Model updating method and device, storage medium, terminal, network side equipment

Abstract

A model updating method and device, a storage medium, a terminal, and a network side device, wherein the method includes: determining whether a locally deployed model needs to be updated; if the determination result is yes, cooperating with the network to update the locally deployed model. The solution provided by the present invention enables the UE to trigger the model updating process when determining that a locally deployed model needs to be updated, and to perform data interaction with the network side to complete the update of the UE's locally deployed model.

Description

Technical Field

[0001] The present invention relates to the field of communications, and in particular to a model updating method and device, a storage medium, a terminal, and a network side device. Background Art

[0002] Artificial Intelligence (AI) technology is a means to accelerate the intelligentization of communication networks. The generalization ability of current AI models is limited, that is, in certain scenarios and conditions, the application of AI can make traditional communication network functions gain compared with traditional methods; however, in other cases, AI performance may deteriorate or even be lower than the performance of traditional communication network methods. Therefore, AI models also need to be updated to adapt to the changing network environment, capture the latest AI technology achievements, and then improve model accuracy, ensure model performance and introduce new functional features.

[0003] The AI ​​model deployed on the terminal side is subject to the limited training, reasoning and storage capabilities of the terminal. When the performance of the AI ​​model deteriorates, it is sometimes unable to complete the model update process by itself. At this time, the network needs to assist the terminal to complete the model update. Therefore, it is necessary to define the conditions for triggering model updates and design the model update process. However, in the prior art, there are no conditions for triggering model updates and corresponding model update processes. Summary of the invention

[0004] The technical problem solved by the present invention is how to provide conditions for triggering model update and the corresponding model update process.

[0005] To solve the above problems, an embodiment of the present invention provides a model updating method, which includes: determining whether the locally deployed model needs to be updated; if the determination result is yes, updating the locally deployed model in cooperation with the network.

[0006] Optionally, before determining whether the locally deployed model needs to be updated, it also includes: obtaining attribute information of the locally deployed model; determining whether the locally deployed model needs to be updated includes: determining whether the locally deployed model needs to be updated based on the attribute information; cooperating with the network to update the locally deployed model includes: initiating a model update process to the network to interact with the network for update data, and the update data is used to update the locally deployed model.

[0007] Optionally, the attribute information includes at least one of the following: a model identifier, a model version number, a model validity period, a model type, a model volume, and a model accuracy.

[0008] Optionally, before determining whether the locally deployed model needs to be updated, the method further includes: receiving model information sent by the network, the model information including at least one of a model identifier, a model version number, a model validity period, a model type, a model volume, and a model accuracy; determining whether the locally deployed model needs to be updated based on the attribute information, further includes: comparing the model information with the attribute information to determine whether an updated model exists on the network, and when an updated model exists on the network, the locally deployed model needs to be updated.

[0009] Optionally, when the attribute information includes the validity period of the model, the determining whether the locally deployed model needs to be updated further includes: when the validity period of the model expires, the locally deployed model needs to be updated.

[0010] Optionally, before determining whether the locally deployed model needs to be updated, the method further includes: detecting the performance of the locally deployed model; and determining whether the locally deployed model needs to be updated, the method further includes: when the performance of the locally deployed model is lower than an expected threshold, the locally deployed model needs to be updated.

[0011] Optionally, the expected threshold is received from a network or acquired locally.

[0012] Optionally, the judgment of whether the locally deployed model needs to be updated includes: when a model update instruction sent by the network is received, the judgment result is yes; wherein the model update instruction is an instruction sent to the terminal when the network determines that the model deployed by the terminal needs to be updated; the cooperation with the network to update the locally deployed model includes: interacting with the network for update data, and the update data is used to update the locally deployed model.

[0013] Optionally, the method further includes: sending relevant information of the locally deployed model to the network; wherein the relevant information enables the network to determine whether the model deployed by the terminal that sends the relevant information needs to be updated.

[0014] Optionally, the relevant information may exist in the RRC signaling, or in a NAS container of the RRC signaling, or in a non-NAS container of the RRC signaling.

[0015] Optionally, when reporting the measurement report to the network, the relevant information is also reported.

[0016] Optionally, if in a non-connected state, the model update instruction is carried through a paging message or a system message. After receiving the model update instruction sent by the network, it also includes: switching from a non-connected state to a connected state to cooperate with the network to update the locally deployed model; after completing the update of the locally deployed model, restoring the original non-connected state.

[0017] Optionally, if in a connected state, the model update instruction is carried via RRC signaling.

[0018] An embodiment of the present invention further provides a model updating method, the method comprising: determining whether it is necessary to update the model deployed on the terminal; if the determination result is yes, updating the model deployed on the terminal in cooperation with the terminal.

[0019] Optionally, the method also includes: if a model update process initiated by the terminal is received, determining that the model deployed on the terminal needs to be updated; cooperating with the terminal to update the model deployed on the terminal includes: interacting with the terminal for update data, the update data being used to update the model locally deployed on the terminal; wherein, if the terminal determines that the locally deployed model needs to be updated based on attribute information of the locally deployed model, the model update process is initiated.

[0020] Optionally, the attribute information includes at least one of the following: a model identifier, a model version number, a model validity period, a model type, a model volume, and a model accuracy.

[0021] Optionally, the method further includes: sending model information to the terminal so that the terminal compares the model information with the attribute information and determines whether there is an updated model in the network; when there is an updated model in the network, the terminal determines that the locally deployed model needs to be updated; wherein the model information includes at least one of a model identifier, a model version number, a model validity period, a model type, a model volume, and a model accuracy.

[0022] Optionally, when the validity period of the model expires, the terminal determines that the model deployed on the terminal needs to be updated.

[0023] Optionally, when the terminal detects that the performance of the locally deployed model is lower than an expected threshold, the terminal determines that the locally deployed model needs to be updated.

[0024] Optionally, the method further includes: sending the expected threshold to the terminal.

[0025] Optionally, if the judgment result is yes, cooperating with the terminal to update the model deployed on the terminal includes: if the judgment result is yes, sending a model update instruction to the terminal so that the terminal determines that its locally deployed model needs to be updated; cooperating with the terminal to update the model deployed on the terminal includes: interacting with the terminal to update data, and the update data is used to update the model locally deployed on the terminal.

[0026] Optionally, the method further includes: receiving relevant information of the locally deployed model sent by the terminal; and judging whether the model deployed by the terminal needs to be updated includes: determining whether the model deployed by the terminal needs to be updated based on the relevant information.

[0027] Optionally, the relevant information may exist in the RRC signaling, or in a NAS container of the RRC signaling, or in a non-NAS container of the RRC signaling.

[0028] Optionally, when the terminal reports the measurement report, the relevant information is also reported.

[0029] Optionally, if the terminal is in a non-connected state, the model update instruction is carried through a paging message or a system message to cause the terminal to switch from a non-connected state to a connected state, and after completing the update of the model locally deployed on the terminal, the terminal returns to its original non-connected state.

[0030] Optionally, if the terminal is in a connected state, the model update instruction is carried via RRC signaling.

[0031] Optionally, the method is executed by a network side device, the network side device includes an AI entity and a base station, the AI ​​entity is used to determine whether a model deployed on a terminal needs to be updated, and the base station communicates with the terminal and the AI ​​entity respectively.

[0032] An embodiment of the present invention also provides a model updating device, which includes: a first judgment module, used to judge whether the locally deployed model needs to be updated; a first updating module, used to cooperate with the network to update the locally deployed model if the judgment result is yes.

[0033] An embodiment of the present invention further provides a model updating device, which includes: a second judgment module, used to judge whether the model deployed on the terminal needs to be updated; and a second updating module, used to cooperate with the terminal to update the model deployed on the terminal if the judgment result is yes.

[0034] An embodiment of the present invention further provides a storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps of the above method are executed.

[0035] An embodiment of the present invention further provides a terminal, comprising a memory and a processor, wherein the memory stores a computer program executable on the processor, and the processor executes the steps of any one of the methods when running the computer program.

[0036] An embodiment of the present invention further provides a network side device, comprising a memory and a processor, wherein the memory stores a computer program executable on the processor, and the processor executes the steps of the above method when running the computer program.

[0037] Compared with the prior art, the technical solution of the embodiment of the present invention has the following beneficial effects:

[0038] The embodiment of the present invention provides a model updating method, the method comprising: determining whether it is necessary to update the locally deployed model; if the determination result is yes, cooperating with the network to update the locally deployed model. Compared with the prior art, when the UE determines that the locally deployed model needs to be updated, the model updating process is triggered, and data is interacted with the network side to complete the update of the locally deployed model of the UE.

[0039] Furthermore, the UE can obtain information about models supported by the network through system messages or RRC signaling, and enhance its awareness of network-side support and model updates. Therefore, when there is a model update in the network, the UE can detect it in time, respond, and initiate a model update process to ensure the performance of the UE-side model. In addition, the UE can also trigger a model update process for models whose model validity timer has expired, ensuring that the model deployed locally on the UE is in the latest state, and guaranteeing the performance of the AI ​​model and the introduction of new features.

[0040] Furthermore, by comparing with the expected threshold, when the performance of the model deployed locally by the UE drops below the expected threshold, the UE can initiate a model update process to the network. This operation is beneficial to ensuring the performance of the model and preventing the impact of severe degradation of the model performance on the communication performance and the reduction of the user experience.

[0041] Furthermore, different processes for updating the UE model in connected and non-connected states are provided, which can ensure the implementation of model updates on the UE side, ensure the performance of the model on the UE side, provide guarantees for the normal operation of communication network functions, and improve user experience.

[0042] Furthermore, the UE can report relevant information of the local deployment model to the network through measurement reports, etc., so that the network side can accurately know the model situation on the UE side, and trigger the update process when the network side determines that the UE model needs to be updated. In this way, the performance of the UE side model can be guaranteed, the normal operation of the communication network function can be guaranteed, and the user experience can be improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Figure 1 A schematic diagram of a flow chart of a model updating method according to an embodiment of the present invention;

[0044] Figure 2 A schematic diagram of a flow chart of another model updating method according to an embodiment of the present invention;

[0045] Figure 3 is an interactive flow chart of the first model updating method according to an embodiment of the present invention;

[0046] Figure 4 is an interactive flow chart of a second model updating method according to an embodiment of the present invention;

[0047] Figure 5 is an interactive flow chart of a third model updating method according to an embodiment of the present invention;

[0048] Figure 6 A schematic diagram of a flow chart of a model updating device according to an embodiment of the present invention;

[0049] Figure 7 The figure is a flow chart of another model updating device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0050] As mentioned in the background art, the prior art has a problem of how to provide conditions for triggering model update and a corresponding model update process.

[0051] To solve the above problems, an embodiment of the present invention provides a model updating method, which includes: determining whether the locally deployed model needs to be updated; if the determination result is yes, updating the locally deployed model in cooperation with the network.

[0052] Therefore, when it is determined that the locally deployed model needs to be updated, data interaction with the network can be triggered to complete the update of the locally deployed model.

[0053] In order to make the above-mentioned purposes, features and beneficial effects of the present invention more obvious and easy to understand, the specific embodiments of the present invention are described in detail below in conjunction with the accompanying drawings. It should be noted that the model mentioned in the embodiment of the present invention is an AI model, which can be configured on the UE side and / or the network side. The network can configure, upgrade, update, replace or delete the AI ​​model deployed by the UE (hereinafter collectively referred to as update). The AI ​​model can be used to enhance the communication network function or the calculation of signals and / or parameters in communication.

[0054] See also Figure 1 , Figure 1 The following is a flow chart of a model updating method according to an embodiment of the present invention, wherein the method comprises:

[0055] Step S101, determining whether the locally deployed model needs to be updated;

[0056] Step S102: If the judgment result is yes, the locally deployed model is updated in cooperation with the network.

[0057] Optionally, if the judgment result in step S101 is no, the model update operation is not performed.

[0058] Figure 1 The method is executed by the terminal, that is, the user equipment (UE) side. When the UE determines that the locally deployed model needs to be updated, the model update process can be triggered, and data can be interacted with the network side to complete the update of the UE locally deployed model.

[0059] Optionally, when updating the model deployed locally on the UE, the UE first falls back to the traditional communication algorithm or uses other local alternative AI models.

[0060] In one embodiment, Figure 1 Before determining whether the locally deployed model needs to be updated in step S101, the method further includes: obtaining attribute information of the locally deployed model; determining whether the locally deployed model needs to be updated in step S101 includes: determining whether the locally deployed model needs to be updated based on the attribute information; cooperating with the network to update the locally deployed model includes: initiating a model update process to the network to interact with the network for update data, wherein the update data is used to update the locally deployed model.

[0061] The attribute information is information related to whether the model deployed locally on the UE needs to be updated, and the attribute information includes at least one of the following: an identifier of the model, a version number of the model, a validity period of the model, a model type, a model volume, and a model accuracy. After the model deployed locally on the UE is updated, the attribute information corresponding to the model will also be updated.

[0062] The UE can actively trigger the model update process, and its triggering mechanism is: if the UE detects that the attribute information of its locally deployed model meets the update conditions, the model update is triggered. The UE initiates the model update process to the network to establish an interactive process for updating data with the network. The UE obtains the update data from the network and updates the locally deployed model based on the update data.

[0063] If the UE determines that the locally deployed model needs to be updated, when the UE is in a connected state and initiates a model update process to the network, the information of the target model to be updated may be included in the signaling notifying the network (such as Radio Resource Control (RRC) signaling, etc.), and the information of the auxiliary model update may also be included. Among them, the RRC signaling may be a UEAssistanceInformation message, etc.

[0064] Optionally, before determining whether the locally deployed model needs to be updated, the method further includes: receiving model information sent by the network, the model information including at least one of a model identifier, a model version number, a model validity period, a model type, a model volume, and a model accuracy; determining whether the locally deployed model needs to be updated based on the attribute information, further includes: comparing the model information with the attribute information to determine whether an updated model exists on the network, and when an updated model exists on the network, the locally deployed model needs to be updated.

[0065] The model information is sent by the network to the UE and is used to indicate information about models that the network can provide. Optionally, the model information can be carried by RRC signaling or broadcast messages (such as system messages) sent by the base station.

[0066] After receiving the model information, the UE may compare the model information with the relevant information (i.e., attribute information) of the locally deployed model to check whether the locally deployed model needs to be updated. For example, after the UE receives the model information sent by the network, if the identifier and the corresponding version number of the model locally deployed by the UE are inconsistent with the identifier and the corresponding version number of the model that the network can provide, the UE may determine that the locally deployed model needs to be updated, and the UE initiates the model update process.

[0067] It should be noted that the logic of the UE comparing the model information and the attribute information to determine whether the locally deployed model needs to be updated includes but is not limited to the above situation, and the logic can be adjusted according to the UE or the network's need to update the model.

[0068] In this embodiment, the UE can obtain the model information supported by the network through system messages or RRC signaling and other messages, thereby enhancing the perception of network-side support and updated models. Therefore, when the network model is updated, the UE can detect it in time, respond, initiate the model update process, and ensure the performance of the UE-side model.

[0069] In one embodiment, when the attribute information includes the validity period of the model, the determining whether the locally deployed model needs to be updated further includes: when the validity period of the model expires, the locally deployed model needs to be updated.

[0070] The validity period of a model indicates that the model is valid within a certain period of use. After the usage period, the model becomes invalid. If the usage period of the model exceeds the validity period of the model, the validity period of the model expires. After the network updates a model for the UE, the validity period of the model can be configured for the UE. When the UE detects that the validity period of its locally deployed model has expired, it can trigger an update of the locally deployed model. The validity period of a model can also be that the model is valid before a certain time, and expires after this time, that is, the validity period of the model can be an absolute time.

[0071] Optionally, after the network updates a model for the UE, the UE starts a valid timer locally according to the validity period of the model. When the valid timer reaches the validity period of the model, the validity period of the model locally deployed by the UE expires. It should be noted that when the timer expires, if the model on the network side is not updated, the result of triggering the model update process may only be to restart the model validity timer, and the actual model update process does not occur.

[0072] In this embodiment, the model update process is triggered for the model whose model validity timer has expired, which can ensure that the model deployed locally on the UE is in the latest state, thereby ensuring the performance of the AI ​​model and the introduction of new features.

[0073] In one embodiment, before determining whether the locally deployed model needs to be updated in step S101, it also includes: detecting the performance of the locally deployed model; determining whether the locally deployed model needs to be updated also includes: when the performance of the locally deployed model is lower than an expected threshold, the locally deployed model needs to be updated.

[0074] Optionally, the expected threshold is received from the network or obtained locally. Specifically, the network may send the expected threshold of the model to the UE, such as through a system message. Alternatively, the UE may obtain the performance value of a traditional communication algorithm (an algorithm that does not use an AI model) and use it as the expected threshold, or the UE may also obtain the expected threshold in other ways, which will not be described here.

[0075] In this embodiment, by comparing with the expected threshold, when the performance of the model deployed locally by the UE drops below the expected threshold, the UE initiates a model update process to the network. This operation is beneficial to ensuring the performance of the model and preventing the impact of a serious drop in model performance on communication performance and a reduction in user experience.

[0076] It should be noted that for the above embodiments, before the validity period of the model deployed locally by the UE expires, if any situation occurs that requires a model update, the UE can initiate a model update process to the network. When the UE is in the process of updating the model, it can first fall back to using the traditional communication algorithm, and then switch back to using the AI ​​model after the model update is completed.

[0077] In one embodiment, the determination of whether the locally deployed model needs to be updated includes: when a model update instruction sent by the network is received, the determination result is yes; wherein the model update instruction is an instruction sent to the terminal when the network determines that the model deployed by the terminal needs to be updated; the updating of the locally deployed model in cooperation with the network includes: interacting with the network for update data, and the update data is used to update the locally deployed model.

[0078] In addition to being triggered by the UE, the process of updating the UE's locally deployed model can also be triggered by the network side. The network side can send a model update instruction to the UE through a device that can communicate with the UE (such as a base station, access point (AP for short), etc.) to instruct the UE to start updating its locally deployed model.

[0079] When the network sends a model update instruction to the UE, the UE may be in a connected state or a non-connected state (including an idle state and an inactive state). The network can select different indication methods based on the state of the UE to send the model update instruction to the UE. If the UE is in a connected state, the network can send the model update instruction to the UE through RRC signaling or other methods; if the UE is in a non-connected state, the network can send the model update instruction to the UE through a paging message (Paging) or a system message (such as a SIB message, etc.).

[0080] Optionally, if in a non-connected state, the model update instruction is carried through a paging message or a system message. After receiving the model update instruction sent by the network, it also includes: switching from a non-connected state to a connected state to cooperate with the network to update the locally deployed model; after completing the update of the locally deployed model, restoring the original non-connected state.

[0081] If the UE receives a model update instruction in the non-connected state, the UE enters the connected state to perform the model update process, and after the update is completed, the UE returns to the non-connected state before entering the connected state. If the UE is in the idle state before the model update, it enters the connected state to perform the model update, and after the update is completed, it returns to the idle state again; if the UE is in the inactive state before the model update, it returns to the inactive state again after the update is completed.

[0082] This provides different processes for updating the UE model in connected and non-connected states, which can ensure the implementation of model updates on the UE side, ensure the performance of the model on the UE side, provide guarantees for the normal operation of communication network functions, and improve user experience.

[0083] In one embodiment, the method further comprises: sending relevant information of the locally deployed model to the network; wherein the relevant information enables the network to determine whether the model deployed by the terminal sending the relevant information needs to be updated.

[0084] The relevant information is information related to the model locally deployed by the UE, and the relevant information may include information such as the model identifier, the model version number, the model validity period, the model type, the model volume, and the model accuracy. In order to ensure that the network side is aware of the model information locally deployed by the UE, the UE may send the relevant information of the locally deployed model to the network side so that the network stores the information. Optionally, the network may send the information to a server or terminal related to the AI ​​model, such as an AI entity, for centralized management.

[0085] Optionally, the relevant information may be carried in RRC signaling, or in a NAS container of RRC signaling, or in a non-NAS container of RRC signaling.

[0086] In addition, when the environment in which the UE is located causes the performance of the model deployed locally by the UE to degrade, the UE can actively report the relevant information to the base station of the current cell. Further, the network can select a suitable model for the UE to perform model update according to the environment in which the UE is located or the current location of the UE.

[0087] Optionally, when the UE reports a measurement report to the network, it also reports the relevant information.

[0088] Among them, when the UE is in a connected state, relevant information of the model already existing in the UE locally can be attached when reporting a measurement report to the network. The measurement report can be a measurement report reported to the network after the UE performs cell measurement or channel measurement. It should be noted that the UE can also report the relevant information to the network through other reporting messages.

[0089] In this embodiment, the UE can report the relevant information of the local deployment model to the network through measurement reports, etc., so that the network side can accurately know the model situation on the UE side, and trigger the model update process when the network side determines that the UE model needs to be updated. In this way, the performance of the UE side model can be guaranteed, the normal operation of the communication network function can be guaranteed, and the user experience can be improved.

[0090] See also Figure 2 , Figure 2This is a flow chart of another model updating method according to an embodiment of the present invention. The method is executed by a network side device (such as a base station or an AP, etc.), and the method includes:

[0091] Step S201, determining whether the model deployed on the terminal needs to be updated;

[0092] Step S202: If the judgment result is yes, then cooperate with the terminal to update the model deployed on the terminal.

[0093] Optionally, the method also includes: if a model update process initiated by the terminal is received, determining that the model deployed on the terminal needs to be updated; cooperating with the terminal to update the model deployed on the terminal includes: interacting with the terminal for update data, the update data being used to update the model locally deployed on the terminal; wherein, if the terminal determines that the locally deployed model needs to be updated based on attribute information of the locally deployed model, the model update process is initiated.

[0094] Optionally, the attribute information includes at least one of the following: a model identifier, a model version number, a model validity period, a model type, a model volume, and a model accuracy.

[0095] Optionally, the method further includes: sending model information to the terminal so that the terminal compares the model information with the attribute information and determines whether there is an updated model in the network; when there is an updated model in the network, the terminal determines that the locally deployed model needs to be updated; wherein the model information includes at least one of a model identifier, a model version number, a model validity period, a model type, a model volume, and a model accuracy.

[0096] Optionally, when the validity period of the model expires, the terminal determines that the model deployed on the terminal needs to be updated.

[0097] Optionally, when the terminal detects that the performance of the locally deployed model is lower than an expected threshold, the terminal determines that the locally deployed model needs to be updated.

[0098] Optionally, the method further includes: sending the expected threshold to the terminal.

[0099] Optionally, if the judgment result is yes, cooperating with the terminal to update the model deployed on the terminal includes: if the judgment result is yes, sending a model update instruction to the terminal so that the terminal determines that its locally deployed model needs to be updated; cooperating with the terminal to update the model deployed on the terminal includes: interacting with the terminal to update data, and the update data is used to update the model locally deployed on the terminal.

[0100] Optionally, the method further includes: receiving relevant information of the locally deployed model sent by the terminal; and judging whether the model deployed by the terminal needs to be updated includes: determining whether the model deployed by the terminal needs to be updated based on the relevant information.

[0101] Optionally, the relevant information may exist in the RRC signaling, or in a NAS container of the RRC signaling, or in a non-NAS container of the RRC signaling.

[0102] Optionally, when the terminal reports the measurement report, the relevant information is also reported.

[0103] Optionally, if the terminal is in a non-connected state, the model update instruction is carried through a paging message or a system message to cause the terminal to switch from a non-connected state to a connected state, and after completing the update of the model locally deployed on the terminal, the terminal returns to its original non-connected state.

[0104] Optionally, if the terminal is in a connected state, the model update instruction is carried via RRC signaling.

[0105] Figure 2 The method is performed by a network-side device, which includes a base station or an AP. Figure 2 For more information on the working principle and working method of the method, please refer to Figure 1 The relevant description about the network side is not repeated here. When the module for managing the AI ​​model deployed on the network side (such as the AI ​​entity) is deployed inside the network side equipment such as the base station, the network side equipment only needs to interact with the UE to update the model on the UE side.

[0106] In one embodiment, the network side device includes an AI entity and a base station or an AP and other devices. The AI ​​entity is used to determine whether the model deployed on the terminal needs to be updated, and the base station communicates with the terminal and the AI ​​entity respectively.

[0107] When the module for managing the AI ​​model deployed on the network side (such as an AI entity) is deployed outside a network side device such as a base station (hereinafter taking the base station (gNB) as an example), the network side device also needs to interact with the module (hereinafter referred to as the AI ​​entity) for data before the model update on the UE side can be realized.

[0108] When UE Figure 1 When the model update process is initiated to the network, please refer to Figure 3 , Figure 3This is an interactive flow chart of the first model update method of an embodiment of the present invention. If the base station (gNB) receives the model update process initiated by the UE, it sends an AI model update request (which can be represented by AIModelUpdateRequest) to the AI ​​entity. If the AI ​​entity supports the corresponding model update or supports the model requested to be updated by the UE, it returns a response to the AI ​​model update request (which can be represented by AIModelUpdateRequestResponse) to the base station to inform the base station, and sends update data to the base station (which can be represented by AIModelDistribution / AIModelUpdate). The base station forwards the update data to the UE to update the model deployed on the UE side. Figure 3 The method may be initiated by a connected UE.

[0109] When the network actively updates the model for the UE based on the relevant information of the locally deployed model reported by the UE, see Figure 4 , Figure 4 This is an interactive flow chart of the second model update method of an embodiment of the present invention. When reporting a measurement report, a connected UE attaches relevant information of an existing model on the terminal side (which can be represented by Measurement Report+ModelInfo); the gNB receives the relevant information reported by the UE, and after adding the status information on the base station side, forwards this information to the AI ​​entity, for example, through an AIModelUpdateRequest message; the AI ​​entity decides whether to actively initiate a model update based on the above information. This part belongs to the network implementation and is not specified in the present invention; if the AI ​​entity supports the corresponding model update or supports the model requested to be updated by the UE, a response to the AI ​​model update request (which can be represented by AIModelUpdateRequestResponse) is returned to the base station to inform the base station, and update data is sent to the base station (which can be represented by AIModelDistribution / AIModelUpdate), and the base station forwards the update data to the UE to update the model deployed on the UE side. Alternatively, the network maintains the information of the current model of the UE for the connected UE. When the model on the network side is updated, the network can actively initiate a model update process to notify the UE to update the model.

[0110] When the UE is in a non-connected state, the network side can also actively trigger the UE to update the model. Figure 1 The update process is triggered actively when a model update instruction is sent to the UE. For details, see Figure 5 , Figure 5The interactive flow chart of the third model update method of the embodiment of the present invention. For idle / inactive UEs, the base station and the AI ​​entity exchange model information: the base station requests the AI ​​entity for the AI ​​model information supported by the current network, such as through the CurrentModelInfoRequest message; the AI ​​entity returns the AI ​​model information it supports to the base station, such as through the CurrentModelInfoResponse message; the base station broadcasts the model information in the system message of the cell; the UE receives the model information broadcast by the cell and compares it with the stored terminal side model information; if there is a model update, the UE enters the connected state; the UE initiates the model update process to the gNB, so that the gNB and the AI ​​entity follow the example Figure 3 The described process is interactive and the model is updated actively: after the model update is completed, the UE returns to the original state (idle or inactive state).

[0111] Alternatively, for idle / inactive UEs, the model update process can also be triggered by the network side (not shown): the network maintains the information of the AI ​​model locally deployed by the UE; after the model on the network side is updated, the network can actively initiate the model update process to notify the UE to update the model; such as notifying the UE to update the model through paging and other methods; in this case, since the network needs to maintain the current AI model information of the UE, the network can be notified after each UE-side model is updated, so that the network maintains the accuracy of the maintenance information. For network-assisted UE model update, after the model update process is completed, the network-side maintenance model information can be updated; after the UE-side model is updated without network assistance, the UE needs to actively notify the network of the model information currently in use.

[0112] pass Figures 3 to 5 The method described provides an interactive process for model updating when the AI ​​entity is deployed outside a network side device such as a base station (hereinafter taking the base station (gNB) as an example), thereby reducing the burden on network side devices (such as base stations, etc.).

[0113] In order to clarify the application scenarios of the model updating method provided in the embodiment of the present invention, the following also includes embodiments of several specific scenarios. It should be noted that the following embodiments do not represent all application scenarios:

[0114] Embodiment 1: Model information interaction between base station and AI entity Scenario 1: The base station sends a request message to the AI ​​entity on the base station side to inquire about the AI ​​model information it supports. The request message may be a CurrentModelInfoRequest message, which may be a periodic request message. After receiving the request message sent by the base station, the AI ​​entity on the base station side returns a response message, which is used to indicate the base station's supported models and related model information. The response message may be a CurrentModelInfoResponse message. In this embodiment, through the model information interaction between the base station and the AI ​​entity on the base station side, the base station can know the currently supported model information, which helps the base station broadcast the correct model information in the current cell and facilitates the execution of model updates on the UE side.

[0115] Embodiment 2: Model information interaction scenario 2 between base station and AI entity: After the AI ​​entity on the base station side completes the model update under the operation of Operation Administration and Maintenance (OAM), the AI ​​entity on the base station side can actively send a model update message to the base station to notify the base station that the network side model has been updated and the updated model information has been updated, such as through a ModelInfoUpdate message; after the base station receives the model update message sent by the AI ​​entity on the base station side, it updates the stored model information according to the model information contained in the model update message; after the base station completes the model update, it responds to the AI ​​entity on the base station side with a model update completion message, which can be a ModelInfoUpdateComplete message. In this embodiment, through the model information interaction between the base station and the AI ​​entity on the base station side, the base station can know the currently supported model information, which helps the base station broadcast the correct model information in the current cell, and is conducive to the execution of model updates on the UE side.

[0116] Example 3: Broadcast scenario of AI model information on the base station side: After completing the interaction with the AI ​​entity model information on the base station side, the base station broadcasts the supported AI model information in the current cell, which can be done through system message SIB and other methods; the AI ​​model information may include but is not limited to one or more of the following information: model identifier; model version number; model effective timer length; model type; model volume; model accuracy; In this embodiment, by broadcasting supported AI model information in the cell, the UE's perception of the network side model information can be enhanced. When the network model is updated, the UE can detect it in time and respond, initiate the model update process, and ensure the performance of the UE side model.

[0117] Embodiment 4: Idle / inactive UE triggers model update scenario 1: UE receives a broadcast message from the current cell; UE compares the model information contained in the received broadcast message with the currently stored model information, and when there is a model information update, such as an update to the model version information, the UE proactively initiates a model update request to the network. In this embodiment, since the cell broadcast message contains the model information supported by the current cell, when the UE finds that the model has been updated according to the broadcast message, it can directly initiate a model update request to the network, requesting the network to assist in the model update on the UE side, which is beneficial for the UE side to always keep the latest AI model and ensure the performance of the AI ​​model and the introduction of new features.

[0118] Example 5: Scenario 2 of triggering model update on the UE side in connected state (expiration of valid timer may also occur in Idle / Inactive state) When the valid timer of the AI ​​model on the UE side expires, the UE can notify the network through RRC signaling that the AI ​​model on the UE side needs to be updated; the RRC signaling can be UEAssistanceInformation; the UE can include information about the model that needs to be updated in the RRC signaling; wherein, when the timer expires, since the model on the network side may not be updated, the result of triggering the model update process at this time may only restart the model valid timer, and the actual model update process does not occur; when the valid timer in the Idle / Inactive state expires, the UE can actively enter the connected state, and the subsequent process is consistent with Example 5. After completing the model update, the UE returns to the original state. In this embodiment, the model update process is triggered for the model whose valid timer has expired, which can ensure that the UE side model is in the latest state and guarantee the performance of the AI ​​model and the introduction of new features.

[0119] Example 6: Scenario 3 of triggering model update on the UE side in connected state (model performance degradation may also occur in Idle / Inactive state): When the UE detects that the model performance is lower than the expected threshold, the UE can notify the network through RRC signaling that the UE-side AI model needs to be updated; the RRC signaling can be UEAssistanceInformation; the UE can include information about the model that needs to be updated in the RRC signaling, and can also additionally include data information for auxiliary model updates; the expected threshold can be a fixed value issued by the network, or it can be a performance value of a traditional communication algorithm; when the performance of the Idle / Inactive state model degrades, the UE can actively enter the connected state, and the subsequent process is consistent with Example 6. After completing the model update, the UE returns to its original state. In this embodiment, by comparing with the expected threshold, when the model performance drops below the threshold, the UE initiates the model update process. This operation is beneficial to ensuring model performance and preventing the impact of severe degradation of model performance on communication performance and reduction of user experience.

[0120] Example 7: Idle / inactive UE side triggering model update scenario 4: When the effective timer of the UE side AI model expires, the UE can enter the connected state, and then notify the network through RRC signaling that the UE side AI model needs to be updated; the RRC signaling can be UEAssistanceInformation; the UE can include information about the model that needs to be updated in the RRC signaling. The effect achieved by this embodiment is consistent with that of Example 5.

[0121] Example 8: Scenario 5 of triggering model update on the idle / inactive UE side: When the UE detects that the model performance is lower than the expected threshold, the UE can enter the connected state, and then notify the network through RRC signaling that the UE-side AI model needs to be updated; the RRC signaling can be UEAssistanceInformation; the UE can include information about the model that needs to be updated in the RRC signaling, and can also additionally include data information for auxiliary model update; the expected threshold can be a fixed value issued by the network, or it can be a performance value of a traditional communication algorithm; the effect achieved by this embodiment is consistent with that of Example 6.

[0122] Embodiment 9: Connected UE model update process 1, the model update step includes: the UE meets the situation of the UE side triggering the model update process described in Embodiment 5 or Embodiment 6; the connected UE indicates the gNB through RRC signaling (such as UEAssistancecInformation message) to determine that the UE side needs to update the model; optionally, the UE can first fall back to using the traditional communication algorithm, and then switch back to using the AI ​​model after the model update is completed; the UE reports the model to be updated and related model information, such as the model identifier, version number, etc., which can be included in the non-NAS container of the RRC signaling; the gNB initiates a model update request to the AI ​​entity and forwards the UE's model information to the AI ​​entity, and the model update request signaling can be AIModelUpdateRequest; the AI ​​entity returns a model update response message, and the model update response message can be AIModelUpdateRequestResponse, which is used to indicate to the base station whether the AI ​​entity can meet the AI ​​model requested to be updated; if the AI ​​entity can support the AI ​​model requested to be updated, then the AI ​​entity updates the UE side AI model, such as through messages such as AIModelDistribution / AIModelUpdate; after the model update process is completed, the UE switches from the traditional mode back to using the AI ​​model mode. This embodiment provides a process for updating the connected UE model, which can ensure the implementation of the UE-side model update, ensure the performance of the UE-side model, provide guarantee for the normal operation of the communication network functions, and improve the user experience.

[0123] Embodiment 10: Idle / inactive UE model update process 2, the model update step includes: the UE meets the conditions of the UE side triggering the model update process described in Embodiment 7 or Embodiment 8; the idle / inactive UE enters the connected state; the UE entering the connected state indicates to the gNBUE side through RRC signaling (such as UEAssistancecInformation message) that a model update is required; optionally, the UE can first fall back to using the traditional communication algorithm, and then switch back to using the AI ​​model after the model update is completed; the UE reports the model to be updated and related model information, such as the model identifier, version number, etc., which can be included in the non-NAS of the RRC signaling. container; gNB initiates a model update request to the AI ​​entity, and forwards the UE's model information to the AI ​​entity. The model update request signaling may be AIModelUpdateRequest; the AI ​​entity returns a model update response message, and the model update response message may be AIModelUpdateRequestResponse, which is used to indicate to the base station whether the AI ​​entity can satisfy the requested AI model update; if the AI ​​entity can support the requested AI model update, then the AI ​​entity updates the UE-side AI model, such as through messages such as AIModelDistribution / AIModelUpdate; after the model update process is completed, the UE switches from the traditional method back to the AI ​​model method, and re-enters the original state (idle or inactive state). This embodiment provides a process for updating the idle / inactive UE model, which can ensure the implementation of the UE-side model update, ensure the performance of the UE-side model, provide guarantees for the normal operation of the communication network functions, and improve the user experience.

[0124] Embodiment 11: Idle / inactive UE model update process 3, the model update step includes: the UE meets the UE side triggering model update process described in embodiment 4; if there is a model update, the UE enters the connected state; the UE interacts with the gNB and the AI ​​entity and actively updates the model: the UE sends a model distribution request or a model update request to the gNB, such as an RRC message such as an AIModelDistributionRequest / AIModelUpdateRequest message, to request the network to update the model; the gNB forwards the UE's request message to the AI ​​entity; the AI ​​entity responds to the UE's request message and updates the model, such as through an AIModelDistribution / AIModelUpdate message; after the model update is completed, the UE re-enters the original state (idle or inactive state). Among them, since the cell broadcast message contains the model information supported by the current cell, when the UE finds that the model has been updated according to the broadcast message, it can directly initiate a model update request to the network, requesting the network to assist in the model update on the UE side. This embodiment provides a process for updating the UE model in the idle / inactive state, which can ensure the implementation of the UE side model update, ensure the performance of the UE side model, provide guarantee for the normal operation of the communication network function, and improve the user experience.

[0125] Embodiment 12: Connected UE model update process 4, the model update step includes: when reporting a measurement report, the connected UE attaches the existing model information on the UE side; the gNB receives the model information reported by the UE, and after adding the status information on the base station side, forwards this information to the AI ​​entity, for example, through AIModelUpdateRequest; the status information on the base station side may be L2 buffer status, data rate, packet arrival interval and other information; the AI ​​entity decides whether to actively initiate a model update based on the above information (this part belongs to the network implementation); the AI ​​entity returns a model update response message, which may be AIModelUpdateRequestResponse, used to indicate whether the base station AI entity can meet the requested AI model; the AI ​​entity updates the UE side AI model, such as through messages such as AIModelDistribution / AIModelUpdate; the UE completes the model update process; this embodiment provides a process for updating the model of a connected UE, which can ensure the implementation of the model update on the UE side, ensure the performance of the model on the UE side, provide guarantees for the normal operation of the communication network functions, and improve the user experience.

[0126] Embodiment 13: Connected UE model update process 5, the model update step includes: gNB maintains the information of the current model of the UE for the connected UE; after the AI ​​entity completes the update of the model it has deployed, it notifies the gNB of its updated model information by implementing method 2; the gNB compares the AI ​​entity update information with the model information currently used by the UE to determine whether to actively initiate the model update process; if the gNB detects that some models of the UE can be updated, the gNB sends a model distribution / model update request message to the AI ​​entity, such as through an AIModelDistribution / AIModelUpdate message, to notify the AI ​​entity to actively initiate a model update process to the UE; the AI ​​entity responds to the request message of the gNB and updates the model, such as through an AIModelDistribution / AIModelUpdate message; the UE completes the model update process; this embodiment provides a process for updating the model of the connected UE, which can ensure the implementation of the model update on the UE side, ensure the performance of the model on the UE side, provide guarantees for the normal operation of the communication network functions, and improve the user experience.

[0127] Embodiment 14: Inactive UE model update process 6, the model update step includes: gNB maintains the information of the current model of the UE; after the AI ​​entity completes the update of the model it deploys, it notifies the gNB of its updated model information by implementing method 2; the gNB compares the AI ​​entity update information with the model information currently used by the UE to determine whether to actively initiate the model update process; if the gNB detects that some models of the UE can be updated, the gNB instructs the UE to enter the connected state through paging to prepare for the model update process; the gNB sends a model delivery / model update request message to the AI ​​entity, such as through an AIModelDistribution / AIModelUpdate message, to notify the AI ​​entity to actively initiate a model update process to the UE; the AI ​​entity responds to the request message of the gNB and performs a model update, such as through an AIModelDistribution / AIModelUpdate message; the UE completes the model update process; the UE returns to the inactive state; this embodiment provides a process for updating the model of the inactive UE, which can ensure the implementation of the model update on the UE side, ensure the performance of the model on the UE side, provide guarantees for the normal operation of the communication network functions, and improve the user experience.

[0128] The embodiment of the present invention also provides a model updating device 60, see Figure 6 , the model updating device 60 comprises:

[0129] The first judgment module 601 is used to judge whether the locally deployed model needs to be updated;

[0130] The first updating module 602 is used to cooperate with the network to update the locally deployed model if the judgment result is yes.

[0131] about Figure 6 For more information on the working principle and working method of the model updating device 90, please refer to Figure 1 The relevant description will not be repeated here.

[0132] In a specific implementation, the above-mentioned model updating device 60 may correspond to a chip with a model updating function in a terminal (i.e., UE), or to a chip with a data processing function, such as a system-on-a-chip (SOC), a baseband chip, etc.; or to a chip module in the UE that includes a chip with a model updating function; or to a chip module with a chip with a data processing function, or to a UE.

[0133] The embodiment of the present invention also provides a model updating device 70, see Figure 7 , the model updating device 70 comprises:

[0134] The second judgment module 701 is used to judge whether the model deployed on the terminal needs to be updated;

[0135] The second updating module 702 is used to cooperate with the terminal to update the model deployed on the terminal if the judgment result is yes.

[0136] about Figure 7 For more information on the working principle and working method of the model updating device 70, please refer to Figure 2 The relevant description will not be repeated here.

[0137] In a specific implementation, the above-mentioned model updating device 70 may correspond to a chip with a model updating function in a network side device (such as a base station, etc.), or to a chip with a data processing function, such as a system-on-a-chip (SOC), a baseband chip, etc.; or to a chip module in a network side device that includes a chip with a model updating function; or to a chip module with a chip with a data processing function, or to a network side device.

[0138] In a specific implementation, each module / unit included in each device or product described in the above embodiments may be a software module / unit or a hardware module / unit, or may be partly a software module / unit and partly a hardware module / unit.

[0139] For example, for each device or product applied to or integrated in a chip, each module / unit contained therein may be implemented in the form of hardware such as circuits, or at least some of the modules / units may be implemented in the form of software programs, which run on a processor integrated inside the chip, and the remaining (if any) modules / units may be implemented in the form of hardware such as circuits; for each device or product applied to or integrated in a chip module, each module / unit contained therein may be implemented in the form of hardware such as circuits, and different modules / units may be located in the same component (such as a chip, circuit module, etc.) or different components of the chip module, or at least some of the modules / units may be implemented in the form of software programs. The element can be implemented in the form of a software program, which runs on a processor integrated inside the chip module, and the remaining (if any) modules / units can be implemented in the form of hardware such as circuits; for various devices and products applied to or integrated in the terminal, the various modules / units contained therein can be implemented in the form of hardware such as circuits, and different modules / units can be located in the same component (for example, chip, circuit module, etc.) or in different components in the terminal, or, at least some modules / units can be implemented in the form of a software program, which runs on a processor integrated inside the terminal, and the remaining (if any) modules / units can be implemented in the form of hardware such as circuits.

[0140] An embodiment of the present invention further provides a storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps of any one of the methods are executed.

[0141] An embodiment of the present invention further provides a terminal, including a memory and a processor, wherein the memory stores a computer program that can be run on the processor, and the processor executes the steps of any one of the methods when running the computer program. An embodiment of the present invention further provides a network side device, including a memory and a processor, wherein the memory stores a computer program that can be run on the processor, and the processor executes the steps of any one of the methods when running the computer program.

[0142] Specifically, in the embodiment of the present invention, the processor may be a central processing unit (CPU), and the processor may also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0143] It should also be understood that the memory in the embodiments of the present application may be a volatile memory or a non-volatile memory, or 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), which is used as an external cache. By way of example but not limitation, many forms of random access memory (RAM) are available, such as static RAM (SRAM), dynamic random access memory (DRAM), synchronous DRAM (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link DRAM (SLDRAM) and direct rambus RAM (DR RAM).

[0144] It should be understood that the term "and / or" in this article is only a description of the association relationship of the associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article indicates that the associated objects before and after are in an "or" relationship.

[0145] The "plurality" appearing in the embodiments of the present application refers to two or more.

[0146] The first, second, etc. descriptions appearing in the embodiments of the present application are only used for illustration and distinction of the description objects. There is no order, nor do they indicate any special limitation on the number of devices in the embodiments of the present application, and cannot constitute any limitation on the embodiments of the present application.

[0147] The "connection" that appears in the embodiments of the present application refers to various connection methods such as direct connection or indirect connection to achieve communication between devices, and the embodiments of the present application do not impose any limitations on this.

[0148] Although the present invention is disclosed as above, the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions without departing from the spirit and scope of the present invention, and can make various changes and modifications, including the combination of the above-mentioned different functions and implementation steps, including software and hardware implementation methods, all of which are within the scope of protection of the present invention.

Claims

1. A model updating method, characterized in that: The method comprises: Check the performance of the locally deployed model; Determine whether the locally deployed model needs to be updated, including: when the performance of the locally deployed model is lower than the expected threshold, the locally deployed model needs to be updated; If the judgment result is yes, the locally deployed model is updated in cooperation with the network; the locally deployed model is used to enhance the communication network function or the calculation of signals and / or parameters in communication; when the locally deployed model is updated, it falls back to the traditional communication algorithm or other local alternative models.

2. The method according to claim 1, characterized in that Before determining whether the locally deployed model needs to be updated, the method further includes: Get the property information of the locally deployed model; The determining whether the locally deployed model needs to be updated includes: According to the attribute information, determining whether the locally deployed model needs to be updated; The updating of the locally deployed model in cooperation with the network includes: A model update process is initiated to the network to interact with the network for update data, wherein the update data is used to update the locally deployed model.

3. The method according to claim 2, characterized in that The attribute information includes at least one of the following: a model identifier, a model version number, a model validity period, a model type, a model volume, and a model accuracy.

4. The method according to claim 3, characterized in that Before determining whether the locally deployed model needs to be updated, the method further includes: Receiving model information sent by the network, the model information including at least one of a model identifier, a model version number, a model validity period, a model type, a model volume, and a model accuracy; The determining, based on the attribute information, whether it is necessary to update the locally deployed model further includes: The model information is compared with the attribute information to determine whether there is an updated model in the network. When there is an updated model in the network, the locally deployed model needs to be updated.

5. The method according to claim 2, characterized in that: When the attribute information includes the validity period of the model, the determining whether the locally deployed model needs to be updated further includes: When the validity period of the model expires, the locally deployed model needs to be updated.

6. The method according to claim 1, characterized in that The expected threshold is received from the network or acquired locally.

7. The method according to claim 1, characterized in that The determining whether the locally deployed model needs to be updated includes: When a model update instruction sent by the network is received, the judgment result is yes; The model update instruction is an instruction sent to the terminal when the network determines that the model deployed by the terminal needs to be updated; The updating of the locally deployed model in cooperation with the network includes: interacting with the network to update data, wherein the update data is used to update the locally deployed model.

8. The method according to claim 7, characterized in that The method further comprises: Send information about the locally deployed model to the network; The relevant information enables the network to determine whether the model deployed by the terminal that sends the relevant information needs to be updated.

9. The method according to claim 8, characterized in that The relevant information may exist in the RRC signaling, or in a NAS container of the RRC signaling, or in a non-NAS container of the RRC signaling.

10. The method according to claim 8, characterized in that When reporting the measurement report to the network, the related information is also reported.

11. The method according to claim 7 or 8, characterized in that: If the model is in a non-connected state, the model update instruction is carried by a paging message or a system message. After receiving the model update instruction sent by the network, the method further includes: Switch from a non-connected state to a connected state to update the locally deployed model in coordination with the network; After completing the update of the locally deployed model, restore the original disconnected state.

12. The method according to claim 7 or 8, characterized in that: If in a connected state, the model update instruction is carried via RRC signaling.

13. A model updating method, characterized in that: The method comprises: Receiving a measurement report sent by a terminal, wherein the measurement report also includes relevant information of a model locally deployed by the terminal; Based on the measurement report, determining whether a model deployed by the terminal needs to be updated; If the judgment result is yes, the model deployed by the terminal is updated in cooperation with the terminal; the model deployed by the terminal is used to enhance the communication network function or the calculation of signals and / or parameters in communication; when the deployed model is updated, the terminal falls back to the traditional communication algorithm or other alternative models.

14. The method according to claim 13, characterized in that The method further comprises: If a model update process initiated by the terminal is received, it is determined that the model deployed on the terminal needs to be updated; The updating of the model deployed on the terminal in cooperation with the terminal includes: Interacting with the terminal to update data, wherein the update data is used to update a model locally deployed on the terminal; If the terminal determines that the locally deployed model needs to be updated based on the attribute information of the locally deployed model, a model update process is initiated.

15. The method according to claim 14, characterized in that The attribute information includes at least one of the following: a model identifier, a model version number, a model validity period, a model type, a model volume, and a model accuracy.

16. The method according to claim 15, characterized in that The method further comprises: Sending model information to the terminal so that the terminal compares the model information with the attribute information and determines whether there is an updated model on the network. When the updated model exists on the network, the terminal determines that the locally deployed model needs to be updated; The model information includes at least one of a model identifier, a model version number, a model validity period, a model type, a model volume, and a model accuracy.

17. The method according to claim 15, characterized in that When the validity period of the model expires, the terminal determines that the model deployed on the terminal needs to be updated.

18. The method according to claim 14, characterized in that When the terminal detects that the performance of the locally deployed model is lower than an expected threshold, the terminal determines that the locally deployed model needs to be updated.

19. The method according to claim 13, characterized in that The method further comprises: The expected threshold is sent to the terminal.

20. The method according to claim 13, characterized in that If the judgment result is yes, then cooperating with the terminal to update the model deployed by the terminal includes: If the judgment result is yes, sending a model update instruction to the terminal, so that the terminal determines that the locally deployed model needs to be updated; The updating of the model deployed on the terminal in cooperation with the terminal includes: Interact with the terminal to update data, where the update data is used to update the model locally deployed on the terminal.

21. The method according to claim 13, characterized in that The relevant information may exist in the RRC signaling, or in a NAS container of the RRC signaling, or in a non-NAS container of the RRC signaling.

22. The method according to claim 13, characterized in that When the terminal reports the measurement report, the relevant information is also reported at the same time.

23. The method according to claim 20, characterized in that If the terminal is in a non-connected state, the model update instruction is carried by a paging message or a system message to enable the terminal to switch from a non-connected state to a connected state, and after completing the update of the model deployed locally on the terminal, the terminal returns to its original non-connected state.

24. The method according to claim 20, characterized in that If the terminal is in a connected state, the model update instruction is carried via RRC signaling.

25. The method according to any one of claims 13 to 24, characterized in that: The method is executed by a network side device, which includes an AI entity and a base station. The AI ​​entity is used to determine whether a model deployed on a terminal needs to be updated, and the base station communicates with the terminal and the AI ​​entity respectively.

26. A model updating device, characterized in that: The device comprises: A first detection module is used to detect the performance of the locally deployed model; The first judgment module is used to judge whether the locally deployed model needs to be updated, including: when the performance of the locally deployed model is lower than the expected threshold, the locally deployed model needs to be updated; the first update module is used to cooperate with the network to update the locally deployed model if the judgment result is yes; the locally deployed model is used to enhance the communication network function or the calculation of signals and / or parameters in communication; when updating the locally deployed model, fall back to the traditional communication algorithm or other local alternative models.

27. A model updating device, characterized in that: The device is deployed on a network side device, and the device includes: A receiving unit, configured to receive a measurement report sent by a terminal, wherein the measurement report also includes relevant information of a model locally deployed by the terminal; A second judgment module is used to judge whether it is necessary to update the model deployed by the terminal based on the measurement report; The second update module is used to cooperate with the terminal to update the model deployed by the terminal if the judgment result is yes; the model deployed by the terminal is used to enhance the communication network function or the calculation of signals and / or parameters in communication; when the terminal is updated with the deployed model, it falls back to the traditional communication algorithm or other alternative models.

28. A storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 12 or the steps of the method according to any one of claims 13 to 25 are executed.

29. A terminal comprising a memory and a processor, wherein the memory stores a computer program that can be run on the processor, characterized in that: When the processor runs the computer program, the steps of the method according to any one of claims 1 to 12 are performed.

30. A network side device, comprising a memory and a processor, wherein the memory stores a computer program that can be run on the processor, characterized in that: When the processor runs the computer program, the steps of the method according to any one of claims 13 to 25 are performed.

Images