining AI context switching and deletion

[0232] When the AI ​​model context state changes to INACTIVE, a timer is started. When the timer times out, the AI ​​model context is deleted.

[0233] Method 4: Retain or securely process key information

[0234] The terminal's USIM or eSIM Profile may contain model key information. When the model key information is included, the terminal uses the model key information to perform secure processing on the AI ​​model.

[0235] Once the security processing is passed, the corresponding AI model can be retained, indicating that the AI ​​model can be used.

[0236] Otherwise, it can be processed in any of the following ways: Method 1 to Method 3.

[0237] It should be noted that if the terminal's USIM or the eSIM's Profile contains model key information, the processing priority of method 4 is higher than methods 1 to 3.

[0238] When using the AI ​​model context for management, the terminal can update the retained model information to the AI ​​model context corresponding to the current IMSI, and perform the AI ​​model reporting process of step (5) in Example 1 in the subsequent signaling process.

[0239] Method 5: Temporarily retain

[0240] The terminal does not process the AI ​​model for the time being and executes the AI ​​model reporting process of step (5) in Example 1. The network side decides how to process the AI ​​model.

[0241] In the embodiment of the present application, for a terminal using a USIM, when the terminal is powered on or the USIM is plugged in or out, it is determined whether the USIM has been replaced, and how to manage the locally stored AI model is determined by comparing the HPLMN corresponding to the IMSI stored in the non-volatile memory with the current HPLMN or EHPLMN, and by operating the model key information.

[0242] In an embodiment of the present application, for a terminal device using an eSIM, when a profile is deactivated, a decision is made on how to manage the locally stored AI model based on information such as whether other profiles are activated and whether the two profiles belong to the same PLMN.

[0243] An embodiment of the present application proposes a method for managing an AI model stored in a terminal when the USIM is plugged in or out or the profile status of the eSIM changes. Through this embodiment of the present application, the security of the AI ​​model can be protected and repeated transmission of the model can be avoided as much as possible.

[0244] The model processing method provided in the embodiment of the present application can be executed by a model processing device. In the embodiment of the present application, the model processing device provided in the embodiment of the present application is described by taking the execution of the model processing method by the model processing device as an example.

[0245] Please refer to FIG8 , which is a structural diagram of a model processing device provided in an embodiment of the present application. The terminal includes the model processing device. As shown in FIG8 , the model processing device 300 includes:

[0246] An operation module 301 is configured to perform a target operation on a stored first artificial intelligence (AI) model when the terminal satisfies a first condition;

[0247] The first condition includes at least one of the following:

[0248] The subscriber identity module (SIM) of the terminal is changed; the SIM configuration of the terminal is changed.

[0249] Optionally, the target operation includes at least one of the following:

[0250] Retention or deletion;

[0251] Update the state of the AI ​​model context, or delete the AI ​​model context;

[0252] Secure processing based on key information.

[0253] Optionally, the deletion process includes any one of the following:

[0254] Deleting the first AI model;

[0255] A first timer is started, and when the first timer times out, the first AI model is deleted.

[0256] Optionally, updating the state of the AI ​​model context includes:

[0257] When the context state of the first AI model is an activated state, updating the context state of the first AI model to an inactivated state;

[0258] When the context state of the second AI model stored in the terminal is in an inactive state, if the international mobile subscriber identity IMSI contained in the context of the second AI model is the same as the IMSI of the SIM of the terminal, the context state of the second AI model is updated to an active state.

[0259] Optionally, deleting the AI ​​model context includes:

[0260] When the context state of the first AI model changes to an inactive state, starting a second timer;

[0261] When the second timer times out, the context of the first AI model is deleted.

[0262] Optionally, the performing security processing based on the key information includes:

[0263] In a case where the first AI model is associated with the first key information, the terminal matches the first key information associated with the first AI model with the second key information associated with the SIM of the terminal;

[0264] When the first key information matches the second key information successfully, the terminal retains the first AI model.

[0265] Optionally, the device further comprises:

[0266] A storage module is configured to store the model information of the first AI model in the AI ​​model context corresponding to the IMSI of the SIM of the terminal when the terminal retains the first AI model.

[0267] Optionally, the operation module is specifically configured to:

[0268] When the terminal satisfies the second condition, if the terminal obtains first configuration information, performing a target operation on the stored first AI model based on the first configuration information, where the first configuration information is configuration information configured by a network-side device for the terminal to manage the first AI model;

[0269] The second condition includes at least one of the following:

[0270] The Home Public Land Mobile Network (HPLMN) of the terminal's SIM is the same as the HPLMN corresponding to the IMSI stored in the terminal;

[0271] The HPLMN corresponding to the IMSI stored in the terminal is in the Equivalent Local Public Land Mobile Network EHPLMN list corresponding to the SIM of the terminal.

[0272] Optionally, the operation module is specifically configured to:

[0273] If the terminal does not meet the second condition, determining a target operation;

[0274] The target operation is performed on the stored first AI model.

[0275] Optionally, the device further comprises:

[0276] A sending module, configured to send a first message to a network-side device, where the first message is used to report information about an AI model that can be used by the terminal;

[0277] A receiving module is used to receive a second message sent by the network side device, where the second message carries first indication information, and the first indication information is used to indicate the operation of the AI ​​model that can be used by the terminal.

[0278] Optionally, the first message further carries at least one of the following: a terminal identifier; a model identifier; a message type indication;

[0279] or

[0280] The second message also carries at least one of the following: a terminal identifier; a model identifier; and a message type indication.

[0281] Optionally, the SIM card is a pluggable SIM card, and the device further includes:

[0282] A first determining module is configured to determine whether the IMSI of the SIM card of the terminal is the same as the IMSI stored in the terminal when the terminal is powered on or a SIM card insertion or removal is detected;

[0283] A second determining module is configured to determine a SIM change of the terminal when the IMSI of the SIM of the terminal is different from the stored IMSI;

[0284] Among them, the SIM corresponding to the IMSI stored in the terminal is associated with the first AI model.

[0285] Optionally, the SIM card is a non-pluggable SIM card, and the device further includes:

[0286] A third determining module, configured to determine a SIM configuration change when the terminal satisfies a third condition;

[0287] The third condition includes at least one of the following:

[0288] When the first SIM configuration of the terminal is in an activated state, the terminal deactivates the first SIM configuration;

[0289] When the first SIM configuration of the terminal is in a deactivated state, the terminal activates the second SIM configuration;

[0290] The terminal deletes the first SIM configuration;

[0291] The first SIM configuration is associated with the first AI model.

[0292] The model processing device in the embodiment of the present application can be an electronic device, such as an electronic device with an operating system, or a component in an electronic device, such as an integrated circuit or chip. The electronic device can be a terminal, or it can be other devices other than a terminal. For example, the terminal can include but is not limited to the types of terminal 11 listed above, and other devices can be servers, network attached storage (NAS), etc., which are not specifically limited in the embodiment of the present application.

[0293] The model processing device provided in the embodiment of the present application can implement each process implemented in the method embodiment of Figure 4 and achieve the same technical effect. To avoid repetition, it will not be described here.

[0294] Please refer to FIG9 , which is a structural diagram of a model processing device provided in an embodiment of the present application. The network-side device includes the model processing device. As shown in FIG9 , the model processing device 400 includes:

[0295] A receiving module 401 is configured to receive a first message sent by a terminal, where the first message carries information about an AI model that can be used by the terminal;

[0296] The sending module 402 is used to send a second message to the terminal, where the second message carries first indication information, and the first indication information is used to indicate the operation of the AI ​​model that can be used by the terminal.

[0297] Optionally, the receiving module is specifically configured to:

[0298] When the terminal meets the first condition, receiving a first message sent by the terminal;

[0299] The first condition includes at least one of the following:

[0300] The SIM card of the terminal is changed; the SIM card configuration of the terminal is changed.

[0301] Optionally, the first message further carries at least one of the following: a terminal identifier; a model identifier; a message type indication;

[0302] or

[0303] The second message also carries at least one of the following: a terminal identifier; a model identifier; and a message type indication.

[0304] The model processing device in the embodiment of the present application can be an electronic device, such as an electronic device with an operating system, or a component in an electronic device, such as an integrated circuit or chip. The electronic device can be a terminal, or it can be other devices other than a terminal. For example, the terminal can include but is not limited to the types of terminal 11 listed above, and other devices can be servers, network attached storage (NAS), etc., which are not specifically limited in the embodiment of the present application.

[0305] The model processing device provided in the embodiment of the present application can implement each process implemented in the method embodiment of Figure 5 and achieve the same technical effect. To avoid repetition, it will not be described here.

[0306] Optionally, as shown in Figure 10, an embodiment of the present application further provides a communication device 500, including a processor 501 and a memory 502, wherein the memory 502 stores a program or instruction that can be run on the processor 501. For example, when the communication device 500 is a terminal, the program or instruction is executed by the processor 501 to implement the various steps of the above-mentioned embodiment of the model processing method applied to the terminal, and can achieve the same technical effect. To avoid repetition, it is not repeated here. When the communication device 500 is a network-side device, the program or instruction is executed by the processor 501 to implement the various steps of the above-mentioned embodiment of the model processing method applied to the network-side device, and can achieve the same technical effect. To avoid repetition, it is not repeated here.

[0307] The present application also provides a terminal including a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is configured to execute a program or instruction to implement the steps in the method embodiment shown in FIG4 . This terminal embodiment corresponds to the above-mentioned terminal-side method embodiment, and each implementation process and implementation method of the above-mentioned method embodiment are applicable to this terminal embodiment and can achieve the same technical effects.

[0308] Specifically, FIG11 is a schematic diagram of the hardware structure of a terminal implementing an embodiment of the present application.

[0309] The terminal 600 includes but is not limited to: a radio frequency unit 601, a network module 602, an audio output unit 603, an input unit 604, a sensor 605, a display unit 606, a user input unit 607, an interface unit 608, a memory 609 and at least some of the components of the processor 610.

[0310] Those skilled in the art will appreciate that the terminal 600 may also include a power supply (such as a battery) to power various components. The power supply may be logically connected to the processor 610 via a power management system, thereby enabling the power management system to manage charging, discharging, and power consumption. The terminal structure shown in FIG11 does not limit the terminal. The terminal may include more or fewer components than shown, or may combine certain components, or have different component arrangements, which will not be described in detail here.

[0311] It should be understood that in an embodiment of the present application, the input unit 604 may include a graphics processing unit (GPU) 6041 and a microphone 6042, and the GPU 6041 processes the image data of a static picture or video obtained by an image capture device (such as a camera) in a video capture mode or an image capture mode. The display unit 606 may include a display panel 6061, and the display panel 6061 may be configured in the form of a liquid crystal display, an organic light emitting diode, etc. The user input unit 607 includes a touch panel 6071 and at least one of other input devices 6072. The touch panel 6071 is also called a touch screen. The touch panel 6071 may include two parts: a touch detection device and a touch controller. Other input devices 6072 may include, but are not limited to, a physical keyboard, function keys (such as volume control keys, switch keys, etc.), a trackball, a mouse, and an operating stick, which will not be repeated here.

[0312] In the embodiment of the present application, after receiving downlink data from a network-side device, the radio frequency unit 601 may transmit the data to the processor 610 for processing. Furthermore, the radio frequency unit 601 may send uplink data to the network-side device. Typically, the radio frequency unit 601 includes, but is not limited to, an antenna, an amplifier, a transceiver, a coupler, a low-noise amplifier, a duplexer, and the like.

[0313] The memory 609 can be used to store software programs or instructions and various data. The memory 609 may mainly include a first storage area for storing programs or instructions and a second storage area for storing data, wherein the first storage area may store an operating system, applications or instructions required for at least one function (such as a sound playback function, an image playback function, etc.). In addition, the memory 609 may include a volatile memory or a non-volatile memory, or the memory 609 may include both volatile and non-volatile memories. Among them, the non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may be a random access memory (RAM), a static random access memory (SRAM), a dynamic random access memory (DRAM), a synchronous dynamic random access memory (SDRAM), a double data rate synchronous dynamic random access memory (DDRSDRAM), an enhanced synchronous dynamic random access memory (ESDRAM), a synchronous link dynamic random access memory (SLDRAM), and a direct memory bus random access memory (DRRAM). The memory 609 in the embodiment of the present application includes but is not limited to these and any other suitable types of memory.

[0314] Processor 610 may include one or more processing units. Optionally, processor 610 integrates an application processor and a modem processor. The application processor primarily handles operations related to the operating system, user interface, and application programs, while the modem processor primarily processes wireless communication signals, such as a baseband processor. It is understood that the modem processor may not be integrated into processor 610.

[0315] The processor 610 is configured to:

[0316] When the terminal meets the first condition, performing a target operation on the stored first artificial intelligence AI model;

[0317] The first condition includes at least one of the following:

[0318] The subscriber identity module (SIM) of the terminal is changed; the SIM configuration of the terminal is changed.

[0319] Optionally, the target operation includes at least one of the following:

[0320] Retention or deletion;

[0321] Update the state of the AI ​​model context, or delete the AI ​​model context;

[0322] Secure processing based on key information.

[0323] Optionally, the deletion process includes any one of the following:

[0324] Deleting the first AI model;

[0325] A first timer is started, and when the first timer times out, the first AI model is deleted.

[0326] Optionally, updating the state of the AI ​​model context includes:

[0327] When the context state of the first AI model is an activated state, updating the context state of the first AI model to an inactivated state;

[0328] When the context state of the second AI model stored in the terminal is in an inactive state, if the international mobile subscriber identity IMSI contained in the context of the second AI model is the same as the IMSI of the SIM of the terminal, the context state of the second AI model is updated to an active state.

[0329] Optionally, deleting the AI ​​model context includes:

[0330] When the context state of the first AI model changes to an inactive state, starting a second timer;

[0331] When the second timer times out, the context of the first AI model is deleted.

[0332] Optionally, the performing security processing based on the key information includes:

[0333] In a case where the first AI model is associated with the first key information, the terminal matches the first key information associated with the first AI model with the second key information associated with the SIM of the terminal;

[0334] When the first key information matches the second key information successfully, the terminal retains the first AI model.

[0335] Optionally, the processor 610 is further configured to:

[0336] In a case where the terminal retains the first AI model, the model information of the first AI model is stored in the AI ​​model context corresponding to the IMSI of the SIM of the terminal.

[0337] Optionally, the processor 610 is specifically configured to:

[0338] When the terminal satisfies the second condition, if the terminal obtains first configuration information, performing a target operation on the stored first AI model based on the first configuration information, where the first configuration information is configuration information configured by a network-side device for the terminal to manage the first AI model;

[0339] The second condition includes at least one of the following:

[0340] The Home Public Land Mobile Network (HPLMN) of the terminal's SIM is the same as the HPLMN corresponding to the IMSI stored in the terminal;

[0341] The HPLMN corresponding to the IMSI stored in the terminal is in the Equivalent Local Public Land Mobile Network EHPLMN list corresponding to the SIM of the terminal.

[0342] Optionally, the processor 610 is specifically configured to:

[0343] If the terminal does not meet the second condition, determining a target operation;

[0344] The target operation is performed on the stored first AI model.

[0345] Optionally, the radio frequency unit 601 is configured to:

[0346] Sending a first message to a network-side device, where the first message is used to report information about an AI model that can be used by the terminal;

[0347] Receive a second message sent by the network side device, where the second message carries first indication information, and the first indication information is used to indicate the operation of the AI ​​model that can be used by the terminal.

[0348] Optionally, the first message further carries at least one of the following: a terminal identifier; a model identifier; a message type indication;

[0349] or

[0350] The second message also carries at least one of the following: a terminal identifier; a model identifier; and a message type indication.

[0351] Optionally, the SIM card is a pluggable SIM card, and the processor 610 is configured to:

[0352] When the terminal is powered on or a SIM card is detected to be inserted or removed, determining whether the IMSI of the SIM card of the terminal is the same as the IMSI stored in the terminal;

[0353] If the IMSI of the SIM of the terminal is different from the stored IMSI, determining that the SIM of the terminal has been changed;

[0354] Among them, the SIM corresponding to the IMSI stored in the terminal is associated with the first AI model.

[0355] Optionally, the SIM card is a non-pluggable SIM card, and the processor 610 is configured to:

[0356] If the terminal satisfies a third condition, determining a SIM configuration change;

[0357] The third condition includes at least one of the following:

[0358] When the first SIM configuration of the terminal is in an activated state, the terminal deactivates the first SIM configuration;

[0359] When the first SIM configuration of the terminal is in a deactivated state, the terminal activates the second SIM configuration;

[0360] The terminal deletes the first SIM configuration;

[0361] The first SIM configuration is associated with the first AI model.

[0362] It can be understood that the implementation process of each implementation method mentioned in this embodiment can refer to the relevant description of the method embodiment Figure 4, and achieve the same or corresponding technical effects. To avoid repetition, it will not be repeated here.

[0363] Specifically, the terminal of the embodiment of the present application also includes: instructions or programs stored in the memory 609 and executable on the processor 610. The processor 610 calls the instructions or programs in the memory 609 to execute the methods of the modules shown in FIG8 and achieve the same technical effect. To avoid repetition, it will not be described here.

[0364] The present application also provides a network-side device, including a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is configured to execute a program or instruction to implement the steps of the method embodiment shown in FIG5 . This network-side device embodiment corresponds to the above-mentioned model processing method embodiment applied to a core network device, and each implementation process and implementation method of the above-mentioned method embodiment are applicable to this network-side device embodiment and can achieve the same technical effects.

[0365] Specifically, embodiments of the present application also provide a network-side device. As shown in Figure 12, the network-side device 700 includes an antenna 701, a radio frequency device 702, a baseband device 703, a processor 704, and a memory 705. Antenna 701 is connected to radio frequency device 702. In the uplink direction, radio frequency device 702 receives information via antenna 701 and sends the received information to baseband device 703 for processing. In the downlink direction, baseband device 703 processes the information to be transmitted and sends it to radio frequency device 702. Radio frequency device 702 processes the received information and then sends it through antenna 701.

[0366] The method executed by the network-side device in the above embodiment may be implemented in the baseband device 703 , which includes a baseband processor.

[0367] The baseband device 703 may include, for example, at least one baseband board, on which multiple chips are arranged, as shown in Figure 12, one of which is, for example, a baseband processor, which is connected to the memory 705 through a bus interface to call the program in the memory 705 and execute the network device operations shown in the above method embodiment.

[0368] The network side device may further include a network interface 706 , which is, for example, a Common Public Radio Interface (CPRI).

[0369] Specifically, the network side device 700 of the embodiment of the present application also includes: instructions or programs stored in the memory 705 and can be run on the processor 704. The processor 704 calls the instructions or programs in the memory 705 to execute the method of execution of each module shown in Figure 9 and achieve the same technical effect. To avoid repetition, it will not be repeated here.

[0370] An embodiment of the present application also provides a readable storage medium, on which a program or instruction is stored. When the program or instruction is executed by a processor, the various processes of the above-mentioned model processing method embodiment are implemented and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

[0371] The processor is the processor in the terminal or network-side device described in the above embodiments. The readable storage medium includes a computer-readable storage medium, such as a computer read-only memory (ROM), random access memory (RAM), a magnetic disk, or an optical disk. In some examples, the readable storage medium may be a non-transitory readable storage medium.

[0372] An embodiment of the present application further provides a chip, which includes a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is used to run programs or instructions to implement the various processes of the above-mentioned model processing method embodiment, and can achieve the same technical effect. To avoid repetition, it will not be repeated here.

[0373] It should be understood that the chip mentioned in the embodiments of the present application can also be called a system-level chip, a system chip, a chip system or a system-on-chip chip, etc.

[0374] An embodiment of the present application further provides a computer program / program product, which is stored in a storage medium. The computer program / program product is executed by at least one processor to implement the various processes of the above-mentioned model processing method embodiment and can achieve the same technical effect. To avoid repetition, it will not be repeated here.

[0375] An embodiment of the present application also provides a model processing system, including: a terminal and a network side device, wherein the terminal can be used to execute the steps of the model processing method applied to the terminal as described above, and the network side device can be used to execute the steps of the model processing method applied to the network side device as described above.

[0376] It should be noted that, in this article, the terms "comprise", "include" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprises a..." does not exclude the presence of other identical elements in the process, method, article or device comprising the element. In addition, it should be noted that the scope of the methods and devices in the embodiments of the present application is not limited to performing functions in the order shown or discussed, and may also include performing functions in a substantially simultaneous manner or in the opposite order according to the functions involved. For example, the described method may be performed in an order different from that described, and various steps may also be added, omitted or combined. In addition, the features described with reference to certain examples may be combined in other examples.

[0377] Through the description of the above embodiments, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of a computer software product plus a necessary general hardware platform, or of course, by hardware. The computer software product is stored in a storage medium (such as ROM, RAM, magnetic disk, optical disk, etc.) and includes a number of instructions for causing a terminal or network-side device to execute the methods described in each embodiment of the present application.

[0378] The embodiments of the present application are described above in conjunction with the accompanying drawings, but the present application is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the guidance of this application, ordinary technicians in this field can also make many forms of implementation methods without departing from the purpose of this application and the scope of protection of the claims. These implementation methods are all within the protection of this application.

Claims

1. A model processing method, comprising: When the terminal meets the first condition, the terminal performs a target operation on the stored first artificial intelligence AI model; The first condition includes at least one of the following: The subscriber identity module (SIM) of the terminal is changed; the SIM configuration of the terminal is changed.

2. The method according to claim 1, wherein The target operation includes at least one of the following: Retention or deletion; Update the state of the AI ​​model context, or delete the AI ​​model context; Secure processing based on key information.

3. The method according to claim 2, wherein: The deletion process includes any of the following: Deleting the first AI model; A first timer is started, and when the first timer times out, the first AI model is deleted.

4. The method according to claim 2 or 3, wherein: Updating the state of the AI ​​model context includes: When the context state of the first AI model is an activated state, updating the context state of the first AI model to an inactivated state; When the context state of the second AI model stored in the terminal is in an inactive state, if the international mobile subscriber identity IMSI contained in the context of the second AI model is the same as the IMSI of the SIM of the terminal, the context state of the second AI model is updated to an active state.

5. The method according to any one of claims 2 to 4, wherein Deleting the AI ​​model context includes: When the context state of the first AI model changes to an inactive state, starting a second timer; When the second timer times out, the context of the first AI model is deleted.

6. The method according to any one of claims 2 to 5, wherein: The security processing based on the key information includes: In a case where the first AI model is associated with the first key information, the terminal matches the first key information associated with the first AI model with the second key information associated with the SIM of the terminal; When the first key information matches the second key information successfully, the terminal retains the first AI model.

7. The method according to any one of claims 2 to 6, further comprising: In a case where the terminal retains the first AI model, the terminal stores the model information of the first AI model in the AI ​​model context corresponding to the IMSI of the SIM of the terminal.

8. The method according to any one of claims 1 to 7, wherein The terminal performs a target operation on the stored first AI model, including: When the terminal satisfies the second condition, if the terminal obtains first configuration information, the terminal performs a target operation on the stored first AI model based on the first configuration information, where the first configuration information is configuration information configured by a network-side device for the terminal to manage the first AI model; The second condition includes at least one of the following: The Home Public Land Mobile Network (HPLMN) of the terminal's SIM is the same as the HPLMN corresponding to the IMSI stored in the terminal; The HPLMN corresponding to the IMSI stored in the terminal is in the Equivalent Local Public Land Mobile Network EHPLMN list corresponding to the SIM of the terminal.

9. The method according to claim 8, wherein The terminal performs a target operation on the stored first AI model, further comprising: If the terminal does not meet the second condition, the terminal determines a target operation; The terminal performs the target operation on the stored first AI model.

10. The method according to any one of claims 1 to 9, further comprising: The terminal sends a first message to the network-side device, where the first message is used to report information about an AI model that can be used by the terminal; The terminal receives a second message sent by the network side device, where the second message carries first indication information, and the first indication information is used to indicate the operation of the AI ​​model that can be used by the terminal.

11. The method according to claim 10, wherein: The first message also carries at least one of the following: a terminal identifier; a model identifier; a message type indication; or, The second message also carries at least one of the following: a terminal identifier; a model identifier; and a message type indication.

12. The method according to any one of claims 1 to 11, wherein The SIM card is a pluggable SIM card, and the method further includes: When the terminal is powered on or a SIM card is detected to be inserted or removed, determining whether the IMSI of the SIM card of the terminal is the same as the IMSI stored in the terminal; If the IMSI of the SIM of the terminal is different from the stored IMSI, determining that the SIM of the terminal has been changed; Among them, the SIM corresponding to the IMSI stored in the terminal is associated with the first AI model.

13. The method according to any one of claims 1 to 11, wherein The SIM card is a non-pluggable SIM card, and the method further includes: If the terminal satisfies a third condition, the terminal determines a SIM configuration change; The third condition includes at least one of the following: When the first SIM configuration of the terminal is in an activated state, the terminal deactivates the first SIM configuration; When the first SIM configuration of the terminal is in a deactivated state, the terminal activates the second SIM configuration; The terminal deletes the first SIM configuration; The first SIM configuration is associated with the first AI model.

14. A model processing method comprising: The network-side device receives a first message sent by the terminal, where the first message carries information about an AI model that can be used by the terminal; The network side device sends a second message to the terminal, where the second message carries first indication information, and the first indication information is used to indicate the operation of the AI ​​model that can be used by the terminal.

15. The method according to claim 14, wherein The network side device receives a first message sent by the terminal, including: When the terminal meets the first condition, the network side device receives the first message sent by the terminal; The first condition includes at least one of the following: The SIM card of the terminal is changed; the SIM card configuration of the terminal is changed.

16. The method according to claim 14 or 15, wherein: The first message also carries at least one of the following: a terminal identifier; a model identifier; a message type indication; or, The second message also carries at least one of the following: a terminal identifier; a model identifier; and a message type indication.

17. A model processing device comprising: An operation module, configured to perform a target operation on the stored first artificial intelligence (AI) model when the terminal meets a first condition; The first condition includes at least one of the following: The subscriber identity module (SIM) of the terminal is changed; the SIM configuration of the terminal is changed.

18. The device according to claim 17, wherein The target operation includes at least one of the following: Retention or deletion; Update the state of the AI ​​model context, or delete the AI ​​model context; Secure processing based on key information.

19. The device according to claim 18, wherein The deletion process includes any of the following: Deleting the first AI model; A first timer is started, and when the first timer times out, the first AI model is deleted.

20. The device according to claim 18 or 19, wherein Updating the state of the AI ​​model context includes: When the context state of the first AI model is an activated state, updating the context state of the first AI model to an inactivated state; When the context state of the second AI model stored in the terminal is in an inactive state, if the international mobile subscriber identity IMSI contained in the context of the second AI model is the same as the IMSI of the SIM of the terminal, the context state of the second AI model is updated to an active state.

21. The apparatus according to any one of claims 17 to 20, further comprising: A sending module, configured to send a first message to a network-side device, where the first message is used to report information about an AI model that can be used by the terminal; A receiving module is used to receive a second message sent by the network side device, where the second message carries first indication information, and the first indication information is used to indicate the operation of the AI ​​model that can be used by the terminal.

22. A model processing device comprising: a receiving module, configured to receive a first message sent by a terminal, where the first message carries information about an AI model that can be used by the terminal; A sending module is used to send a second message to the terminal, where the second message carries first indication information, and the first indication information is used to indicate the operation of the AI ​​model that can be used by the terminal.

23. A communication device comprising a processor and a memory, wherein the memory stores a program or instruction that can be run on the processor, and when the program or instruction is executed by the processor, the steps of the model processing method according to any one of claims 1 to 13 are implemented, or the steps of the model processing method according to any one of claims 14 to 16 are implemented.

24. A chip comprising a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is configured to execute a program or instruction to implement the steps of the model processing method according to any one of claims 1 to 13, or to implement the steps of the model processing method according to any one of claims 14 to 16.

25. A readable storage medium storing a program or instruction, wherein the program or instruction, when executed by a processor, implements the steps of the model processing method according to any one of claims 1 to 13, or implements the steps of the model processing method according to any one of claims 14 to 16.

26. A computer program / program product, which, when executed by at least one processor, implements the steps of the model processing method according to any one of claims 1 to 13, or implements the steps of the model processing method according to any one of claims 14 to 16.

Images