Information transmission method and device, terminal and network side equipment

Abstract

The invention discloses an information transmission method and device, a terminal and network side equipment, and belongs to the technical field of communication, and the information transmission method comprises the steps that the terminal receives a first message through user plane connection with a first target network element; wherein the first message comprises related information of an artificial intelligence (AI) model, and the related information of the AI model comprises at least one of the following items: identification information of the AI model; file information of the AI model; attribute information of the AI model; and a download address of the AI model.

Description

Technical Field

[0001] This application belongs to the field of communication technologies, and particularly relates to an information transmission method, apparatus, terminal, and network-side device. Background Art

[0002] Currently, in a mobile communication network, tasks can be performed or services can be provided based on Artificial Intelligence (AI). For example, a terminal can perform Channel State Information (CSI) prediction, positioning, etc. based on a pre-trained AI model. In actual situations, the training and generation of an AI model may be located on the 3rd Generation Partnership Project (3GPP) network side, Over The Top (OTT) server side, etc., while the inference based on the AI model is located on the terminal side. Therefore, it is necessary to transfer the AI model from the training party to the terminal. However, in the prior art, there is no corresponding solution for how the network transfers the AI model to the terminal. Summary of the Invention

[0003] Embodiments of this application provide an information transmission method, apparatus, terminal, and network-side device, which can provide a way for the network side to transfer an AI model to the terminal.

[0004] In a first aspect, an information transmission method is provided. The method includes:

[0005] The terminal receives a first message through a user plane connection with a first target network element;

[0006] wherein the first message includes information related to an Artificial Intelligence (AI) model, and the information related to the AI model includes at least one of the following:

[0007] Identification information of the AI model;

[0008] File information of the AI model;

[0009] Attribute information of the AI model;

[0010] Download address of the AI model.

[0011] In a second aspect, an information transmission apparatus is provided. The apparatus includes:

[0012] A first receiving module, configured to receive a first message through a user plane connection with a first target network element;

[0013] wherein the first message includes information related to an Artificial Intelligence (AI) model, and the information related to the AI model includes at least one of the following:

[0014] Identification information of the AI model;

[0015] File information of the AI model;

[0016] Attribute information of the AI model;

[0017] Download address of the AI model.

[0018] In a third aspect, an information transmission method is provided, and the method includes:

[0019] The first target network element sends a first message through the user plane connection with the terminal;

[0020] Wherein, the first message includes information related to an artificial intelligence (AI) model, and the information related to the AI model includes at least one of the following:

[0021] Identification information of the AI model;

[0022] File information of the AI model;

[0023] Attribute information of the AI model;

[0024] Download address of the AI model.

[0025] In a fourth aspect, an information transmission device is provided, and the device includes:

[0026] A fifth sending module, configured to send a first message through the user plane connection with the terminal;

[0027] Wherein, the first message includes information related to an artificial intelligence (AI) model, and the information related to the AI model includes at least one of the following:

[0028] Identification information of the AI model;

[0029] File information of the AI model;

[0030] Attribute information of the AI model;

[0031] Download address of the AI model.

[0032] In a fifth aspect, a terminal is provided, and the terminal includes a processor and a memory. The memory stores a program or instruction that can 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.

[0033] In a sixth aspect, a terminal is provided, including a processor and a communication interface. The communication interface is configured to receive a first message through a user plane connection with a first target network element. The first message includes information related to an artificial intelligence (AI) model, and the information related to the AI model includes at least one of the following: identification information of the AI model; file information of the AI model; attribute information of the AI model; download address of the AI model.

[0034] In a seventh aspect, a network-side device is provided. The network-side device includes a processor and a memory. The memory stores a program or instructions that can be run on the processor. When the program or instructions are executed by the processor, the steps of the method described in the third aspect are implemented.

[0035] In an eighth aspect, a network-side device is provided, including a processor and a communication interface. The communication interface is configured to send a first message through a user plane connection with a terminal. The first message includes information related to an artificial intelligence (AI) model, and the information related to the AI model includes at least one of the following: identification information of the AI model; file information of the AI model; attribute information of the AI model; download address of the AI model.

[0036] In a ninth aspect, an information transmission system is provided, including a terminal and a network-side device. The terminal can be used to execute the steps of the information transmission method described in the first aspect, and the network-side device can be used to execute the steps of the information transmission method described in the third aspect.

[0037] In a tenth aspect, a readable storage medium is provided. A program or instructions are stored on the readable storage medium. When the program or instructions are executed by a processor, the steps of the method described in the first aspect are implemented, or the steps of the method described in the third aspect are implemented.

[0038] In an eleventh aspect, a chip is provided. The chip includes a processor and a communication interface. The communication interface is coupled to the processor. The processor is configured to run a program or instructions to implement the steps of the method described in the first aspect, or to implement the steps of the method described in the third aspect.

[0039] In a twelfth aspect, a computer program / program product is provided. The computer program / program product is stored in a storage medium. The computer program / program product is 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 third aspect.

[0040] In an embodiment of the present application, the terminal receives a first message through a user plane connection with a first target network element; wherein, the first message includes information related to an AI model, and the information related to the AI model includes at least one of the following: identification information of the AI model; file information of the AI model; attribute information of the AI model; download address of the AI model, that is, in an embodiment of the present application, the network side transmits information related to the AI model to the terminal through a user plane connection with the terminal, so that the network side can conveniently transmit the AI model to the terminal. Description of the Drawings

[0041] Figure 1 is a block diagram of a wireless communication system applicable to an embodiment of the present application;

[0042] Figure 2a is one of the schematic diagrams of AI positioning provided by an embodiment of the present application;

[0043] Figure 2b is another schematic diagram of AI positioning provided by an embodiment of the present application;

[0044] Figure 2c is a third schematic diagram of AI positioning provided by an embodiment of the present application;

[0045] Figure 2d is a fourth schematic diagram of AI positioning provided by an embodiment of the present application;

[0046] Figure 2e is a fifth schematic diagram of AI positioning provided by an embodiment of the present application;

[0047] Figure 3a is a flowchart of the LMF initiating a user plane connection provided by an embodiment of the present application;

[0048] Figure 3b is a flowchart of the UE initiating a user plane connection provided by an embodiment of the present application;

[0049] Figure 4 is a flowchart of a method for information transmission provided by an embodiment of the present application;

[0050] Figure 5 is a flowchart of another method for information transmission provided by an embodiment of the present application;

[0051] Figure 6a is a flowchart of yet another method for information transmission provided by an embodiment of the present application;

[0052] Figure 6b is a flowchart of yet another method for information transmission provided by an embodiment of the present application;

[0053] Figure 6c is a flowchart of yet another method for information transmission provided by an embodiment of the present application;

[0054] Figure 6d is a flowchart of yet another information transmission method provided by an embodiment of the present application;

[0055] Figure 7 is a structural diagram of an information transmission device provided by an embodiment of the present application;

[0056] Figure 8 is a structural diagram of another information transmission device provided by an embodiment of the present application;

[0057] Figure 9 is a structural diagram of a communication device provided by an embodiment of the present application;

[0058] Figure 10 is a structural diagram of a terminal provided by an embodiment of the present application;

[0059] Figure 11 is a structural diagram of a network - side device provided by an embodiment of the present application. Detailed implementation manners

[0060] Next, the technical solutions in the embodiments of the present application will be clearly described in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art belong to the scope of protection of the present application.

[0061] The terms "first", "second", etc. in the present application are used to distinguish similar objects, rather than to describe a specific order or sequence. It should be understood that such terms can be interchanged under appropriate circumstances 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 usually of the same type, and do not limit the number of objects. For example, the first object can be one or multiple. In addition, "or" in the present application means at least one of the connected objects. For example, "A or B" covers three scenarios, namely, Scenario 1: including A and not including B; Scenario 2: including B and not including A; Scenario 3: including both A and B. The character " / " generally represents an "or" relationship between the associated objects before and after.

[0062] The term "indication" in the present application can be either a direct indication (or an explicit indication) or an indirect indication (or an implicit indication). Among them, a direct indication can be understood as that the sender clearly tells the receiver specific information, operations to be performed, or request results, etc. in the sent indication; an indirect indication can be understood as that the receiver determines the corresponding information according to the indication sent by the sender, or makes a judgment and determines the operations to be performed or request results, etc. according to the judgment result.

[0063] It should be noted that the technology described in the embodiments of the present application is not limited to Long Term Evolution (LTE) / LTE-Advanced (LTE-A) systems, and can also be used in other wireless communication systems, such as Code Division Multiple Access (CDMA), Time Division Multiple Access (TDMA), Frequency Division Multiple Access (FDMA), Orthogonal Frequency Division Multiple Access (OFDMA), Single-carrier Frequency-Division Multiple Access (SC-FDMA), or other systems. The terms "system" and "network" in the embodiments of the present application are often used interchangeably, and the described technology can be used in the above-mentioned systems and radio technologies, as well as in other systems and radio technologies. The following description describes the New Radio (NR) system for illustrative purposes and uses the NR terminology in most of the following descriptions, but these technologies can also be applied to systems other than the NR system, such as the 6th Generation (6 th Generation, 6G) communication system.

[0064] Figure 1A block diagram of a wireless communication system to which embodiments of the present application can be applied is shown. The wireless communication system includes a terminal 11 and a network-side device 12. Among them, the terminal 11 can be a mobile phone, a tablet personal computer, a 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), a virtual reality (VR) device, a robot, a wearable device, a flight vehicle, a vehicle user equipment (VUE), a shipborne device, a pedestrian user equipment (PUE), a smart home (home devices with wireless communication functions, such as refrigerators, TVs, washing machines, or furniture, etc.), a game console, a personal computer (PC), a teller machine, or a self-service machine, etc., which are terminal-side devices. Wearable devices include: smart watches, smart bracelets, smart earphones, smart glasses, smart jewelry (smart bracelets, smart bracelets, smart rings, smart necklaces, smart anklets, smart ankle chains, etc.), smart wristbands, smart clothing, etc. Among them, the vehicle user equipment can also be referred to as a vehicle terminal, a vehicle controller, a vehicle module, a vehicle component, a vehicle chip, or a vehicle unit, etc. It should be noted that the specific type of the terminal 11 is not limited in the embodiments of the present application. The network-side device 12 can include an access network device or a core network device. Among them, the access network device can also be referred to as a radio access network (RAN) device, a radio access network function, or a radio access network unit. The access network device can include a base station, a wireless local area network (WLAN) access point (AP), or a wireless fidelity (WiFi) node, 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, Transmission Reception Point (TRP), or some other suitable term in the art. As long as the same technical effect is achieved, the base station is not limited to specific technical terms. It should be noted that in the embodiments of this application, only the base station in the NR system is taken as an example for introduction, and the specific type of the base station is not limited.

[0065] The core network device may include, but is not limited to, at least one of the following: core network node, core network function, Mobility Management Entity (MME), Access and Mobility Management Function (AMF), Session Management Function (SMF), User Plane Function (UPF), Policy Control Function (PCF), Policy and Charging Rules Function (PCRF), Edge Application Server Discovery Function (EASDF), Unified Data Management (UDM), Unified Data Repository (UDR), Network Data Analytics Function (NWDAF), Home Subscriber Server (HSS), Centralized network configuration (CNC), Network Repository Function (NRF), Network Exposure Function (NEF), Local NEF (L-NEF), Binding Support Function (BSF), Application Function (AF), Location Management Function (LMF), etc. It should be noted that in the embodiments of this application, only the core network devices in the NR system are taken as examples for introduction, and the specific types of core network devices are not limited.

[0066] For ease of understanding, some content related to the embodiments of this application is described below:

[0067] I. AI positioning

[0068] AI positioning aims to use an AI model to predict measurement information, so as to give the position estimate of the target, which can save a large amount of measurement resources and reduce computational power consumption. Currently, it includes the following five frameworks:

[0069] Case 1: UE-based positioning using the UE-side model, direct AI / Machine Learning (ML) or AI / ML-assisted positioning, such as Figure 2a shown;

[0070] Case 2a: UE-assisted / Location Management Function (LMF) positioning using the UE-side model, AI / ML-assisted positioning, such as Figure 2b shown;

[0071] Case 2b: UE-assisted / LMF positioning using the LMF-side model, direct AI / ML positioning, such as Figure 2c shown;

[0072] Case 3a: NG-RAN node-assisted positioning using the gNB-side model, AI / ML-assisted positioning, such as Figure 2d shown;

[0073] Case 3b: NG-RAN node-assisted positioning using the LMF-side model, direct AI / ML positioning, such as Figure 2e shown.

[0074] For Case 1 and Case 2a, the training and generation of the model may occur on the network side or the Over-the-Top (OTT) server side, and the inference occurs on the terminal side. Therefore, the model needs to be sent from the trainer to the terminal.

[0075] For Case 1:

[0076] Model training: OTT server, CN (LMF / NWDAF);

[0077] Model inference: UE side, where the intermediate inference is completed inside the UE, and the AI positioning result is sent to the CN.

[0078] For Case 2a:

[0079] Model training: OTT server, CN (LMF / NWDAF);

[0080] Model inference: UE side, and the AI measurement information is sent to the CN.

[0081] Generally speaking, in the above two cases:

[0082] The terminal obtains the trained AI positioning model from the Core Network (CN) or the OTT server;

[0083] The terminal performs model inference locally to obtain AI measurement information (i.e., case 2a) or directly obtains the AI positioning result (i.e., case 1).

[0084] The terminal reports the positioning intermediate quantity (i.e., AI measurement information, case 2a) or the positioning result (i.e., AI position estimate, case 1) to the CN. The CN determines the final AI position estimate based on the AI measurement quantity or directly uses the position estimate reported by the terminal.

[0085] II. User Plane Positioning

[0086] Existing technologies support the network and the terminal to transmit positioning-related information through the user plane connection. For example, LTE positioning protocol (LPP) messages and location services (LCS-SS) messages. One is based on the Secure User Plane Location (SUPL) protocol, which is a standardized interface defined by the Open Mobile Alliance (OMA) for transmitting positioning messages and is widely used in commercial scenarios. It is a user plane positioning transmission technology based on the application layer through the user plane connection between the UE and the SUPL server. The other is based on the LCS User Plane Positioning (LCS-UPP) protocol, which is a 5G interface for the 3rd Generation Partnership Project (3GPP) to transmit positioning messages and is a connection for user plane positioning between the UE and the LMF.

[0087] The LCS-UPP protocol currently has two ways to establish a connection: UE-triggered establishment and LMF-triggered establishment.

[0088] The two establishment methods only differ in the active initiator. In the process, the UE is made to know some secure information such as the connection address of the LMF. Subsequently, the UE initiates a connection of the Transport Layer Security (TLS) protocol above the Protocol Data Unit (PDU) session to establish a user plane connection from the UE to the LMF.

[0089] In the relevant protocol, the process for the UE to establish a user plane connection with the LMF and transmit LPP messages or LCS-SS messages through the user plane has been specified. The UE can initiate the establishment of the user plane, and the LMF can initiate, modify, or release the user plane. During the establishment process, the first step is for the UE to establish an exclusive PDU session based on the UE Route Selection Policy (URSP) ( Figure 3a and Figure 3b not shown in the figure); on top of the PDU session, in the second step, the UE uses the received user plane information (such as the LMF address) to establish a connection (such as Figure 3a step a7); in the third step, on top of the connection, LPP messages or LCS-SS messages (such as event reports) can be transmitted between the UE and the LMF.

[0090] Exemplarily, Figure 3a shows the process of the LMF-initiated UserPlane Connection in the relevant protocol, Figure 3b shows the process of the UE-initiatedUser Plane Connection in the relevant protocol.

[0091] Next, in conjunction with the accompanying drawings, the information transmission method provided in the embodiments of the present application will be described in detail through some embodiments and their application scenarios.

[0092] Please refer to Figure 4 , Figure 4 which is a flowchart of an information transmission method provided in the embodiments of the present application. This method can be executed by a terminal. As Figure 4 shown, it includes the following steps:

[0093] Step 401, the terminal receives a first message through the user plane connection with the first target network element;

[0094] Among them, the first message includes information related to the AI model, and the information related to the AI model includes at least one of the following:

[0095] The identification information of the AI model;

[0096] The file information of the AI model;

[0097] The attribute information of the AI model;

[0098] The download address of the AI model.

[0099] In this embodiment, the above first target network element may include, but is not limited to, at least one of a network element for managing a target service, a network element for managing an AI model, etc. For example, if the target service is a positioning service, the above network element for managing the target service may include an LMF, the above AI model may be a model related to the positioning service, and the above network element for managing the AI model may include an NWDAF.

[0100] The identification information of the above AI model may include, but is not limited to, at least one of the ID of the model, the Analytics ID, the Functionality ID, etc. Among them, the above Analytics ID is used to describe the purpose or scenario of the AI model. For example, AI positioning, UE mobility, etc. It should be noted that the above model ID may be a globally unique identifier, or may be a locally unique identifier. For example, a unique identifier within a Public Land Mobile Network (PLMN). In this embodiment, since the identification information of the AI model can uniquely identify the AI model globally or locally, therefore, the identification information of the AI model can help the terminal to perform convenient and fast retrieval. For example, when subsequently using, updating, or deleting the AI model, the network and the terminal only need to use the AI model identification information, and do not need to interact with a large amount of model file information.

[0101] The file information of the above AI model may include, but is not limited to, model parameter information, model structure information, etc. In this embodiment, the file information of the AI model is the specific parameters and execution files of the model. The file information of the AI model may be a standardized file (such as exe, xml, etc.), or a non-standardized file supported for installation or use by the terminal, which can help the terminal perform AI inference under various different services and improve the service quality.

[0102] The attribute information of the above AI model may include, but is not limited to, the usage information of the model (e.g., model validity period, effective range, etc.), the size of the model, the applicable range of the model, the generalization information of the model, and other attribute parameters. In this embodiment, the terminal can determine whether it is suitable to use the AI model in certain geographical regions and certain access scenarios and whether the accuracy of the AI model meets the requirements according to the generalization information of the model. In addition, the size of the model (mainly referring to the required storage space, such as 100 MB, 1 GB) can help the terminal determine which model to download according to its own storage space. For example, when the network does not provide the file information of the above AI model but provides the model download address, the network provides the size of the model to the terminal, and the terminal can determine whether to download a larger model or a smaller model according to its remaining storage space, so as to balance its own storage space and the AI service experience.

[0103] The download address of the above AI model can be used by the terminal to download the AI model. For example, the terminal requests to download the AI model, such as the file information of the AI model, from the device corresponding to the download address of the above AI model, such as the address of the OTT server, based on the request method of the application layer Hypertext Transfer Protocol (HTTP). In practical applications, some models may not be generated by 3GPP training but are provided by a third party (such as an OTT server). In this embodiment, by providing the download address information of the AI model to the terminal, the terminal can choose whether to download the model and select the appropriate model to download. In addition, by providing the download address information of the AI model to the terminal, it is also possible to avoid sending the model file to the terminal every time the model is transmitted, which can achieve the purpose of saving signaling.

[0104] Exemplarily, in the case where it is necessary to transmit the relevant information of the AI model, the terminal and the first target network element can reuse the existing user plane connection to transmit the relevant information of the AI model. For example, if there is already a user plane connection for transmitting positioning-related information between the terminal and the first target network element, the terminal and the first target network element can reuse the existing user plane connection for transmitting positioning-related information to transmit the relevant information of the AI model; or, if there is no user plane connection between the terminal and the first target network element, the terminal and the first target network element can establish a new user plane connection or a user plane connection dedicated to AI model transmission to transmit the relevant information of the AI model.

[0105] Among them, the establishment of a new user plane connection or a user plane connection dedicated to AI model transmission between the above terminal and the first target network element can be triggered or initiated by the terminal or by the first target network element. Optionally, when the first target network element is a network element that manages the target service, the specific process of establishing a new user plane connection or a user plane connection dedicated to AI model transmission between the above terminal and the first target network element can refer to the process of establishing a user plane connection between the terminal and the first target network element in the related art. For example, it can refer to the aforementioned LCS User Plane Positioning (LCS-UPP) protocol.

[0106] The above first message can be carried in the existing user plane signaling, or can be carried in the newly defined or added user plane signaling. For example, the user plane signaling dedicated to the AI model. Exemplarily, the above newly added user plane signaling may include at least one of the following:

[0107] Message type (message type) Information Element (IE), used to indicate the message for AI model transmission, or the response message of the model request, or the message for model update transmission, or the response message of the model update, etc.;

[0108] Model identification information IE, used to indicate the identification information of the AI model;

[0109] Model file information IE, used to carry the file information of the AI model;

[0110] Model attribute information IE, used to carry the attribute information of the AI model.

[0111] Exemplarily, when the relevant information of the AI model received by the terminal includes the file information of the AI model, the terminal can perform processing such as inference or continued training based on the received file information of the AI model. For example, perform positioning based on the file information of the AI model; when the relevant information of the AI model received includes the download address of the AI model, the terminal can download the file information of the AI model based on the download address of the AI model, and then can perform processing such as inference or continued training based on the downloaded file information of the AI model.

[0112] In the embodiments of the present application, the terminal receives a first message through the user plane connection with the first target network element; wherein, the first message includes information related to the AI model, and the information related to the AI model includes at least one of the following: identification information of the AI model; file information of the AI model; attribute information of the AI model; download address of the AI model, that is, in the embodiments of the present application, the network side transmits the information related to the AI model to the terminal through the user plane connection with the terminal, so that the network side can conveniently transmit the AI model to the terminal.

[0113] Optionally, the first target network element includes a first network element or a second network element, wherein the first network element is a network element that manages the target service, the AI model is a model related to the target service, and the second network element is a network element that manages the AI model.

[0114] For example, in the case where the terminal needs to obtain an AI model related to the positioning service, the above-mentioned network element that manages the target service may be the LMF, and the above-mentioned network element that manages the AI model may be the NWDAF; in the case where the terminal needs to obtain an AI model related to the sensing service, the above-mentioned network element that manages the target service may be a sensing function or network element, and the above-mentioned network element that manages the AI model may be the NWDAF.

[0115] In some embodiments, the above-mentioned network element that manages the target service and the above-mentioned network element that manages the AI model may be the same network element, such as the LMF. The AI model related to positioning may be generated locally by the LMF or successfully obtained by requesting the NWDAF before, and then saved locally by the LMF. Therefore, the LMF does not need to obtain a new model from the NWDAF.

[0116] In one embodiment, in the case where the AI model is a model related to the target service, the information related to the AI model is sent to the terminal through the user plane connection between the network element that manages the target service and the terminal, which is convenient for the network element that manages the target service to manage the target service.

[0117] In another embodiment, the information related to the AI model is sent to the terminal through the user plane connection between the network element that manages the AI model and the terminal, which is convenient for the quick sending of the information related to the AI model.

[0118] Optionally, before the terminal receives the first message through the user plane connection with the first target network element, the method further includes:

[0119] The terminal sends a first request message to a second target network element;

[0120] wherein, the first request message is used to request to obtain the AI model.

[0121] Exemplarily, the above first request message may include at least one of the identification information of the AI model, the indication information for indicating that the terminal needs to obtain the AI model, the indication information for indicating that the AI model needs to be transmitted through the user plane, the description information of the AI model, the address information of the model storage network element, the service type of using the model, etc. Among them, the above service type of using the model is used to indicate the service to which the requested AI model is applied. For example, services such as positioning and sensing.

[0122] The above second target network element includes a first network element or a second network element or a forwarding network element (such as AMF, SMF), etc.

[0123] The following is an example for illustration by cases:

[0124] Case 1: The terminal sends a first request message to the first network element, and the first network element replies to the terminal with a first message.

[0125] For example, the terminal sends a first request message to the first network element to request to obtain an AI model; after receiving the first request message, the first network element sends a first message carrying the relevant information of the AI model to the terminal through the user plane connection with the terminal.

[0126] Case 2: The terminal sends a first request message to the first network element, and the second network element replies to the terminal with a first message.

[0127] For example, the terminal sends a first request message to the first network element to request to obtain an AI model; after receiving the first request message, the first network element sends a second request message to the second network element to request to obtain an AI model; after receiving the second request message, the second network element sends a first message carrying the relevant information of the AI model to the terminal through the user plane connection with the terminal.

[0128] Case 3: The terminal sends a first request message to the second network element, and the second network element replies to the terminal with a first message.

[0129] For example, the terminal sends a first request message to the second network element to request to obtain an AI model; after receiving the first request message, the second network element sends a first message carrying the relevant information of the AI model to the terminal through the user plane connection with the terminal.

[0130] Case 4: The terminal sends a first request message to the second network element, and the first network element replies to the terminal with a first message.

[0131] For example, the terminal sends a first request message to a second network element to request an AI model. After receiving the first request message, the second network element sends a second request message to a first network element to request an AI model. After receiving the second request message, the first network element sends a first message carrying information related to the AI model to the terminal through the user plane connection with the terminal.

[0132] Situation Five: The terminal sends a first request message to a forwarding network element (such as AMF, SMF, etc.), and the first network element replies to the terminal with a first message.

[0133] For example, the terminal sends a first request message to a forwarding network element to request an AI model. After receiving the first request message, the second network element forwards the first request message to the first network element. After receiving the first request message forwarded by the forwarding network element, the first network element sends a first message carrying information related to the AI model to the terminal through the user plane connection with the terminal.

[0134] Situation Six: The terminal sends a first request message to a forwarding network element (such as AMF, SMF, etc.), and the second network element replies to the terminal with a first message.

[0135] For example, the terminal sends a first request message to a forwarding network element to request an AI model. After receiving the first request message, the forwarding network element sends a target request message to the first network element to request an AI model. After receiving the target request message, the first network element sends a second request message to the second network element. After receiving the second request message, the second network element sends a first message carrying information related to the AI model to the terminal through the user plane connection with the terminal.

[0136] In this embodiment, the terminal sends a first request message to a second target network element, which facilitates the network side to more accurately and conveniently obtain information related to the required AI model based on the first request message.

[0137] Optionally, the first request message includes at least one of the following:

[0138] First indication information for indicating that the terminal needs to obtain an AI model;

[0139] Second indication information for indicating that the AI model needs to be transmitted through the user plane;

[0140] Identification information of the AI model;

[0141] Description information of the AI model;

[0142] Identification information of the terminal;

[0143] First capability information for indicating that the terminal supports obtaining an AI model through the user plane;

[0144] The model stores the address information of the network element;

[0145] The type of service that uses the model.

[0146] In this embodiment, the first indication information is used to indicate a request to obtain an AI model. It should be noted that the first indication information can be explicit indication information or implicit indication information. For example, when the terminal sends a model request message as the first request message, the message type (message type) of the first request message indicates a model request (modelrequest), and the network side identifies the message type of the first request message as the first indication information, that is, it understands that the UE is requesting an AI model. In this embodiment, the purpose of the first request message is identified by the first indication information, that is, the terminal needs to obtain an AI model, which can help the network side identify that the first request message is for requesting a model, rather than a model confirmation reply, and can more clearly express the terminal's needs.

[0147] The above-mentioned second indication information is used to indicate the transmission of the AI ​​model through the user plane. It should be noted that when the terminal sends the first request message to the network side through the user plane, optionally, the first request message may carry the second indication information, which is used to instruct the network side to transmit the AI ​​model information through the user plane. In this embodiment, the terminal indicates through the second indication information how it wishes to send the relevant information of the AI ​​model to the terminal. Since the terminal and the network can interact in various ways such as APP layer transmission and 3GPP architecture transmission, the second indication information clearly indicates the use of the user plane to pass the relevant information of the AI ​​model to the terminal, which can avoid the network side using a random selection of transmission methods for transmission. In addition, the use of user plane transmission can download large models to the terminal more quickly, thereby improving the efficiency of model downloading.

[0148] The identification information of the above-mentioned terminal may include but is not limited to at least one of the terminal (i.e., UE) ID (for example, a user permanent identifier (Subscription Permanent Identifier, SUPI)) and the vendor (Vendor) ID. In this embodiment, the identification information of the above-mentioned terminal is used to identify the identity of the requester, which can help the network side record which users of the model are used. When the model needs to be monitored, updated, or modified later, the user can be found quickly. For example, when the network side needs to delete the model, a deletion request can be sent to the user of the model in a targeted manner instead of broadcasting, which can improve the network side's management efficiency of the model.

[0149] The description information of the above AI model may include parameter information for describing model requirements. In this embodiment, the requirements of a certain AI model are described through the description information of the AI model, which can help the network side quickly identify or determine which model should be used / downloaded to the terminal. In one case, the terminal may not know the identification information of the model. The terminal only knows what its requirements for the model are (for example, what service the model is used for and who the user of the model is). Through the description information of the AI model, the network can know in more detail the requirements of the terminal for the AI model, helping the network side select / train and generate a more suitable model from among many AI models instead of randomly sending down a model, which can improve the interaction efficiency between the terminal and the network and the experience of the terminal using the AI model.

[0150] It should be noted that the identification information of the above AI model can be understood as the identification information of the AI model requested by the terminal, and the description information of the above AI model can be understood as the description information of the AI model requested by the terminal.

[0151] The address information (address) of the above model storage network element, for example, LMF address / NWDAF address / OTT server address. Among them, the address information of the above model storage network element can be pre-configured in the terminal, and the first network element can send the first request message to the above model storage network element according to the address information of the above model storage network element. In this embodiment, the address information of the model storage network element can indicate to the network where to obtain the model, which can help the network element that forwards the first request message (such as AMF) know which network element the first request message should be forwarded to. In practical applications, as the network element that acts as a message relay (i.e., the forwarding network element), it may not know to whom the message can be forwarded. In this embodiment, by providing the address information of the above model storage network element, the request message of the model (i.e., the first request message) can be successfully sent to the target network element (such as NWDAF, LMF), improving the message forwarding efficiency.

[0152] The above service type for using the model is used to indicate the service to which the requested AI model is applied, for example, services such as positioning and communication sensing. In this embodiment, the service type for using the model can indicate to the network the service to which the model requested by the terminal is applicable, and this service type for using the model can be used by the forwarding network element that forwards the first request message. Exemplarily, if the terminal does not know the address information of the model storage network element and only knows what service the requested model is used for, such as positioning or communication sensing, then after the forwarding network element receives the first request message, it can forward the model request to the corresponding LMF or Sensing Function (SF) according to the service type for using the model, which is beneficial to improving the message forwarding efficiency.

[0153] The above first capability information is used to indicate that the terminal has the capability to obtain the AI model through the user plane. Through this first capability information, it can help the network side select an appropriate model download method. For example, if the terminal does not support downloading the AI model through the user plane, then the network side may not be able to use the user plane connection to download the model. This allows the network to fully consider and be aware of the device conditions of the terminal regarding model transfer, improving the efficiency of transferring the model. In one scenario, the terminal does not carry the second indication information, so the network can decide to transfer the model to the terminal through the user plane based on the first capability information.

[0154] It should be noted that in the case where the above first request message includes at least one of the address information of the model storage network element and the service type using the model, the above second target network element may be a forwarding network element. In this case, the second target network element can determine the target network element based on at least one of the address information of the model storage network element and the service type using the model, and forward the above first request message or send the target request message determined according to the first request message to the target network element. Among them, the above target request message may include each item of information in the first request message except the address information of the model storage network element. For example, in the case where the above first request message includes the address information of the model storage network element, the above target network element may be the model storage network element; in the case where the terminal does not provide the address information of the model storage network element, it is possible to judge the purpose of the model requested by the terminal based on the above service type using the model, and determine the target network element (LMF, NWDAF or other network elements) based on the purpose of the model requested by the terminal. It can be understood that at least one of the above address information of the model storage network element and the service type using the model may be visible to forwarding network elements such as AMF and SMF.

[0155] It should also be noted that in the case where the terminal sends the first request message to the first target network element through the control plane signaling, the above first request message optionally carries the above second indication information, where the above second indication information is used to indicate the transfer of the AI model through the user plane connection.

[0156] It should also be noted that in the case where the terminal sends the first request message to the first target network element through the control plane signaling, the above first request message may include at least one of the address information of the model storage network element and the service type using the model; while in the case where the terminal sends the first request message to the first target network element through the user plane connection, the above first request message may not include at least one of the address information of the model storage network element and the service type using the model.

[0157] Optionally, the description information of the AI model includes at least one of the following:

[0158] Service type indication information, used to indicate the service type that the requested model needs to provide;

[0159] Information about the model usage object;

[0160] The type of model input data, where the type of model input data includes at least one of the type of input data required for model inference and the type of input data required for model training;

[0161] The type of model inference result.

[0162] The above service type indication information is used to indicate the service type that the requested model needs to provide. For example, the requested model is used to provide services such as positioning or remote sensing. In this embodiment, through the service type indication information, the network element that manages the model can train the correct model when training the model, or can retrieve more systematically when searching for the model, so as to obtain a model that meets the terminal's requirements. For example, some models are for positioning, some models are suitable for remote sensing, and some are for image recognition. When the terminal provides the above service type indication information to the network, it can more accurately express the terminal's requirements for the model, avoid the network training / downloading a model with a wrong usage purpose, and thus improve the interaction efficiency between the terminal and the network.

[0163] The above information about the model usage object is used to indicate the object that can use the model. For example, UE, Programmable Real-time Unit (PRU), gNB, etc. In this embodiment, through the information about the model usage object, the terminal can more accurately express its requirements for the model. For example, in positioning, for the same positioning AI model, some may be used by the core network, and some may be used by the access network. The generalization effect and accuracy are different for different users. Therefore, clearly indicating the model usage object through the above information about the model usage object can help the network send a more accurate model. In addition, considering that the usage effect of the same model may be different on the terminals of different terminal manufacturers, and the privacy settings for downloading the model are also different, taking this requirement into account, the terminal can tell the network which terminal device the user is. The more detailed the information about the model test object provided, the clearer the network can know the terminal's requirements, and thus it is beneficial for the network to download a more suitable model to the terminal.

[0164] The type of input data required for the above model inference can be understood as the type of input data required for the AI model to perform inference. For example, for an AI model related to positioning, the type of input data required for the above model inference can be used to indicate positioning-related data. The type of input data required for the above model training can be understood as the type of data used for AI model training, such as Channel Impulse Response (CIR) / Power Delay Profile (PDP) / Delay Profile (DP). By providing the type of the above model input data in this embodiment, the terminal's requirements for the model can be expressed more accurately, which is conducive to the network downloading a more suitable model to the terminal.

[0165] The type of the above model inference result can be understood as the type of data output by using the AI model for inference. For example, for an AI model related to positioning, the type of the above model inference result can be used to indicate location information or measured intermediate feature information. By providing the type of the above model inference result in this embodiment, the terminal's requirements for the model can be expressed more accurately, which is conducive to the network downloading a more suitable model to the terminal.

[0166] Optionally, the terminal sends a first request message to the second target network element, including:

[0167] The terminal sends the first request message to the second target network element through the user plane connection between the terminal and the second target network element;

[0168] Or,

[0169] The terminal sends the first request message to the second target network element through control plane signaling.

[0170] In one implementation, the terminal can send the first request message to the second target network element through the user plane connection between the terminal and the second target network element. Exemplarily, the terminal can reuse the existing user plane connection between the terminal and the second target network element to transmit the above first request message. For example, if there is an existing user plane connection for transmitting positioning-related information between the terminal and the second target network element, the terminal and the second target network element can reuse the existing user plane connection for transmitting positioning-related information to transmit the first request message; or, if there is no user plane connection between the terminal and the second target network element, the terminal and the second target network element can establish a new user plane connection or a user plane connection dedicated to AI model transmission to transmit the first request message. Optionally, the above first request message can carry trigger reason information for indicating the transmission of the AI model.

[0171] In this embodiment, the terminal can send the first request message point-to-point to the network through the user plane, directly sending the first request message to the network without the need for intermediate network elements in the control plane to forward it. This enables fast and efficient requests and responses, and can also support periodic or relatively frequent interactions for model requests, improving the transfer efficiency of the model.

[0172] Exemplarily, the above first request message can be carried in a newly defined or added user plane signaling, and the message type carried by the message type IE of this user plane signaling is used to indicate the model request message.

[0173] Optionally, when the above first target network element is the same as the second target network element, the above first request message and the first message can be transmitted using the same user plane connection between the terminal and the second target network element, which is beneficial for simplifying the signaling control in the AI model transfer process.

[0174] In another embodiment, the terminal can send the first request message to the second target network element through control plane signaling, which is beneficial for more conveniently implementing the transfer of the first request message. Exemplarily, the above first request message is carried in a control plane bearer or container and transmitted to the network side. For example, the above first request message can be carried in an existing control plane container of an existing protocol and transmitted to the network side, or the above first request message can be carried in a newly defined or added control plane container and transmitted to the network side.

[0175] In this embodiment, when the terminal transmits the first request message through the control plane, it can reuse the existing connections between network elements and use the mechanism of network element forwarding to send the request message to the network element that manages the model, without the need to establish / use a user plane connection channel for model transfer, reducing the user plane connection and user plane resource overhead, and lowering the implementation requirements for the terminal / network device.

[0176] Optionally, the method further includes:

[0177] The terminal sends a first response message to the first target network element through the user plane connection between the terminal and the first target network element, where the first response message is used to indicate whether the terminal has successfully received the relevant information of the AI model.

[0178] Exemplarily, the above first response message can include indication information on whether the AI model has been successfully received, reason information for receiving failure, etc.

[0179] Exemplarily, the above first response message can be carried in a newly defined or added user plane signaling, and the message type carried by the message type IE of this user plane signaling is used to indicate the model transfer reply message.

[0180] It should be noted that each response message involved in the embodiments of the present application may also be referred to as a reply message, a feedback message, etc.

[0181] In this embodiment, the terminal sends a first response message to the first target network element through the user plane connection between the terminal and the first target network element, which can directly send the first response message point-to-point to the network without the need for an intermediate network element on the control plane to forward it. It can quickly and efficiently perform requests and responses, and can also support periodic or relatively frequent interactions of model responses, which can improve the transmission efficiency of the model. In addition, the terminal receives a first message through the user plane connection between the terminal and the first target network element, and sends a first response message to the first target network element through the user plane connection between the terminal and the first target network element, which is beneficial to simplifying the signaling control in the AI model transmission process.

[0182] Optionally, when the first response message is used to indicate that the terminal fails to receive the relevant information of the AI model, the first response message includes cause information, and the cause information is used to indicate the reason for the terminal's failure to receive the relevant information of the AI model.

[0183] Exemplarily, the reasons for the terminal's failure to receive the relevant information of the AI model may include at least one of the following: incorrect model format, invalid download address.

[0184] In some alternative embodiments, the terminal may send a first response message to the first target network element through control plane signaling, where the first response message is used to indicate whether the terminal has successfully received the relevant information of the AI model.

[0185] Optionally, before the terminal receives the first message through the user plane connection with the first target network element, the method further includes:

[0186] When the terminal needs to obtain the relevant information of the AI model, the terminal sends a User Plane Connection Establishment Request message, where the User Plane Connection Establishment Request message is used to request the establishment of a user plane connection between the terminal and the first target network element.

[0187] In this embodiment, when the terminal needs to obtain the relevant information of the AI model, the terminal can trigger or initiate the establishment of a user plane connection between the terminal and the first target network element, that is, the terminal sends a User Plane Connection Establishment Request message.

[0188] In this embodiment, the establishment of a user plane connection is triggered by the terminal to transfer the model, which enables the terminal to actively establish a user plane connection in a timely manner to prepare for the transfer of the model in advance, rather than waiting for the network side to trigger the establishment of the user plane connection. In this way, when the network side decides to send down the model, it can directly use the established user plane connection, which can reduce the latency and improve the model download efficiency.

[0189] Optionally, the user plane connection establishment request message carries a trigger reason value for indicating that the trigger reason is model transfer.

[0190] In this embodiment, during the process of establishing a user plane connection between the terminal and the first target network element, the request message for establishing the user plane sent by the terminal carries a trigger reason value, which is used to indicate that the trigger reason is model transfer. That is, the user plane connection establishment request (User Plane Connection Establishment Request) message carries a trigger reason value for indicating that the trigger reason is model transfer. Exemplarily, the above User Plane Connection Establishment Request message includes a trigger reason value, and the User Plane Connection Establishment Request is included in the User Plane Positioning Protocol Connection Management Information (UPP-CMI) container. The UPP-CMI container belongs to an IE in the NAS signaling. The UE will encapsulate this UPP-CMI container in the NAS message and send it to the AMF. The AMF will transparently transmit this UPP-CMI container when receiving the NAS message and forward it to the LMF.

[0191] Optionally, after the terminal receives the first message through the user plane connection with the first target network element, the method further includes:

[0192] The terminal receives a second message through the user plane connection with the first target network element, where the second message includes update information of the AI model;

[0193] The terminal sends a second response message to the first target network element through the user plane connection with the first target network element, where the second response message is used to indicate whether the terminal has successfully received the update information of the AI model.

[0194] Exemplarily, the update information of the above AI model may include the information of the AI model after update. For example, the file information of the AI model after update, the attribute information of the AI model after update, etc. The above second response message may include indication information on whether the update information of the AI model is successfully received, reason information for receiving failure, etc.

[0195] Exemplarily, when the relevant information of the above AI model is stored in the first target network element, when the first target network element updates the above AI model, it may send the information of the AI model after update to the terminal; when the relevant information of the above AI model is stored in a network element different from the above first target network element, the network element storing the relevant information of the AI model may, after updating the above AI model, send the information of the AI model after update to the first target network element, and then the first target network element may send the information of the AI model after update to the terminal. For example, if the above first target network element is the LMF and the relevant information of the above AI model is stored in the NWDAF, the NWDAF may, after updating the AI model, send the information of the AI model after update to the LMF, and then the LMF may send the information of the AI model after update to the terminal.

[0196] Exemplarily, the above second message may be carried in a newly defined or newly added first user plane signaling, and the message type carried by the message type IE of this first user plane signaling is used to indicate a model transfer message, a model update message, etc. The above second response message may be carried in a newly defined or newly added second user plane signaling, and the message type carried by the message type IE of this second user plane signaling is used to indicate a model response message, a model update response message, etc.

[0197] In this embodiment, the terminal receives the second message through the user plane connection with the first target network element, where the second message includes the update information of the AI model, and sends a second response message to the first target network element through the user plane connection with the first target network element, where the second response message is used to indicate whether the terminal successfully receives the update information of the AI model, which is beneficial to ensuring the consistency of the understanding of the transmission situation of the update information of the above AI model between the terminal and the network side.

[0198] Please refer to Figure 5 , Figure 5 which is a flowchart of an information transmission method provided by an embodiment of the present application. This method may be executed by a first target network element. As Figure 5 shown, it includes the following steps:

[0199] Step 501, the first target network element sends a first message through the user plane connection with the terminal;

[0200] Among them, the first message includes information related to the AI model, and the information related to the AI model includes at least one of the following:

[0201] The identification information of the AI model;

[0202] The file information of the AI model;

[0203] The attribute information of the AI model;

[0204] The download address of the AI model.

[0205] Optionally, the first target network element includes a first network element or a second network element. Among them, the first network element is a network element that manages the target service, the AI model is a model related to the target service, and the second network element is a network element that manages the AI model.

[0206] Optionally, before the first target network element sends the first message through the user plane connection with the terminal, the method further includes:

[0207] The first target network element receives a first request message sent by the terminal;

[0208] Among them, the first request message is used to request to obtain an AI model.

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

[0210] The first indication information, which is used to indicate that the terminal needs to obtain an AI model;

[0211] The second indication information, which is used to indicate that the AI model needs to be transmitted through the user plane;

[0212] The identification information of the AI model;

[0213] The description information of the AI model;

[0214] The identification information of the terminal;

[0215] The first capability information, which is used to indicate that the terminal supports obtaining an AI model through a user plane connection;

[0216] The address information of the model storage network element;

[0217] The service type for using the model.

[0218] Optionally, the description information of the AI model includes at least one of the following:

[0219] The service type indication information, which is used to indicate the service type that the requested model needs to provide;

[0220] The information of the model usage object;

[0221] The type of model input data, where the type of model input data includes at least one of the type of input data required for model inference and the type of input data required for model training;

[0222] The type of model inference result.

[0223] Optionally, the first target network element receives a first request message sent by the terminal, including:

[0224] The first target network element receives the first request message sent by the terminal through the user plane connection with the terminal;

[0225] Or,

[0226] The first target network element receives the first request message sent by the terminal through control plane signaling.

[0227] Optionally, before the first target network element sends a first message through the user plane connection with the terminal, the method further includes:

[0228] When the first target network element determines to transmit information related to the AI model to the terminal through the user plane connection, the first target network element determines the identification information of the AI model;

[0229] The first target network element obtains information related to the AI model according to the identification information of the AI model.

[0230] Exemplarily, when the first target network element receives the first request message, the first target network element may determine to transmit information related to the AI model to the terminal through the user plane connection according to the first request message, and determine the identification information of the AI model according to the first request message. Exemplarily, when the above first request message includes the identification information of the AI model, the identification information of the AI model can be directly obtained from the first request message. When the above first request message does not include the identification information of the AI model, the identification information of the AI model can be determined based on the above first request message. For example, the identification information of the AI model is determined based on the description information of the AI model included in the above first request message; when the first target network element does not receive the first request message, the first target network element may determine by itself to transmit information related to the AI model to the terminal through the user plane connection and determine the identification information of the AI model.

[0231] After determining the identification information of the AI model, if the first target network element locally stores the relevant information of the AI model, the first target network element may obtain the relevant information of the AI model from the local and send it to the terminal; alternatively, the first target network element may send a request message carrying the identification information of the AI model to the network element storing the relevant information of the AI model to request to obtain the relevant information of the AI model, and may receive the relevant information of the AI model sent by the network element storing the relevant information of the AI model. For example, if the first target network element is an LMF, the LMF may send a request message carrying the identification information of the AI model to the LMF or NWDAF storing the relevant information of the AI model, and may receive the relevant information of the AI model sent by the LMF or NWDAF storing the relevant information of the AI model.

[0232] In some alternative embodiments, the first target network element may query the NRF to query the storage address of the AI model indicated by the identification information of the AI model, and send a model request message to the network element corresponding to the storage address to request to obtain the relevant information of the AI model.

[0233] In this embodiment, when the first target network element determines to transmit the relevant information of the AI model to the terminal through the user plane connection, it determines the identification information of the AI model, and obtains the relevant information of the AI model according to the identification information of the AI model. That is, the first target network element decides whether to transmit the relevant information of the AI model to the terminal through the user plane connection and determines the identification information of the AI model, which is beneficial to more accurately control the transmission of the AI model and can reduce the failure of the AI model transmission caused by network-side factors.

[0234] In some alternative embodiments, when the first target network element is a second network element, the first network element may determine that it is necessary to transmit the relevant information of the AI model to the terminal, determine the identification information of the AI model, and send it to the second network element; the second network element receives the identification information of the AI model from the first network element, obtains the relevant information of the AI model based on the identification information of the AI model, and sends the relevant information of the AI model to the terminal through the user plane connection with the terminal.

[0235] Optionally, the method further includes:

[0236] The first target network element receives a first response message sent by the terminal through the user plane connection with the terminal, where the first response message is used to indicate whether the terminal successfully receives the relevant information of the AI model.

[0237] Optionally, when the first response message is used to indicate that the terminal fails to receive the relevant information of the AI model, the first response message includes cause information, which is used to indicate the reason why the terminal fails to receive the relevant information of the AI model.

[0238] Optionally, before the first target network element sends the first message through the user plane connection with the terminal, the method further includes:

[0239] When it is determined that the relevant information of the AI model needs to be transmitted to the terminal, the first target network element sends a User Plane Connection Establishment Command message, where the User Plane Connection Establishment Command message is used to indicate the establishment of the user plane connection between the first target network element and the terminal.

[0240] In this embodiment, when it is determined that the relevant information of the AI model needs to be transmitted to the terminal, the first target network element may trigger or initiate the establishment of the user plane connection between the first target network element and the terminal, that is, the first target network element sends a User Plane Connection Establishment Command message to indicate the establishment of the user plane connection between the first target network element and the terminal.

[0241] In this embodiment, the model transmission can directly trigger the establishment of the user plane connection between the terminal and the first target network element, which is beneficial to quickly establish a user plane connection that can be used to transmit the relevant information of the AI model between the terminal and the first target network element.

[0242] Optionally, the User Plane Connection Establishment Command message carries a trigger cause value indicating that the trigger cause is model transmission.

[0243] In this embodiment, during the process of establishing the user plane connection between the first target network element and the terminal, the User Plane Connection Establishment Command message sent by the first target network element may carry a trigger cause value, which is used to indicate that the trigger cause is model transmission.

[0244] Optionally, the method further includes:

[0245] The first target network element sends a second message through the user plane connection with the terminal, where the second message includes the update information of the AI model;

[0246] The first target network element receives a second response message through the user plane connection with the terminal, where the second response message is used to indicate whether the terminal successfully receives the update information of the AI model.

[0247] Optionally, the first target network element is the first network element;

[0248] Before the first target network element sends a first message through a user plane connection with the terminal, the method further includes:

[0249] The first target network element sends a second request message to a second network element, where the second request message includes identification information of an AI model, or the second request message includes identification information of the AI model and identification information of the terminal;

[0250] The first target network element receives a third response message sent by the second network element, where the third response message includes relevant information of the AI model.

[0251] In this embodiment, the above identification information of the AI model may include, but is not limited to, at least one of a model ID, an analytics ID, a functionality ID, etc. The above identification information of the terminal may include, but is not limited to, at least one of a terminal (i.e., UE) ID (e.g., SUPI) and a vendor ID, for the second network element to know the specific consumer.

[0252] Exemplarily, the first target network element sends a second request message to the second network element; the second network element receives the second request message sent by the first target network element, and may obtain relevant information of the AI model based on the identification information of the AI model included in the second request message, and send it to the first target network element.

[0253] Optionally, the first target network element is the second network element;

[0254] Before the first target network element sends a first message through a user plane connection with the terminal, the method further includes:

[0255] The first target network element receives a third request message sent by the first network element, where the third request message includes identification information of an AI model, or the third request message includes identification information of the AI model and identification information of the terminal;

[0256] The first target network element sends a fourth response message to the first network element, where the fourth response message includes relevant information of the AI model.

[0257] In this embodiment, the identification information of the above AI model may include, but is not limited to, at least one of the ID of the model, the Analytics ID, the Functionality ID, etc. The identification information of the above terminal may include, but is not limited to, at least one of the terminal (i.e., UE) ID (e.g., SUPI) and the Vendor ID, for the second network element to know the specific consumer.

[0258] Exemplarily, the first network element sends a third request message to the first target network element; the first target network element receives the third request message sent by the first network element, and may obtain the relevant information of the AI model based on the identification information of the AI model included in the third request message, and send it to the first network element.

[0259] It should be noted that the implementation manner of this embodiment can refer to Figure 4 the relevant description of the embodiment shown, which will not be elaborated here.

[0260] The embodiments of the present application will be described below with examples:

[0261] Example 1: Reuse the user plane and control plane interaction requirements between the UE and the LMF to issue / update the model, and issue the model on the user plane.

[0262] Referring to Figure 6a , the information transmission method provided in this embodiment may include the following steps:

[0263] Step 0a, a Mobile Terminated Location Request (MT-LR) or a deferred MT-LR triggers the LMF to use an AI model to locate the UE;

[0264] Or,

[0265] Step 0b, a Mobile Originated Location Request (MO-LR) triggers the LMF to need to use an AI model to locate the UE, or the UE requests to obtain an AI model to perform AI positioning or other AI tasks. Specifically, in this step, the UE sends a first request message to the LMF. The relevant content of the first request message can refer to the relevant description of the foregoing embodiment and will not be elaborated here.

[0266] It should be noted that the first request message sent in step 0b above can be carried in a newly defined or added control plane Container and transmitted to the network side.

[0267] Step 1: The LMF determines to use AI positioning or other AI tasks and determines the model identification information.

[0268] For the above step a0, the LMF determines the analysis ID / model ID by itself, for example, by interacting with the NWDAF to determine the model identification information; for the above step 0b, the LMF determines to use AI positioning or transfer the AI model to the UE according to the first request message sent by the UE, determines the analysis ID / model ID, and decides to transfer the AI model to the UE through the user plane.

[0269] Here, a new trigger reason for the LMF to establish a user plane connection is added: transfer model. This trigger reason indicates that the network side needs to send the AI model to the UE through the user plane. In the case where there is no connection between the LMF and this UE currently, the LMF needs to trigger the process of the network-initiated user plane connection, provide the LMF address to the UE in step 4, and then the UE and the LMF establish a user plane connection through steps 5 - 6.

[0270] It should be noted that the LMF determines the analysis ID / model ID according to the first request message sent by the terminal. When the analysis ID / model ID is directly carried in the first request message, the LMF can directly use this analysis ID / model ID to request the relevant information of the AI model from the NWDAF; if it is not carried, the LMF can determine the analysis ID / model ID according to the description information of the AI model.

[0271] It should also be noted that the LMF can also query the NRF to query the storage address of the required AI model, such as the NWDAF, or other LMFs, and further execute step 2 to send a model request message. In one implementation, if the AI model exists in the current LMF, steps 2 and 3 are not executed. When the LMF determines that it stores this AI model, it can directly send this AI model to the UE without requesting this model from the NWDAF.

[0272] Step 2: The LMF sends a model request message to the NWDAF, carrying the analysis ID / model ID and the UE ID.

[0273] Step 3: The NWDAF sends the relevant information of the AI model to the LMF, where the AI model is the model indicated by the above analysis ID / model ID. The relevant information of this AI model can refer to the relevant description of the foregoing embodiments and will not be elaborated here.

[0274] Steps 4 - 6: A user plane connection is established between the UE and the LMF.

[0275] It should be noted that the above steps 4 - step 6 can refer to the process of establishing a user plane connection between the UE and the LMF in the prior art. In addition, the establishment of the user plane connection between the UE and the LMF can be initiated by the UE or by the LMF, and Figure 6a the description in Figure 6a takes the initiation by the LMF as an example.

[0276] It should also be noted that a new trigger reason for the network side to initiate the establishment of a user plane connection is added here: transfer model. If there is already a user plane connection between the UE and the LMF, this user plane connection can be directly used. If not, a new user plane connection between the UE and the LMF is created.

[0277] It should also be noted that Figure 6a the SMF / UPF in Figure 6a are not all applicable at the same time. For example, during the control plane signaling transfer (e.g., Figure 6a step 5), here it is the SMF, and during the subsequent user plane message transfer (e.g., Figure 6a steps 7 - step 8 in Figure 6a ), here it is the UPF. The relationship between the two is that the SMF is responsible for the selection and management of the UPF node. Therefore, in Figure 6a Figure 6a , the two are put together for the convenience of illustration.

[0278] Step 7, the LMF sends model - related information (i.e., the related information of the above - mentioned AI model) to the UE, carrying the model ID, model information (i.e., the file information of the above - mentioned AI model), model attribute information, model download address, etc.

[0279] For this step, one implementation method is to add a new user plane signaling, and the newly added user plane signaling can include at least one of the message type IE, model identification information IE, model file information IE, and model attribute information IE, etc.

[0280] Step 8, the UE sends a model response message to the LMF.

[0281] For this step, one implementation method is to add a new user plane signaling, and the newly added user plane signaling can include the message type IE, which is used to indicate the model transfer reply message. The above - mentioned model response message can indicate either successful reception or reception failure. Optionally, in the case of indicating reception failure, the above - mentioned model response message can also carry cause information to indicate the reason for reception failure.

[0282] Steps 9 - step 10: The NWDAF updates the model and notifies the LMF. The LMF sends the updated model to the UE through the user plane, that is, repeats steps 7 - step 8.

[0283] It should be noted that in order to distinguish the user plane signaling in step 10 from that in steps 7 and 8, the LMF will use new message type IEs. For example, the message for transferring model updates and the response message for model updates. In addition, the signaling also carries at least one of the updated model identification information IE, the updated model file information IE, and the updated model attribute information IE, etc.

[0284] Example 2: Reusing the user plane between the UE and the LMF, the user plane interaction requires the distribution / update of a model, and the model is distributed through the user plane.

[0285] The main difference between Example 2 and Example 1 is that the signaling triggering the LMF to distribute the model is triggered by the user plane signaling.

[0286] See Figure 6b , the information transmission method provided in this embodiment may include the following steps:

[0287] Steps 1 - 3 may be the user plane connection established between the UE and the LMF in a previous service, which may be initiated by the UE or the LMF. If not established, then after step 5, the LMF may initiate the process of establishing a user plane connection between the UE and the LMF, such as step 5a. Figure 6b It is described by taking the example that the user plane connection has been established between the UE and the LMF in a previous service.

[0288] It should be noted that in this example, a new trigger reason for establishing the user plane connection is added on both the UE side and the LMF side: transferring the model. In step 1, if it is initiated by the UE, the trigger reason of the UE may be for establishing the connection because the model needs to be transferred. Therefore, in the request message (for example, Figure 3b the step b1 of the UE initiating the user plane connection shown) carries the trigger reason: transferring the model. If there is no existing user plane connection, then as in step 5a, the LMF creates a new one. At this time, in the request message (for example, Figure 3a the step a2 of the LMF initiating the user plane connection shown) carries the trigger reason: transferring the model.

[0289] It should be noted that Figure 6b the SMF / UPF in Figure 6b are not all applicable at the same time. For example, during the control plane signaling transmission (for example, Figure 6b step 2 here is the SMF), and when the user plane message is transmitted later (for example, Figure 6b steps 4 and 8 here), it is the UPF. The relationship between the two is that the SMF is responsible for the selection and management of the UPF node. Therefore, in

[0290] Step 4: The UE sends a first request message to the LMF via the user plane connection, requesting to obtain a model to assist with AI positioning or an AI task. For the relevant content of this first request message, reference can be made to the relevant descriptions in the foregoing embodiments, which will not be elaborated here.

[0291] Step 5: The LMF determines to use AI positioning or other AI tasks or the LMF decides to transfer the AI model to the UE, determines the analysis ID / model ID, and decides to send it to the UE via the user plane.

[0292] If there is no existing user plane connection between the LMF and the UE, then as in step 5a, a new user plane connection from the UE to the LMF can be established. For example, reference can be made to Figure 3a the process of establishing a user plane connection initiated by the LMF shown.

[0293] Step 5a: The LMF initiates the establishment of a user plane connection between the UE and the LMF.

[0294] It should be noted that for the above steps 1 - step 3 and the above step 5a, only one of them can be executed. For example, only the above steps 1 - step 3 are executed, or only the above step 5a is executed.

[0295] Steps 6 - step 7: The interaction process between the LMF and the NWDAF. The request message sent by the LMF to the NWDAF carries the analysis ID / model ID and the UE ID; the LMF obtains the relevant information of the AI model from the NWDAF. For the relevant information of the AI model, reference can be made to the relevant descriptions in the foregoing embodiments, which will not be elaborated here.

[0296] Step 8: The LMF sends the model - related information (i.e., the relevant information of the above - mentioned AI model) to the UE via the user plane connection.

[0297] For this step, one implementation method can be to add a new user plane signaling, and the newly added user plane signaling includes a message type for indicating the response message to the model request.

[0298] An alternative implementation method can be to add two new user plane signalings, namely, a model transfer message and a model request rejection message. The model transfer message is used to transfer the relevant information of the above - mentioned AI model, and the model request rejection message is used to reject the UE's model request and optionally carry a rejection reason value.

[0299] Steps 9 - step 10: The NWDAF updates the model and notifies the LMF. The LMF sends the updated model to the UE via the user plane, and the UE replies with an acknowledgement (ACK) to the network side.

[0300] For this step, one implementation can be to add two user plane signaling messages. One user plane command includes the message type for indicating the model update transfer message (from LMF to UE), and the other user plane command includes the message type for indicating the model update response message (from UE to LMF).

[0301] Example 3: Create the user plane and control plane interactions between the new UE and the NWDAF to request the distribution / update of the model, and the model is distributed through the user plane.

[0302] The main difference between Example 3 and Example 1 is that a new user plane connection from the UE to the NWDAF is created for distributing or updating the model.

[0303] See Figure 6c , the information transmission method provided in this embodiment may include the following steps:

[0304] Steps 0 - 1: MT-LR triggers the LMF to perform AI positioning or other AI tasks and needs to distribute the model to the UE. Or, during the MO-LR process, the UE sends a first request message to the LMF to request the model to perform AI positioning or other AI tasks. After receiving it, the LMF agrees to use AI positioning or other AI tasks, determines the analysis ID / model ID, and decides to transmit it to the UE through the user plane.

[0305] Step 2: The LMF requests the NWDAF to distribute the model to the UE; the NWDAF decides to transfer the model to the UE through the user plane. Similarly, a new trigger reason for the NWDAF to establish a user plane connection is added here: to transfer the model, and this trigger reason can be sent to the UE in the downlink message of Figure 6c shown in Step 4.

[0306] In this step, the UE ID is mandatory, which enables the NWDAF to know with whom to establish a connection and send the model in the subsequent Steps 4 - 6.

[0307] Steps 4 - 6: The process of creating a user plane connection between the UE and the NWDAF. Specifically:

[0308] Step 4: The NWDAF provides the NWDAF address and port information to the UE for the UE to establish a connection in Step 6. Some optional signaling implementation methods are: NWDAF -> LMF -> AMF -> UE; or, NWDAF -> AMF -> UE. Before the user plane connection is established, this information is transmitted through the control plane. The UE replies whether to accept the establishment of the NWDAF user plane connection, including two cases: allowed and rejected.

[0309] Step 5: The UE optionally uses a slice and establishes a PDU session for the UE to the NWDAF according to the UE Route Selection Policy (URSP) or the default configuration.

[0310] Step 6: The UE uses the NWDAF address and / or the port information of the NWDAF received in Step 4 to establish a user plane connection with the NWDAF. An optional implementation is for the UE to perform a Transport Layer Security (TLS) handshake with the NWDAF.

[0311] It should also be noted that Figure 6c the SMF / UPF in Figure 6c is not applicable simultaneously. For example, during the control plane signaling transfer (e.g., Figure 6c Step 5), here it is the SMF. When subsequent user plane message transfer occurs (e.g., Figure 6a Steps 7 - 8), here it is the UPF. The relationship between the two is that the SMF is responsible for the selection and management of the UPF node. Therefore, in

[0312] the two are put together for the convenience of illustration.

[0313] Step 7: The NWDAF sends model - related information (i.e., the related information of the above - mentioned IA model) to the UE through user plane signaling.

[0314] For this step, one implementation can be to add two new message types. One message type is used to indicate the model download message, and the other message type is used to indicate the model download reply message. The above - mentioned download reply message includes two categories. One is successful reception, and the other is reception failure. Optionally, in the case of reception failure, the above - mentioned download reply message can carry the failure reason.

[0315] Step 8: The UE replies with an acknowledgement (ACK).

[0316] Step 9: The NWDAF replies that the LMF has downloaded the model to the UE, or replies with a failure, and optionally, also carries the failure reason.

[0317] It should be noted that the message type in step 10 above may be different from the message types in steps 7-8 above. For example, in this step 10, two new message types are added. One message type is used to indicate a model update message, and the other message type is used to indicate a model update reply message. The above model update reply message includes two categories. One is reception success, and the other is reception failure. Optionally, in the case of reception failure, the above model update reply message may carry the reason for failure.

[0318] Example 4: Establish a user plane between a newly created UE and NWDAF. The user plane interaction requires the distribution / update of a model, and the user plane distributes the model.

[0319] See Figure 6d , the information transmission method provided in this embodiment may include the following steps:

[0320] Steps 1-3, the process of establishing a user plane connection between the UE and NWDAF can be initiated by the UE or by NWDAF. In this example, a new trigger reason for establishing a user plane connection is added on the UE side and the NWDAF side: transmitting a model. This trigger reason can be sent to the other party in the uplink / downlink message in step 1. If it is initiated by the UE, the UE sends an uplink request, carrying the trigger reason information to NWDAF. NWDAF carries the NWDAF address and the port information of NWDAF in the subsequent reply to the UE, and the UE executes steps 2-3 to establish a user plane connection, referring to Example 3. If it is initiated by NWDAF, NWDAF sends a downlink request, carrying the trigger reason information to the UE and carrying the NWDAF address and the port information of NWDAF to the UE, and the UE executes steps 2-3 to establish a user plane connection, referring to Example 3.

[0321] Step 4, the UE sends a first request message to NWDAF through the user plane, requesting to obtain an AI model to perform AI positioning or other AI tasks.

[0322] Step 5, if only the analysis ID is carried in the first request message, NWDAF determines the model ID according to the analysis ID and decides to distribute model-related information (i.e., the related information of the above AI model) to the UE through the user plane; if the model ID is carried in the first request message, directly distribute the related information of the AI model indicated by the model ID.

[0323] If NWDAF cannot provide the related information of the AI model, a rejection message is carried in the reply message in step 6. Optionally, the above rejection message may carry the reason for rejection.

[0324] Step 6, NWDAF sends model-related information (i.e., the related information of the above AI model) to the UE through the user plane signaling.

[0325] Step 7, the NWDAF updates the model, and then the NWDAF sends the updated model to the user-facing UE.

[0326] For this step, one implementation is to add two new message types. One message type is used to indicate the model update message, and the other message type is used to indicate the model update reply message.

[0327] It should be noted that for the information transmission method provided in the embodiments of the present application, the execution entity may be an information transmission device, or a control module in the information transmission device for executing the information transmission method. In the embodiments of the present application, the information transmission method is executed by the information transmission device as an example to illustrate the information transmission device provided in the embodiments of the present application.

[0328] Please refer to Figure 7 , Figure 7 which is a structural diagram of an information transmission device provided in the embodiments of the present application. As Figure 7 shown, the information transmission device 700 includes:

[0329] A first receiving module 701, configured to receive a first message through a user plane connection with a first target network element;

[0330] Wherein, the first message includes information related to an artificial intelligence (AI) model, and the information related to the AI model includes at least one of the following:

[0331] Identification information of the AI model;

[0332] File information of the AI model;

[0333] Attribute information of the AI model;

[0334] Download address of the AI model.

[0335] Optionally, the first target network element includes a first network element or a second network element. Among them, the first network element is a network element for managing a target service, the AI model is a model related to the target service, and the second network element is a network element for managing the AI model.

[0336] Optionally, the device further includes:

[0337] A first sending module, configured to send a first request message to a second target network element before receiving the first message through the user plane connection with the first target network element;

[0338] Wherein, the first request message is used to request to obtain the AI model, and the second target network element includes the first network element or the second network element.

[0339] Optionally, the first request message includes at least one of the following:

[0340] The first indication information, which is used to indicate that the terminal needs to obtain an AI model;

[0341] The second indication information, which is used to indicate that the AI model needs to be transmitted through the user plane;

[0342] The identification information of the AI model;

[0343] The description information of the AI model;

[0344] The identification information of the terminal;

[0345] The first capability information, which is used to indicate that the terminal supports obtaining the AI model through the user plane;

[0346] The address information of the model storage network element;

[0347] The service type of using the model.

[0348] Optionally, the description information of the AI model includes at least one of the following:

[0349] The service type indication information, which is used to indicate the service type that the requested model needs to provide;

[0350] The information of the model usage object;

[0351] The type of the model input data, where the type of the model input data includes at least one of the type of the input data required for model inference and the type of the input data required for model training;

[0352] The type of the model inference result.

[0353] Optionally, the first sending module is specifically configured to:

[0354] Send a first request message to the second target network element through the user plane connection with the second target network element;

[0355] Or,

[0356] Send a first request message to the second target network element through the control plane signaling.

[0357] Optionally, the device further includes:

[0358] The second sending module, which is used to send a first response message to the first target network element through the user plane connection with the first target network element, where the first response message is used to indicate whether the terminal successfully receives the relevant information of the AI model.

[0359] Optionally, when the first response message is used to indicate that the terminal fails to receive the relevant information of the AI model, the first response message includes cause information, which is used to indicate the reason for the terminal's failure to receive the relevant information of the AI model.

[0360] Optionally, the device further includes:

[0361] A third sending module, configured to send a user plane connection establishment request message when the terminal needs to obtain the relevant information of the AI model, where the user plane connection establishment request message is used to request the establishment of a user plane connection between the terminal and the first target network element.

[0362] Optionally, the user plane connection establishment request message carries a trigger cause value for indicating that the trigger cause is model transfer.

[0363] Optionally, the device further includes:

[0364] A second receiving module, configured to receive a second message through the user plane connection with the first target network element after receiving the first message through the user plane connection with the first target network element, where the second message includes the update information of the AI model;

[0365] A fourth sending module, configured to send a second response message to the first target network element through the user plane connection with the first target network element, where the second response message is used to indicate whether the terminal successfully receives the update information of the AI model.

[0366] The information transmission device in the embodiments of the present application may 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 a chip. The electronic device may be a terminal or other devices other than the terminal. Exemplarily, the terminal may include, but is not limited to, the types of the terminal 11 listed above, and other devices may be a server, a Network Attached Storage (NAS), etc., which are not specifically limited in the embodiments of the present application.

[0367] The information transmission device provided by the embodiments of the present application can implement Figure 4 each process implemented by the method embodiments and achieve the same technical effects. To avoid repetition, details are not described here again.

[0368] Please refer to Figure 8 , Figure 8 which is a structural diagram of an information transmission device provided by the embodiments of the present application. As Figure 8 shown, the information transmission device 800 includes:

[0369] The fifth sending module 801 is configured to send a first message through a user plane connection with a terminal;

[0370] Wherein, the first message includes information related to an artificial intelligence (AI) model, and the information related to the AI model includes at least one of the following:

[0371] Identification information of the AI model;

[0372] File information of the AI model;

[0373] Attribute information of the AI model;

[0374] Download address of the AI model.

[0375] Optionally, the first target network element includes a first network element or a second network element, wherein the first network element is a network element that manages a target service, the AI model is a model related to the target service, and the second network element is a network element that manages the AI model.

[0376] Optionally, the apparatus further includes:

[0377] The third receiving module is configured to receive a first request message sent by the terminal before sending the first message through the user plane connection with the terminal;

[0378] Optionally, the first request message includes at least one of the following:

[0379] First indication information for indicating that the terminal needs to obtain an AI model;

[0380] Second indication information for indicating that the AI model needs to be transmitted through the user plane;

[0381] Identification information of the AI model;

[0382] Description information of the AI model;

[0383] Identification information of the terminal;

[0384] First capability information for indicating that the terminal supports obtaining an AI model through a user plane connection;

[0385] Address information of the model storage network element;

[0386] Service type for using the model.

[0387] Optionally, the description information of the AI model includes at least one of the following:

[0388] Service type indication information for indicating the service type that the requested model needs to provide;

[0389] Information about the object using the model;

[0390] The type of model input data, where the type of model input data includes at least one of the type of input data required for model inference and the type of input data required for model training;

[0391] The type of model inference result.

[0392] Optionally, the third receiving module is specifically configured to:

[0393] Receive a first request message sent by the terminal through a user plane connection with the terminal;

[0394] Or,

[0395] Receive a first request message sent by the terminal through control plane signaling.

[0396] Optionally, the device further includes:

[0397] A determination module, configured to determine the identification information of the AI model when it is determined that relevant information of the AI model is to be transmitted to the terminal through a user plane connection;

[0398] An acquisition module, configured to acquire relevant information of the AI model according to the identification information of the AI model.

[0399] Optionally, the device further includes:

[0400] A fourth receiving module, configured to receive a first response message sent by the terminal through a user plane connection with the terminal, where the first response message is used to indicate whether the terminal has successfully received relevant information of the AI model.

[0401] Optionally, when the first response message is used to indicate that the terminal fails to receive relevant information of the AI model, the first response message includes cause information, and the cause information is used to indicate the reason for the terminal's failure to receive relevant information of the AI model.

[0402] Optionally, the device further includes:

[0403] A sixth sending module, configured to send a user plane connection establishment command message when it is determined that relevant information of the AI model needs to be transmitted to the terminal, where the user plane connection establishment command message is used to indicate the establishment of a user plane connection between the first target network element and the terminal.

[0404] Optionally, the user plane connection establishment command message carries a trigger cause value used to indicate that the trigger cause is model transmission.

[0405] Optionally, the device further includes:

[0406] A seventh sending module, configured to send a second message through a user plane connection with the terminal, where the second message includes update information of the AI model;

[0407] A fifth receiving module, configured to receive a second response message through a user plane connection with the terminal, where the second response message is used to indicate whether the terminal successfully receives the update information of the AI model.

[0408] Optionally, the first target network element is a first network element; the apparatus further includes:

[0409] An eighth sending module, configured to send a second request message to a second network element, where the second request message includes identification information of the AI model, or the second request message includes identification information of the AI model and identification information of the terminal;

[0410] A sixth receiving module, configured to receive a third response message sent by the second network element, where the third response message includes relevant information of the AI model.

[0411] Optionally, the first target network element is a second network element;

[0412] The apparatus further includes:

[0413] A seventh receiving module, configured to receive a third request message sent by a first network element, where the third request message includes identification information of the AI model, or the third request message includes identification information of the AI model and identification information of the terminal;

[0414] A ninth sending module, configured to send a fourth response message to the first network element, where the fourth response message includes relevant information of the AI model.

[0415] The information transmission apparatus in the embodiments of the present application may 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 a chip. The electronic device may be a network-side device or other devices other than network-side devices. Exemplarily, the network-side device may include, but is not limited to, the types of network-side devices 12 listed above, and other devices may be a server, a Network Attached Storage (NAS), etc., which are not specifically limited in the embodiments of the present application.

[0416] The information transmission apparatus provided in the embodiments of the present application can implement Figure 5 each process implemented by the method embodiments and achieve the same technical effects. To avoid repetition, details are not described here again.

[0417] Optionally, asFigure 9 As shown in Figure 9 , an embodiment of the present application further provides a communication device 900, including a processor 901 and a memory 902. A program or instruction that can run on the processor 901 is stored on the memory 902. For example, when the communication device 900 is a terminal, when the program or instruction is executed by the processor 901, each step of the above information transmission method embodiment is implemented, and the same technical effect can be achieved. When the communication device 900 is a network-side device, when the program or instruction is executed by the processor 901, each step of the above information transmission method embodiment is implemented, and the same technical effect can be achieved. To avoid repetition, details are not described here again.

[0418] An embodiment of the present application further provides a terminal, including a processor and a communication interface. The communication interface is used to receive a first message through a user plane connection with a first target network element. The first message includes information related to an artificial intelligence (AI) model, and the information related to the AI model includes at least one of the following: identification information of the AI model; file information of the AI model; attribute information of the AI model; download address of the AI model. This terminal embodiment corresponds to the above terminal-side method embodiment. Each implementation process and implementation manner of the above method embodiment can be applied to this terminal embodiment, and the same technical effect can be achieved. Specifically, Figure 10 It is a schematic diagram of the hardware structure of a terminal according to an embodiment of the present application.

[0419] The terminal 1000 includes, but is not limited to, at least some components such as a radio frequency unit 1001, a network module 1002, an audio output unit 1003, an input unit 1004, a sensor 1005, a display unit 1006, a user input unit 1007, an interface unit 1008, a memory 1009, and a processor 1010.

[0420] Those skilled in the art can understand that the terminal 1000 may further include a power source (such as a battery) for supplying power to each component. The power source can be logically connected to the processor 1010 through a power management system, so as to implement functions such as management of charging, discharging, and power consumption management through the power management system. Figure 10 The terminal structure shown in Figure 10 does not limit the terminal. The terminal may include more or fewer components than shown in the figure, or combine certain components, or have different component arrangements, which are not described here again.

[0421] It should be understood that in the embodiments of the present application, the input unit 1004 may include a Graphics Processing Unit (GPU) 10041 and a microphone 10042. The graphics processor 10041 processes the image data of static pictures or videos obtained by an image capturing device (such as a camera) in a video capture mode or an image capture mode. The display unit 1006 may include a display panel 10061, and the display panel 10061 may be configured in the form of, for example, a liquid crystal display, an organic light emitting diode, etc. The user input unit 1007 includes at least one of a touch panel 10071 and other input devices 10072. The touch panel 10071 is also referred to as a touch screen. The touch panel 10071 may include two parts: a touch detection device and a touch controller. The other input devices 10072 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 a joystick, which will not be elaborated here.

[0422] In the embodiments of the present application, after receiving downlink data from a network-side device, the radio frequency unit 1001 may transmit it to the processor 1010 for processing; in addition, the radio frequency unit 1001 may send uplink data to the network-side device. Generally, the radio frequency unit 1001 includes, but is not limited to, an antenna, an amplifier, a transceiver, a coupler, a low-noise amplifier, a duplexer, etc.

[0423] The memory 1009 can be used to store software programs or instructions as well as various data. The memory 1009 may mainly include a first storage area for storing programs or instructions and a second storage area for storing data. Among them, the first storage area may store an operating system, application programs or instructions required for at least one function (such as a sound playback function, an image playback function, etc.). In addition, the memory 1009 may include volatile memory or non-volatile memory. 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 (DDR SDRAM), an enhanced synchronous dynamic random access memory (ESDRAM), a synchronous link dynamic random access memory (SLDRAM), and a direct rambus random access memory (DRRAM). The memory 1009 in the embodiments of the present application includes, but is not limited to, these and any other suitable types of memory.

[0424] The processor 1010 may include one or more processing units; optionally, the processor 1010 integrates an application processor and a modem processor. Among them, the application processor mainly processes operations related to the operating system, user interface, and application programs, etc., and the modem processor mainly processes wireless communication signals, such as a baseband processor. It can be understood that the above modem processor may not be integrated into the processor 1010 either.

[0425] Among them, the radio frequency unit 1001 (write if any) is used to receive a first message through a user plane connection with a first target network element; wherein, the first message includes information related to an artificial intelligence (AI) model, and the information related to the AI model includes at least one of the following: identification information of the AI model; file information of the AI model; attribute information of the AI model; download address of the AI model.

[0426] It can be understood that the implementation processes of the various implementation manners mentioned in this embodiment may refer to the relevant descriptions of the foregoing method embodiments, and achieve the same or corresponding technical effects. To avoid repetition, they will not be elaborated here.

[0427] An embodiment of the present application further provides a network-side device, including a processor and a communication interface. The communication interface is used to send a first message through a user plane connection with a terminal. Among them, the first message includes information related to an artificial intelligence (AI) model. The information related to the AI model includes at least one of the following: identification information of the AI model; file information of the AI model; attribute information of the AI model; download address of the AI model. This embodiment of the network-side device corresponds to the above-mentioned method embodiment of the network-side device. Each implementation process and implementation manner of the above method embodiment can be applied to this embodiment of the network-side device, and the same technical effect can be achieved.

[0428] Specifically, an embodiment of the present application further provides a network-side device. As Figure 11 shown, the network-side device 1100 includes: a processor 1101, a network interface 1102, and a memory 1103. Among them, the network interface 1102 is, for example, a common public radio interface (CPRI).

[0429] Specifically, the network-side device 1100 in the embodiment of the present application further includes: instructions or programs stored on the memory 1103 and executable on the processor 1101. The processor 1101 calls the instructions or programs in the memory 1103 to execute Figure 8 the methods executed by the modules shown, and achieve the same technical effect. To avoid repetition, they will not be elaborated here.

[0430] An embodiment of the present application further provides a readable storage medium, on which a program or instructions are stored. When the program or instructions are executed by a processor, the various processes of the above-mentioned information transmission method embodiment are implemented, and the same technical effect can be achieved. To avoid repetition, they will not be elaborated here.

[0431] Among them, the processor is the processor in the terminal described in the above embodiment. The readable storage medium includes a computer-readable storage medium, such as a computer read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disc. In some examples, the readable storage medium may be a non-transitory readable storage medium.

[0432] Another embodiment of the present application further provides a chip, which includes a processor and a communication interface. The communication interface is coupled to the processor. The processor is configured to run programs or instructions to implement each process of the above-described embodiment of the information transmission method and can achieve the same technical effects. To avoid repetition, details are not described herein again.

[0433] It should be understood that the chip mentioned in the embodiments of the present application may also be referred to as a system-on-chip, system chip, chip system, or system-on-chip.

[0434] Another 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 each process of the above-described embodiment of the information transmission method and can achieve the same technical effects. To avoid repetition, details are not described herein again.

[0435] An embodiment of the present application further provides an information transmission system, including: a terminal and a network-side device. The terminal is configured to execute as Figure 4 and each process of the above-described method embodiments, and the network-side device is configured to execute as Figure 5 and each process of the above-described method embodiments, and can achieve the same technical effects. To avoid repetition, details are not described herein again.

[0436] It should be noted that in this document, the terms "include", "comprise", or any other variation thereof are intended to cover a non-exclusive inclusion, such that a process, method, article, or device including a series of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or device. Without further limitation, an element defined by the statement "including a..." does not exclude the existence of additional identical elements in the process, method, article, or device including the element. In addition, it should be pointed out that the methods and devices in the embodiments of the present application are not limited to performing functions in the order shown or discussed. They may also include performing functions in a substantially simultaneous manner or in a reverse order according to the functions involved. For example, the described methods may be performed in an order different from that described, and various steps may be added, omitted, or combined. Additionally, features described with reference to certain examples may be combined in other examples.

[0437] Through the description of the above embodiments, those skilled in the art can clearly understand that the above-described embodiment methods can be implemented by means of a computer software product plus a necessary general hardware platform, and of course, they can also be implemented by hardware. The computer software product is stored in a storage medium (such as ROM, RAM, magnetic disk, optical disk, etc.) and includes several instructions for causing a terminal or a network-side device to execute the methods described in various embodiments of the present application.

[0438] The embodiments of the present application have been described above in conjunction with the accompanying drawings. However, the present application is not limited to the above specific implementation manners. The above specific implementation manners are merely illustrative rather than restrictive. Under the inspiration of the present application, those of ordinary skill in the art can also make many forms of implementation manners without departing from the purpose of the present application and the scope protected by the claims. These implementation manners all fall within the protection scope of the present application.

Claims

1. An information transmission method, characterized in that, Including: The terminal receives a first message through a user plane connection with a first target network element; Wherein, the first message includes information related to an artificial intelligence (AI) model, and the information related to the AI model includes at least one of the following: Identification information of the AI model; File information of the AI model; Attribute information of the AI model; Download address of the AI model.

2. The method according to claim 1, wherein The first target network element includes a first network element or a second network element. Among them, the first network element is a network element that manages a target service, the AI model is a model related to the target service, and the second network element is a network element that manages the AI model.

3. The method according to any one of claims 1 to 2, characterized in that Before the terminal receives the first message through the user plane connection with the first target network element, the method further includes: The terminal sends a first request message to a second target network element; Wherein, the first request message is used to request to obtain an AI model.

4. The method according to claim 3, characterized in that, The first request message includes at least one of the following: First indication information, used to indicate that the terminal needs to obtain an AI model; Second indication information, used to indicate that the AI model is transmitted through the user plane; Identification information of the AI model; Description information of the AI model; Identification information of the terminal; First capability information, used to indicate that the terminal supports obtaining an AI model through the user plane; Address information of the model storage network element; Service type for using the model.

5. The method according to claim 4, wherein The description information of the AI model includes at least one of the following: Service type indication information, used to indicate the service type that the requested model needs to provide; Information about the object using the model; Type of model input data, and the type of model input data includes at least one of the type of input data required for model inference and the type of input data required for model training; Type of model inference result.

6. The method according to any one of claims 3 to 5, characterized in that The terminal sending the first request message to the second target network element includes: The terminal sends a first request message to the second target network element through a user plane connection with the second target network element; Or, The terminal sends a first request message to the second target network element through control plane signaling.

7. The method according to any one of claims 1 to 6, characterized in that The method further includes: The terminal sends a first response message to the first target network element through a user plane connection with the first target network element, where the first response message is used to indicate whether the terminal successfully receives the information related to the AI model.

8. The method according to claim 7, wherein In the case where the first response message is used to indicate that the terminal fails to receive the information related to the AI model, the first response message includes cause information, and the cause information is used to indicate the reason for the terminal's failure to receive the information related to the AI model.

9. The method according to any one of claims 1 to 8, characterized in that Before the terminal receives the first message through the user plane connection with the first target network element, the method further includes: In the case where the terminal needs to obtain the information related to the AI model, the terminal sends a user plane connection establishment request message, where the user plane connection establishment request message is used to request to establish a user plane connection between the terminal and the first target network element.

10. The method according to claim 9, characterized in that, The user plane connection establishment request message carries a trigger reason value used to indicate that the trigger reason is model transfer.

11. The method according to any one of claims 1 to 10, characterized in that, After the terminal receives a first message through a user plane connection with a first target network element, the method further includes: The terminal receives a second message through a user plane connection with the first target network element, where the second message includes update information of the AI model; The terminal sends a second response message to the first target network element through a user plane connection with the first target network element, where the second response message is used to indicate whether the terminal successfully receives the update information of the AI model.

12. An information transmission method, characterized in that, Includes: The first target network element sends a first message through a user plane connection with the terminal; Wherein, the first message includes information related to an artificial intelligence (AI) model, and the information related to the AI model includes at least one of the following: Identification information of the AI model; File information of the AI model; Attribute information of the AI model; Download address of the AI model.

13. The method according to claim 12, wherein The first target network element includes a first network element or a second network element, where the first network element is a network element that manages a target service, the AI model is a model related to the target service, and the second network element is a network element that manages the AI model.

14. The method according to any one of claims 12 to 13, characterized in that, Before the first target network element sends a first message through a user plane connection with the terminal, the method further includes: The first target network element receives a first request message sent by the terminal; Wherein, the first request message is used to request to obtain an AI model.

15. The method according to claim 14, wherein The first request message includes at least one of the following: First indication information, used to indicate that the terminal needs to obtain an AI model; Second indication information, used to indicate that the AI model needs to be transmitted through the user plane; Identification information of the AI model; Description information of the AI model; Identification information of the terminal; First capability information, used to indicate that the terminal supports obtaining an AI model through a user plane connection; Address information of the model storage network element; Service type for using the model.

16. The method according to claim 15, wherein The description information of the AI model includes at least one of the following: Service type indication information, used to indicate the service type that the requested model needs to provide; Information about the object using the model; Type of model input data, and the type of model input data includes at least one of the type of input data required for model inference and the type of input data required for model training; Type of model inference result.

17. The method according to any one of claims 14 to 16, characterized in that, The first target network element receiving the first request message sent by the terminal includes: The first target network element receives the first request message sent by the terminal through a user plane connection with the terminal; Or, The first target network element receives the first request message sent by the terminal through control plane signaling.

18. The method according to any one of claims 12 to 17, characterized in that, Before the first target network element sends a first message through a user plane connection with the terminal, the method further includes: When the first target network element determines to transmit information related to the AI model to the terminal through a user plane connection, it determines the identification information of the AI model; The first target network element obtains the information related to the AI model according to the identification information of the AI model.

19. The method according to any one of claims 12 to 17, characterized in that, The method further includes: The first target network element receives a first response message sent by the terminal through a user plane connection with the terminal, where the first response message is used to indicate whether the terminal successfully receives relevant information of the AI model.

20. The method according to claim 19, wherein In a case where the first response message is used to indicate that the terminal fails to receive relevant information of the AI model, the first response message includes cause information, and the cause information is used to indicate the reason why the terminal fails to receive relevant information of the AI model.

21. The method according to any one of claims 12 to 20, characterized in that, Before the first target network element sends a first message through a user plane connection with the terminal, the method further includes: In a case where it is determined that relevant information of the AI model needs to be transmitted to the terminal, the first target network element sends a user plane connection establishment command message, where the user plane connection establishment command message is used to indicate establishing a user plane connection between the first target network element and the terminal.

22. The method according to claim 21, wherein The user plane connection establishment command message carries a trigger cause value used to indicate that the trigger cause is model transmission.

23. The method according to any one of claims 12 to 22, characterized in that, The method further includes: The first target network element sends a second message through a user plane connection with the terminal, where the second message includes update information of the AI model; The first target network element receives a second response message through a user plane connection with the terminal, where the second response message is used to indicate whether the terminal successfully receives the update information of the AI model.

24. The method according to any one of claims 12 to 23, characterized in that, The first target network element is the first network element; Before the first target network element sends a first message through a user plane connection with the terminal, the method further includes: The first target network element sends a second request message to a second network element, where the second request message includes identification information of the AI model, or the second request message includes identification information of the AI model and identification information of the terminal; The first target network element receives a third response message sent by the second network element, where the third response message includes relevant information of the AI model.

25. The method according to any one of claims 12 to 23, characterized in that, The first target network element is the second network element; Before the first target network element sends a first message through a user plane connection with the terminal, the method further includes: The first target network element receives a third request message sent by the first network element, where the third request message includes identification information of the AI model, or the third request message includes identification information of the AI model and identification information of the terminal; The first target network element sends a fourth response message to the first network element, where the fourth response message includes relevant information of the AI model.

26. An information transmission device, characterized in that, Applied to a terminal, it includes: A first receiving module, configured to receive a first message through a user plane connection with a first target network element; Wherein, the first message includes relevant information of an artificial intelligence (AI) model, and the relevant information of the AI model includes at least one of the following: Identification information of the AI model; File information of the AI model; Attribute information of the AI model; Download address of the AI model.

27. The device according to claim 26, wherein, The first target network element includes a first network element or a second network element, where the first network element is a network element for managing a target service, the AI model is a model related to the target service, and the second network element is a network element for managing the AI model.

28. The device according to any one of claims 26 to 27, characterized in that The apparatus further includes: A first sending module, configured to send a first request message to a second target network element before receiving a first message through a user plane connection with the first target network element; Wherein, the first request message is used to request to obtain an AI model, and the second target network element includes a first network element or a second network element.

29. The device according to claim 28, wherein The first request message includes at least one of the following: First indication information, used to indicate that the terminal needs to obtain an AI model; Second indication information, used to indicate that the AI model needs to be transmitted through the user plane; Identification information of the AI model; Description information of the AI model; Identification information of the terminal; First capability information, used to indicate that the terminal supports obtaining the AI model through the user plane; Address information of the model storage network element; Service type for using the model.

30. The device according to any one of claims 26 to 29, characterized in that, The apparatus further includes: A second sending module, configured to send a first response message to the first target network element through a user plane connection with the first target network element, where the first response message is used to indicate whether the terminal successfully receives information related to the AI model.

31. The device according to claim 30, characterized in that, In the case where the first response message is used to indicate that the terminal fails to receive information related to the AI model, the first response message includes cause information, and the cause information is used to indicate the reason for the terminal's failure to receive information related to the AI model.

32. The device according to any one of claims 26 to 31, characterized in that, The apparatus further includes: A third triggering module, configured to send a user plane connection establishment request message when the terminal needs to obtain information related to the AI model, where the user plane connection establishment request message is used to request to establish a user plane connection between the terminal and the first target network element.

33. The device according to any one of claims 26 to 32, characterized in that, The apparatus further includes: A second receiving module, configured to receive a second message through a user plane connection with the first target network element after receiving the first message through the user plane connection with the first target network element, where the second message includes update information of the AI model; A fourth sending module, configured to send a second response message to the first target network element through a user plane connection with the first target network element, where the second response message is used to indicate whether the terminal successfully receives the update information of the AI model.

34. An information transmission device, characterized in that, Applied to a first target network element, including: A fifth sending module, configured to send a first message through a user plane connection with a terminal; Wherein, the first message includes information related to an artificial intelligence (AI) model, and the information related to the AI model includes at least one of the following: Identification information of the AI model; File information of the AI model; Attribute information of the AI model; Download address of the AI model.

35. A terminal, characterized in that, Comprising a processor and a memory, the memory stores a program or instruction that can run on the processor, and when the program or instruction is executed by the processor, the steps of the information transmission method according to any one of claims 1 to 11 are implemented.

36. A network-side device, characterized in that, It includes a processor and a memory, and the memory stores programs or instructions that can run on the processor. When the programs or instructions are executed by the processor, the steps of the information transmission method according to any one of claims 12 to 25 are implemented.

37. A readable storage medium, characterized in that, Programs or instructions are stored on the readable storage medium. When the programs or instructions are executed by a processor, the steps of the information transmission method according to any one of claims 1 to 11 are implemented, or the steps of the information transmission method according to any one of claims 12 to 25 are implemented.

Images