Information transmission method and apparatus, model determination method and apparatus, and related device
By uniformly registering and security authentication of AI/ML models of different devices in the communication network, cross-vendor model compatibility and security issues are solved, and effective scheduling and security verification of the model are achieved.
Patent Information
- Application Number
- PCT/CN2024/090465
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- Priority Date
- 2023-05-06
- Filing Date
- 2024-04-29
- Publication Date
- 2024-11-14
AI Technical Summary
In the communication network, due to different optimization methods of different mobile phone manufacturers, the AI/ML models of different mobile phone manufacturers are incompatible with cross-vendor models, which poses security risks, making it difficult to achieve effective model scheduling.
Through the second device, models from different devices are uniformly registered or published, security authentication and identification management are carried out to ensure the compatibility and security of the model.
The model compatibility and security between different devices are achieved, and the security performance and model scheduling efficiency of the target device are improved.
Smart Images

Figure CN2024090465_14112024_PF_FP_ABST
Abstract
Description
Information transmission method, model determination method, device and related equipment
[0001] CROSS-REFERENCE TO RELATED APPLICATIONS
[0002] This application claims priority to Chinese Patent Application No. 202310510909.0 filed in China on May 6, 2023, the entire contents of which are incorporated herein by reference. Technical Field
[0003] The present application belongs to the field of communication technology, and specifically relates to an information transmission method, a model determination method, an apparatus and related equipment. Background Art
[0004] In communication networks, artificial intelligence (AI) methods have been introduced to improve network communication performance.
[0005] Network-side devices or terminal-side devices can train AI or machine learning (ML) models based on training data to obtain a model suitable for a specific AI task. The network-side devices or terminal devices can also send the trained AI / ML model to other terminal devices, allowing them to infer the input data of a specific AI task based on the AI / ML model and obtain the inference result data corresponding to the specific AI task.
[0006] However, when AI / ML models trained by network-side devices or user equipment (UE) are sent to other UEs for use, there may be incompatibility or security risks. For example, different mobile phone manufacturers (UE vendors) have their own optimization methods for communication models, making the AI / ML model trained on one manufacturer's mobile phone unsuitable for another manufacturer's mobile phone.
[0007] Summary of the Invention
[0008] The embodiments of the present application provide an information transmission method, a model determination method, an apparatus and related equipment, which can uniformly register or publish models trained by different devices using a second device, so that other devices can obtain valid or secure models based on the registration information or published information.
[0009] In a first aspect, a method for transmitting information is provided, the method comprising:
[0010] The second device receives a first message from the first device, wherein the first message is used to register or publish the first model;
[0011] The second device sends a second message to the first device, where the second message is a response message for registering or publishing the first model, and the second message carries first information, where the first information includes at least one of the following:
[0012] First indication information, used to indicate whether the first model passes the security authentication of the second device;
[0013] The security authentication certificate of the first model, or the token information of the first model passing the security authentication of the second device;
[0014] model identification information of the first model allocated by the second device;
[0015] Version information of the first model allocated by the second device.
[0016] In a second aspect, an information transmission method is provided, the method comprising:
[0017] The first device sends a first message to the second device, wherein the first message is used to register or publish the first model;
[0018] The first device receives a second message from the second device, wherein the second message is a response message for registering or publishing the first model, and the second message carries first information, where the first information includes at least one of the following:
[0019] First indication information, used to indicate whether the first model passes the security authentication of the second device;
[0020] The security authentication certificate of the first model, or the token information of the first model passing the security authentication of the second device;
[0021] model identification information of the first model allocated by the second device;
[0022] Version information of the first model allocated by the second device.
[0023] In a third aspect, a method for transmitting information is provided, the method comprising:
[0024] The third device receives second capability information from the target device, where the second capability information is related to a model supported by the target device;
[0025] The third device sends a fifth message to the target device according to the second capability information, where the fifth message is used to trigger or activate a second model in the target device, wherein the models supported by the target device include the second model.
[0026] In a fourth aspect, a method for transmitting information is provided, the method comprising:
[0027] The target device receives the third information;
[0028] The target device acquires a target model according to the third information, where the target model includes at least one first model, which is from the first device and registered or published by the second device.
[0029] In a fifth aspect, a model determination method is provided, the method comprising:
[0030] The third device receives first capability information from the target device, where the first capability information is used to indicate the AI capability of the target device;
[0031] The third device determines a target model according to the first capability information, wherein the target model includes a model applicable to the target device.
[0032] In a sixth aspect, a model determination method is provided, the method comprising:
[0033] The target device sends first capability information to the third device, where the first capability information is used to indicate the AI capability of the target device;
[0034] The target device acquires a target model, wherein the target model includes a model applicable to the target device.
[0035] In a seventh aspect, a model determination method is provided, the method comprising:
[0036] The second device obtains first capability information, where the first capability information is used to indicate the AI capability of the target device;
[0037] The second device determines a target model from the first model according to the first capability information, wherein the target model includes a model applicable to the target device.
[0038] In an eighth aspect, an information transmission device is provided, comprising:
[0039] A first receiving module, configured to receive a first message from a first device, wherein the first message is used to register or publish a first model;
[0040] A first sending module is configured to send a second message to the first device, where the second message is a response message for registering or publishing the first model, and the second message carries first information, where the first information includes at least one of the following:
[0041] First indication information, used to indicate whether the first model passes the security authentication of the second device;
[0042] The security authentication certificate of the first model, or the token information of the first model passing the security authentication of the second device;
[0043] model identification information of the first model allocated by the second device;
[0044] Version information of the first model allocated by the second device.
[0045] In a ninth aspect, an information transmission device is provided, comprising:
[0046] A second sending module, configured to send a first message to a second device, wherein the first message is used to register or publish a first model;
[0047] The second receiving module is configured to receive a second message from the second device, wherein the second message is a response message for registering or publishing the first model, and the second message carries first information, where the first information includes at least one of the following:
[0048] First indication information, used to indicate whether the first model passes the security authentication of the second device;
[0049] The security authentication certificate of the first model, or the token information of the first model passing the security authentication of the second device;
[0050] model identification information of the first model allocated by the second device;
[0051] Version information of the first model allocated by the second device.
[0052] In a tenth aspect, an information transmission device is provided, comprising:
[0053] a third receiving module, configured to receive second capability information from a target device, where the second capability information is related to a model supported by the target device;
[0054] The third sending module is used to send a fifth message to the target device according to the second capability information, where the fifth message is used to trigger or activate the second model in the target device, wherein the models supported by the target device include the second model.
[0055] In an eleventh aspect, an information transmission device is provided, comprising:
[0056] a fourth receiving module, configured to receive third information;
[0057] The first acquisition module is configured to acquire a target model according to the third information, where the target model includes at least one first model, which is from a first device and registered or published through a second device.
[0058] In a twelfth aspect, a model determination device is provided, comprising:
[0059] a fifth receiving module, configured to receive first capability information from a target device, where the first capability information is used to indicate an AI capability of the target device;
[0060] A first determining module is configured to determine a target model according to the first capability information, wherein the target model includes a model applicable to the target device.
[0061] In a thirteenth aspect, a model determination device is provided, comprising:
[0062] a fifth sending module, configured to send first capability information to a third device, where the first capability information is used to indicate the AI capability of the target device;
[0063] The second acquisition module is configured to acquire a target model, wherein the target model includes a model applicable to the target device.
[0064] In a fourteenth aspect, a model determination device is provided, comprising:
[0065] A third acquisition module is configured to acquire first capability information, where the first capability information is used to indicate the AI capability of the target device;
[0066] The second determining module is configured to determine a target model from the first model according to the first capability information, wherein the target model includes a model applicable to the target device.
[0067] In the fifteenth aspect, a communication device is provided, which includes a processor and a memory, wherein the memory stores programs or instructions that can be run on the processor, and when the programs or instructions are executed by the processor, the steps of the method described in the first aspect or the second aspect or the third aspect or the fourth aspect or the fifth aspect or the sixth aspect or the seventh aspect are implemented.
[0068] In a sixteenth aspect, a communication device is provided, including a processor and a communication interface:
[0069] Wherein, when the communication device serves as the second device, the communication interface is used to receive a first message from the first device, wherein the first message is used to register or publish a first model; and the communication interface is further used to send a second message to the first device, wherein the second message is a response message for registering or publishing the first model, and the second message carries first information, wherein the first information includes at least one of the following:
[0070] First indication information, used to indicate whether the first model passes the security authentication of the second device;
[0071] The security authentication certificate of the first model, or the token information of the first model passing the security authentication of the second device;
[0072] model identification information of the first model allocated by the second device;
[0073] version information of the first model allocated by the second device;
[0074] or,
[0075] When the communication device serves as the second device, the communication interface is used to obtain first capability information, where the first capability information is used to indicate the AI capability of the target device; and the processor is used to determine a target model from the first model based on the first capability information, where the target model includes a model applicable to the target device.
[0076] or,
[0077] When the communication device serves as the first device, the communication interface is used to send a first message to the second device, where the first message is used to register or publish a first model; the communication interface is further used to receive a second message from the second device, where the second message is a response message for registering or publishing the first model, and the second message carries first information, where the first information includes at least one of the following:
[0078] First indication information, used to indicate whether the first model passes the security authentication of the second device;
[0079] The security authentication certificate of the first model, or the token information of the first model passing the security authentication of the second device;
[0080] model identification information of the first model allocated by the second device;
[0081] version information of the first model allocated by the second device;
[0082] or,
[0083] In a case where the communication device serves as the third device, the communication interface is configured to receive second capability information from a target device, where the second capability information is related to a model supported by the target device; the communication interface is further configured to send a fifth message to the target device based on the second capability information, where the fifth message is configured to trigger or activate a second model in the target device, where the models supported by the target device include the second model;
[0084] or,
[0085] In a case where the communication device serves as the third device, the communication interface is configured to receive first capability information from a target device, where the first capability information is configured to indicate an AI capability of the target device; and the processor is configured to determine a target model based on the first capability information, where the target model includes a model applicable to the target device.
[0086] or,
[0087] In the case where the communication device serves as the target device, the communication interface is used for the target device to receive third information; the processor is used to obtain a target model according to the third information, the target model including at least one first model, the first model being from the first device and registered or published by the second device;
[0088] or,
[0089] When the communication device serves as the target device, the communication interface is used to send first capability information to a third device, where the first capability information is used to indicate the AI capability of the target device; the communication interface is also used to obtain a target model, where the target model includes a model applicable to the target device.
[0090] In the seventeenth aspect, a readable storage medium is provided, on which a program or instruction is stored. When the program or instruction is executed by a processor, the steps of the method described in the first aspect are implemented, or the steps of the method described in the second aspect are implemented, or the steps of the method described in the third aspect are implemented, or the steps of the method described in the fourth aspect are implemented, or the steps of the method described in the fifth aspect are implemented, or the steps of the method described in the sixth aspect are implemented, or the steps of the method described in the seventh aspect are implemented.
[0091] In aspect 18, a wireless communication system is provided, including: a first device, a second device, a third device and a target device, wherein the first device can be used to execute the steps of the method described in aspect 2, the second device can be used to execute the steps of the method described in aspect 1 or aspect 7, the third device can be used to execute the steps of the method described in aspect 3 or aspect 5, and the target device can be used to execute the steps of the method described in aspect 4 or aspect 6.
[0092] In the nineteenth aspect, a chip is provided, which includes a processor and a communication interface, the communication interface and the processor are coupled, and the processor is used to run programs or instructions to implement the method described in the first aspect or the second aspect or the third aspect or the fourth aspect or the fifth aspect or the sixth aspect or the seventh aspect.
[0093] In the twentieth aspect, a computer program / program product is provided, which is stored in a storage medium and is executed by at least one processor to implement the steps of the method described in the first aspect, the second aspect, the third aspect, the fourth aspect, the fifth aspect, the sixth aspect, or the seventh aspect.
[0094] In an embodiment of the present application, the model of the first device is registered by the second device to achieve unified management of models trained or provided by different devices, or the model of the first device is published by the second device, and the model of the first device can be verified during the publishing process, so that other devices can obtain valid or secure models based on the registration information or published information. BRIEF DESCRIPTION OF THE DRAWINGS
[0095] FIG1 is a schematic structural diagram of a wireless communication system to which an embodiment of the present application can be applied;
[0096] FIG2 is a flow chart of a first information transmission method provided in an embodiment of the present application;
[0097] FIG3 is a flow chart of a second information transmission method provided in an embodiment of the present application;
[0098] FIG4 is a flowchart of a third information transmission method provided in an embodiment of the present application;
[0099] FIG5 is a flowchart of a fourth information transmission method provided in an embodiment of the present application;
[0100] FIG6 is a flow chart of a first model determination method provided in an embodiment of the present application;
[0101] FIG7 is a flow chart of a second model determination method provided in an embodiment of the present application;
[0102] FIG8 is a flow chart of a third model determination method provided in an embodiment of the present application;
[0103] FIG9a is a schematic diagram of one of the interactions between the communication devices in an embodiment of the present application;
[0104] FIG9b is a second schematic diagram of interaction between communication devices in an embodiment of the present application;
[0105] FIG9c is a third schematic diagram of interaction between communication devices in an embodiment of the present application;
[0106] FIG10 is a schematic structural diagram of a first information transmission device provided in an embodiment of the present application;
[0107] FIG11 is a schematic structural diagram of a second information transmission device provided in an embodiment of the present application;
[0108] FIG12 is a schematic structural diagram of a third information transmission device provided in an embodiment of the present application;
[0109] FIG13 is a schematic structural diagram of a fourth information transmission device provided in an embodiment of the present application;
[0110] FIG14 is a schematic structural diagram of a first model determination device provided in an embodiment of the present application;
[0111] FIG15 is a schematic structural diagram of a second model determination device provided in an embodiment of the present application;
[0112] FIG16 is a schematic structural diagram of a third model determination device provided in an embodiment of the present application;
[0113] FIG17 is a schematic structural diagram of a communication device provided in an embodiment of the present application;
[0114] FIG18 is a schematic structural diagram of a terminal provided in an embodiment of the present application;
[0115] FIG19 is a schematic structural diagram of a network-side device provided in an embodiment of the present application;
[0116] Figure 20 is a structural diagram of another network-side device provided in an embodiment of the present application. DETAILED DESCRIPTION
[0117] The following will be combined with the accompanying drawings in the embodiments of this application to clearly describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field are within the scope of protection of this application.
[0118] The terms "first", "second", etc. in this application are used to distinguish similar objects, and are not used to describe a specific order or sequence. It should be understood that the terms used in this way are interchangeable where appropriate, so that the embodiments of the present application can be implemented in an order other than those illustrated or described herein, and the objects distinguished by "first" and "second" are generally of the same type, and do not limit the number of objects, for example, the first object can be one or more. In addition, "or" in this application represents at least one of the connected objects. For example, "A or B" covers three options, namely, Option 1: including A but not including B; Option 2: including B but not including A; Option 3: including both A and B. The character " / " generally indicates that the objects associated before and after are in an "or" relationship.
[0119] The term "indication" in this application can be either a direct indication (or explicit indication) or an indirect indication (or implicit indication). A direct indication can be understood as the sender explicitly informing the receiver of specific information, the operation to be performed, or the requested result, etc. in the instruction sent; an indirect indication can be understood as the receiver determining the corresponding information based on the instruction sent by the sender, or making a judgment and determining the operation to be performed or the requested result, etc. based on the judgment result.
[0120] It is worth noting that the technology described in the embodiments of the present application is not limited to the Long Term Evolution (LTE) / LTE-Advanced (LTE-A) system, but can also be used in other wireless communication systems, such as Code Division Multiple Access (CDMA), Time Division Multiple Access (TDMA), Frequency Division Multiple Access (FDMA), Orthogonal Frequency Division Multiple Access (OFDMA), Single-carrier Frequency-Division Multiple Access (SC-FDMA) or other systems. The terms "system" and "network" in the embodiments of the present application are often used interchangeably, and the technology described can be used for the systems and radio technologies mentioned above, as well as for other systems and radio technologies. The following description describes a New Radio (NR) system for illustrative purposes, and NR terminology is used in most of the following description, but these technologies can also be applied to systems other than NR systems, such as 6th generation (6G) systems. th Generation, 6G) communication system.
[0121] FIG1 is a block diagram of a wireless communication system applicable to an embodiment of the present application. The wireless communication system includes a terminal 11 and a network-side device 12. The terminal 11 may be a mobile phone, a tablet computer (Tablet Personal Computer), a laptop computer (Laptop Computer), a notebook computer, a personal digital assistant (PDA), a handheld computer, a netbook, an ultra-mobile personal computer (UMPC), a mobile internet device (MID), an augmented reality (AR), a virtual reality (VR) device, a robot, a wearable device (Wearable Device), an aircraft (Flight Vehicle), a vehicle-mounted device (VUE), a ship-mounted device, a pedestrian user equipment (PUE), a smart home (home appliances with wireless communication capabilities, such as refrigerators, televisions, washing machines, or furniture), a game console, a personal computer (PC), an ATM, or a self-service machine, or other terminal-side devices. Wearable devices include: smart watches, smart bracelets, smart headphones, smart glasses, smart jewelry (smart bracelets, smart bracelets, smart rings, smart necklaces, smart anklets, smart anklets, etc.), smart wristbands, smart clothing, etc. Among them, the vehicle-mounted device can also be called a vehicle-mounted terminal, a vehicle-mounted controller, a vehicle-mounted module, a vehicle-mounted component, a vehicle-mounted chip or a vehicle-mounted unit, etc. It should be noted that the specific type of the terminal 11 is not limited in the embodiment of the present application. The network side device 12 may include an access network device or a core network device, wherein the access network device may also be called a radio access network (Radio Access Network, RAN) device, a radio access network function or a radio access network unit. The access network device may include a base station, a wireless local area network (WLAN) access point (AS) or a wireless fidelity (WiFi) node, etc.Among them, the base station can be referred to as Node B (NB), Evolved Node B (eNB), the next generation Node B (gNB), New Radio Node B (NR Node B), access point, Relay Base Station (RBS), Serving Base Station (SBS), Base Transceiver Station (BTS), radio base station, radio transceiver, Basic Service Set (BSS), Extended Service Set (ESS), Home Node B (HNB), Home Evolved Node B (home evolved Node B), Transmission Reception Point (TRP) or other appropriate terms in the field. As long as the same technical effect is achieved, the base station is not limited to specific technical vocabulary. It should be noted that in the embodiment of the present application, only the base station in the NR system is used as an example for introduction, and the specific type of the base station is not limited.
[0122] The core network device may include but is not limited to at least one of the following: core network node, core network function, location management function (LMF), 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 unit (PCRF), edge application server discovery function (EASDF), unified data management (UDM), unified data storage (UDR), home user server (HSS), centralized network configuration (CNC), network storage function (NRF), network exposure function (NEF), local NEF (Local NEF, or L-NEF), Binding Support Function (BSF), Application Function (AF), Network Data Analytics Function (NWDAF), etc. It should be noted that in the embodiment of the present application, only the core network device in the NR system is taken as an example for introduction, and the specific type of the core network device is not limited. It should be noted that in the embodiment of the present application, only the core network device in the NR system is taken as an example for introduction, and the specific type of the core network device is not limited.
[0123] To facilitate understanding of the information transmission method and model determination method provided in the embodiments of the present application, the following terms in the embodiments of the present application are first explained:
[0124] 1) Model: This may include at least one of an AI model and a machine learning (ML) model.
[0125] 2) First device: It can be a device with a model training function or a device that can provide a model. For example, the first device may include at least one of a third-party business server, an in-network business server, an in-network core network element, a network management system device, a base station device, and a terminal device. The specific type of the first device is not limited here, and for ease of explanation, the embodiment of this application is usually illustrated as a third-party business server, such as a server that provides services to users through the Internet without the operator (Over The Top server, OTT server).
[0126] 3) Second device: can be a device having at least one of the following functions:
[0127] Model information registration function;
[0128] Model information update function;
[0129] Model information deletion function;
[0130] Model identification assignment function;
[0131] Model storage function;
[0132] Model distribution function.
[0133] Specifically, the second device can be a model store / model publishing platform deployed by an operator, or the second device can be a model store / model publishing platform deployed by a third party, for example: it can be a NEF network element, an Analytics Data Repository Function (ADRF) network element, an NRF network element, etc., or a newly defined network element. The specific type of the second device is not limited here, and for the sake of convenience of explanation, the embodiments of this application are generally illustrated by taking the example of the second device being a model store deployed by an operator.
[0134] 4) Third device: A device used to trigger the target device to activate or use a specific model. For example, assuming the target device is a user equipment (UE), the third device can be a model control device in the RAN or core network (CN). The model control device can trigger the activation or use of the corresponding model in the UE based on the actual network environment in which the UE is located. For ease of explanation, the embodiments of this application generally use the example of the third device being a 3GPP model control device as an example, which does not constitute a specific limitation.
[0135] Optionally, at least two of the first, second, and third devices may be physically co-located. For example, the model may be trained or provided by the second or third device. Another example is that the third device and the model store / model publishing platform may be physically co-located, meaning the third device and the second device may be located in the same physical device. Alternatively, the third device and the model store / model publishing platform may be deployed independently. For example, the model management and control device in the CN may be an NWDAF network element.
[0136] 5) Target device: This can be the device for which the model needs to be obtained, such as a UE or a network-side device.
[0137] 6) First model: a model provided or trained by a first device, and the first model is registered or published by a second device.
[0138] 7) Target model: The model acquired by the target device and registered or published by the second device.
[0139] 8) Second model: The model that is activated or used by the target device when the third device triggers the target device to activate or use. The second model can be part or all of the target model.
[0140] The number of first models may be one or at least two, and the number of target models may be one or at least two.
[0141] It should be noted that in the relevant technology, the device for training the model can pass the model file information to the target device, such as: passing the model file, the storage information of the model (the address of the storage model file, the network element identifier, etc.), the model identifier (Identity, ID), the model version ID and other information, wherein the device for training the model and the target device may be devices produced by different manufacturers. In this solution, on the one hand, since devices produced by different manufacturers have their own optimization methods for communication models, when the AI / ML model trained by one manufacturer's device is sent to the device of another manufacturer for use, there may be incompatibility issues or security risks. On the other hand, different manufacturers (especially third parties) have different methods of generating communication models and their own optimization methods for communication models, for example: different management rules for model ID or version ID. At this time, when the AI / ML model trained by one manufacturer's device is sent to the device of another manufacturer for use, there may be a problem of not being able to achieve effective scheduling of the model.
[0142] In the embodiment of the present application, the model from the first device is uniformly managed by the second device, and the models provided or trained by devices generated by different manufacturers can be uniformly registered or published. On the one hand, other devices can select compatible or secure models based on the registration information or publication information of the model; on the other hand, the second device can be used to uniformly manage the model ID or version ID of the models from different devices. In this way, effective scheduling of the model can be achieved based on the unified model ID or version ID.
[0143] The information transmission method, model determination method, information transmission device, model determination device and related equipment provided in the embodiments of the present application are described in detail below with reference to some embodiments and their application scenarios in combination with the accompanying drawings.
[0144] Referring to FIG. 2 , an embodiment of the present application provides an information transmission method, the execution subject of which may be a second device. As shown in FIG. 2 , the information transmission method may include the following steps:
[0145] Step 201: A second device receives a first message from a first device, where the first message is used to register or publish a first model.
[0146] Step 202: The second device sends a second message to the first device, where the second message is a response message for registering or publishing the first model, and the second message carries first information, where the first information includes at least one of the following:
[0147] First indication information, used to indicate whether the first model passes the security authentication of the second device;
[0148] The security authentication certificate of the first model, or the token information of the first model passing the security authentication of the second device;
[0149] model identification information of the first model allocated by the second device;
[0150] Version information of the first model allocated by the second device.
[0151] In one embodiment, after the second device registers the first model from the first device, other devices can obtain the model based on the registration information. For example, the second device performs unified registration and management of the first models from multiple first devices. In this way, other devices can obtain the model based on the unified registration information during the process of obtaining the model, thereby realizing effective scheduling of models between different devices or devices from different manufacturers.
[0152] In one implementation, after the second device publishes the first model from the first device, other devices may obtain the model published by the second device.
[0153] Optionally, the second device may perform security verification on the first model from the first device, such as network access security authentication, and register or publish the first model if it is determined that the first model passes the security verification.
[0154] In this way, the registered or published model can be security verified based on the second device. In this way, when the target device subsequently obtains the registered or published model, the model that has not passed the security verification can be avoided from being directly applied to the target device, thereby improving the security performance of the target device.
[0155] In one embodiment, before the second device sends the second message to the first device, the method further includes:
[0156] The second device determines target information according to the first message, where the target information includes at least one of the following:
[0157] first indication information, where the first indication information indicates whether the first model has passed the security authentication of the second device;
[0158] The security authentication certificate of the first model, or the token information of the first model passing the security authentication of the second device;
[0159] model identification information of the first model allocated by the second device;
[0160] version information of the first model allocated by the second device;
[0161] The corresponding relationship between the first model and the activation condition.
[0162] In one implementation, the second information may be completely identical to the target information, or the second information may include part of the target information.
[0163] In one embodiment, when the first model passes the security verification of the second device, a security authentication certificate of the first model is generated, or token information indicating that the first model passes the security verification of the second device is generated.
[0164] Optionally, the correspondence between the first model and the activation condition can be used to determine the conditions for triggering or activating the first model. For example, assuming that the first model passes the security authentication of the second device, the second device publishes the first model, and the target device can obtain the published first model. However, the second device or the third device can determine in which scenario to activate the first model based on the correspondence between the first model and the activation condition, so that the target device uses the activated first model for model inference.
[0165] It should be noted that the second device can perform security authentication operations independently, or can perform specific security authentication operations with the help of other network devices. The embodiment of the present application does not limit the way in which the second device performs security authentication operations on the model.
[0166] Optionally, the token information of the first model passing the security authentication of the second device can be used by subsequent users of the model (such as the target device) to know that the first model is a model that has passed the security authentication of the second device.
[0167] Optionally, the model identification information of the first model allocated by the second device may be unified model ID management of the first model by the second device, so that first models from different first devices have a unified model ID.
[0168] It is worth noting that different devices or devices from different manufacturers may have different rules for allocating model identifiers, or the same model identifier may be assigned to models of different devices or devices from different manufacturers. By using a second device to perform unified model ID management on models from different devices, the model ID allocated by the second device can uniquely identify the model within the second device or the Public Land Mobile Network (PLMN).
[0169] Optionally, the version information of the first model assigned by the second device may be the unified management of the version ID of the first model by the second device, so that the first models from different first devices have a unified version ID assignment rule.
[0170] It is worth noting that different devices or devices from different manufacturers may have different naming rules for model version information, or different devices or devices from different manufacturers may assign duplicate or conflicting model version information to their model versions. By using a second device to perform unified model version ID management on models from different devices, it can be ensured that model version assignment uses unified rules and uniquely identifies different model versions under the same model ID.
[0171] In addition, the first message may not carry the model version information of the first model. In this case, the second device may also allocate the correct version information to the first model according to the recorded information.
[0172] It should be noted that the second device can independently allocate model identification and model version, or can also allocate model identification and model version with the help of other network devices. The embodiment of this application does not limit the way in which the second device allocates model identification or model version information.
[0173] As an optional implementation manner, the first message carries second information, and the second information includes at least one of the following:
[0174] attribute information of the first model;
[0175] file information of the first model;
[0176] Storage information of the first model.
[0177] In one implementation, the attribute information may be attribute information of a first model determined by the first device. For example, the attribute information of the first model includes at least one of the following:
[0178] version information of the first model;
[0179] parameter information of the first model;
[0180] activation conditions of the first model;
[0181] Functions supported by the first model;
[0182] Producer information of the first model;
[0183] The consumer information of the first model.
[0184] Optionally, the parameter information of the first model may include a parameter type list or parameter values of the first model, for example, indicating the input parameters, output parameters, and weight parameters involved in the first model.
[0185] Optionally, the activation condition of the first model can also be referred to as the "condition for use of the first model" or the "validity or applicable condition (Validity / applicable condition)", that is, only when this condition is met can the model reasoning based on the first model be triggered. For example: the activation condition of the first model may indicate the environmental parameters used for activation of the first model. The environmental parameters may include: time parameters (can only be activated at a certain time point or time period), location parameters (activated in a certain tracking area (TA), cell, site, longitude and latitude position), or channel environment parameters (such as antenna port, carrier frequency, bandwidth, sub-carrier space (SCS), channel characteristics (Signal-to-Noise Ratio (SNR), Line of Sight (LOS) / Non-Line of Sight (NLOS)), etc.
[0186] Optionally, the functions supported by the first model may indicate that the first model is specifically used for reasoning about a certain task type (identified by a function type or analytic ID). For example, the purpose may be trajectory prediction, channel state information (CSI) compression or decompression, AI positioning, beam prediction, etc.
[0187] Optionally, the producer information of the first model may indicate the device or user that provides or trains the first model, such as: Producer identification (ID, Fully Qualified Domain Name (FQDN), Internet Protocol (IP) address, etc.), Producer manufacturer (such as vendor name / ID), and Producer device batch.
[0188] Optionally, the consumer information of the first model can be used to limit the consumers of the model to a specific range, such as consumer identification (ID, FQDN, IP address, Type Allocation Code (TAC)), consumer vendor (vendor name / ID), and consumer device batch.
[0189] Optionally, the storage information of the first model may include: storage address, storage location, storage device and other information of the file information of the first model. The second device or target device can obtain the corresponding file information of the first model from the corresponding storage address or device according to the storage information.
[0190] It should be noted that, for the same first model, the attribute information in the first message reported by the first device, such as version information or model representation information, may be different from the attribute information in the first information. That is to say, when the second device registers or publishes the first model, at least part of the attribute information of the first model may be changed, that is, the attribute information of the published or registered model is determined by the second device.
[0191] After the second device registers or publishes the first model, the target device may obtain the registered or published model.
[0192] As an optional implementation, the target device can obtain the target model from the first device. In this case, the first message may or may not carry the target model's file information or storage information. For example, the first message may only carry the model ID and version information. In other words, the target model's file information or storage information may not be sent to the second device.
[0193] As another optional implementation, the method further includes:
[0194] The second device sends third information to the target device, where the third information includes at least one of the following:
[0195] File information of the target model;
[0196] Storage information of the target model;
[0197] model identification information of the target model allocated by the second device;
[0198] version information of the target model allocated by the second device;
[0199] Second indication information, used to indicate that the target model has passed the security authentication of the second device;
[0200] Activation conditions of the target model;
[0201] The security authentication certificate of the target model, or the token information that proves that the target model has passed the security authentication of the second device;
[0202] Wherein, the first model includes the target model.
[0203] Optionally, the second device may determine information of the target device according to the consumer information in the attribute information, for example, the IP address, identifier, FQDN, TAC, etc. of the target device.
[0204] Optionally, the manner in which the second device sends the third information to the target device may include at least one of the following:
[0205] Sent via the control plane (CP) signaling path;
[0206] Sent through the user plane (UP) path.
[0207] Optionally, the second device sending the third information to the target device may be the second device sending the third information to the target device directly or indirectly, for example: the second device sending the third information to the target device indirectly may be the second device sending the third information to a third device (such as a model control device in RAN or CN), and the third device sending the third information to the target device.
[0208] Optionally, before the second device sends the third information to the target device, the method further includes:
[0209] The second device receives seventh information from the third device, wherein the seventh information includes model identification information or version information of the target model, and the seventh information is used to instruct the second device to send model file information or model storage information corresponding to the model identification information or version information of the target model to the target device.
[0210] In one implementation, the seventh information includes model identification information or version information of the target model. In this case, the model identification information or version information may be used to implicitly instruct the second device to transfer the target model to the target device.
[0211] In another implementation, the seventh information may explicitly instruct the second device to transfer the target model to the target device.
[0212] In another embodiment, the seventh information includes model identification information or version information of the target model and indication information for instructing the second device to send model file information or model storage information corresponding to the target model to the target device. In this way, the indication information can be used to instruct the second device to transfer the model to the target device, and the model identification information or version information of the target model can be used to indicate which model or models are transferred by the second device.
[0213] In this embodiment, the third device may determine the target model supported by the target device and instruct the second device to send the model file information or model storage information corresponding to the target model to the target device, so that the target device can obtain the target model accordingly.
[0214] Through the above model registration or publishing, and the process of sending the third information to the target device, model scheduling between different devices can be achieved, so that the target device obtains the model provided by the first device. Thereafter, some or all of the models obtained by the target device can be activated.
[0215] As an optional implementation manner, the method further includes:
[0216] The second device receives a third message from a third device, where the third message includes at least one of the following:
[0217] Model identification information of the target model;
[0218] Version information of the target model;
[0219] The security authentication certificate of the target model, or the token information of the target model passing the security authentication of the second device;
[0220] The second device sends fourth information to the third device, where the fourth information includes at least one of the following:
[0221] third indication information, used to indicate whether the target model passes the security authentication of the second device;
[0222] The activation conditions of the target model.
[0223] The third device is used to activate the second model of the target device, which can be all or part of the target model already acquired by the target device. For example, if the target device is a user equipment (UE), the third device can be a model management device in the RAN or CN.
[0224] In one embodiment, the second device receives a third message from the third device and provides fourth information to the third device based on the third message, so that the third device can determine whether the target model has passed the security verification of the second device based on the fourth information. In this way, the third device requests the second device to perform a secondary verification of the security authentication information of the target model to determine whether the target model is safe; or, the third device can determine whether the conditions for activating the target model are met based on the fourth information, or the third device determines which target model is to be activated based on the communication parameters corresponding to the target device and the fourth information, that is, the third device obtains the activation conditions of the target model from the second device for subsequent activation of the target model according to the actual network environment.
[0225] It is worth mentioning that before the third device sends the third message to the second device, the third device can receive second capability information from the target device, where the second capability information is related to the models supported by the target device. The models supported by the target device can be models that the target device has already acquired. For example, after completing the registration of the first model, the UE acquires the newly registered model and then reports the model ID list of the target device through the second capability information. At this time, the third device can verify with the second device the activation conditions of the target model of the target device / whether it has passed the security verification of the second device and other information.
[0226] Optionally, the second capability information may carry at least one of the following:
[0227] Version information of the target model;
[0228] The security authentication certificate of the target model, or the token information that the target model passes the security authentication of the second device.
[0229] In this way, the third device determines which models are supported by or already possessed by the target device based on the second capability information from the target device, and sends a third message to the second device requesting verification of these models.
[0230] In this embodiment, the third device and the second device are independent devices. In another embodiment, the third device and the second device can be co-located. In this case, the second device and the third device are the same device. The second device can determine whether the conditions for activating a target model supported by the target device are met based on the second capability information from the target device without exchanging the third message and the fourth information. Alternatively, the second device can determine which target model to activate based on the communication parameters corresponding to the target device and the fourth information.
[0231] As an optional implementation manner, the method further includes:
[0232] The second device obtains first capability information, where the first capability information is used to indicate the AI capability of the target device;
[0233] The second device determines the target model according to the first capability information and the second information.
[0234] In one implementation, the second device may receive first capability information from the target device.
[0235] In another embodiment, the second device may obtain the first capability information from the third device, that is, the third device first obtains the first capability information of the target device and then sends the first capability information to the second device.
[0236] Optionally, assuming that the target device is a UE and the third device is a model management device in the RAN or CN, the manner in which the UE sends the first capability information to the third device may include at least one of the following:
[0237] The UE can send the radio capability (including UE AI capability information) in the Radio Resource Control (RRC) layer to the RAN model management device;
[0238] The UE sends the 5G Mobility Management capability (MM capability) (including UE AI capability information) to the AMF, which then sends it to the model control device in the RAN or CN.
[0239] The UE sends UE model capability reporting information to the model control device in the CN, including UE AI capability information.
[0240] In one embodiment, the first capability information includes at least one of the following:
[0241] Fourth indication information, used to indicate whether the target device supports a model-based AI function, for example, whether the target device supports an AI model-based reasoning function;
[0242] The type of AI function supported by the target device, for example: AI functionality type supported by the target device;
[0243] Function identification information of the AI functions supported by the target device, such as AI functionality ID and Analytics ID supported by the target device;
[0244] The applicable conditions for each AI function supported by the target device.
[0245] Optionally, the AI functionality type / ID can be AI positioning, AI trajectory prediction, AI energy saving, etc.
[0246] Optionally, the AI capability information may also include applicable conditions corresponding to each supported AI functionality type / ID. The applicable conditions include applicable time, applicable business, applicable location, etc.
[0247] In this embodiment, before sending the third information to the target device, the second device also determines the target model supported by the target terminal based on the AI capability of the target device, and thus only sends the target model supported by it to the target terminal, which can reduce the waste of resources caused by sending models that are not supported by the target terminal to the target terminal.
[0248] It should be noted that, in another optional implementation, a third device may also determine the target model based on the AI capabilities supported by the target device. In this case, the third device may notify the second device to provide the target device with the model file information and storage information of the target model determined by the third device. Alternatively, the third device may obtain the model file information and storage information of the registered or published first model from the second device, and after determining the target model based on the AI capabilities supported by the target device, provide the target device with the model file information or storage information of the target model determined by the third device.
[0249] In an embodiment of the present application, the model of the first device is registered by the second device to achieve unified management of models trained or provided by different devices, or the model of the first device is published by the second device, and the model of the first device can be verified during the publishing process, so that other devices can obtain valid or secure models based on the registration information or published information.
[0250] Referring to FIG3 , the execution subject of the second information transmission method provided in an embodiment of the present application may be a first device. The first device may be any device capable of training or providing a model, such as an AF. The AF may interact with the UE through an application layer (e.g., an OTT server). As shown in FIG3 , the second information transmission method may include the following steps:
[0251] Step 301: A first device sends a first message to a second device, where the first message is used to register or publish a first model.
[0252] In one implementation, the first model may be a model trained by the first device.
[0253] In one scenario, the model trained by the first device is used to provide the target device with model inference. For example, assuming that the first device is a third-party server (AF for short), the third-party server can train the model for the UE. Specifically, the third-party server collects training data and performs model training based on the training data and a specific AI model training method to obtain the model. The collected training data can come from the UE, base station, core network, and AF itself.
[0254] In addition, the collected data types may be air interface measurement data, specific service data, Quality of Experience (QoE) data, and the like.
[0255] Step 302: The first device receives a second message from the second device, where the second message is a response message for registering or publishing the first model, and the second message carries first information, where the first information includes at least one of the following:
[0256] First indication information, used to indicate whether the first model passes the security authentication of the second device;
[0257] The security authentication certificate of the first model, or the token information of the first model passing the security authentication of the second device;
[0258] model identification information of the first model allocated by the second device;
[0259] Version information of the first model allocated by the second device.
[0260] In an embodiment of the present application, the meanings and functions of the above-mentioned first message, second message, first device, second device, first information, first indication information, first model, security authentication certificate of the first model, token information of the first model passing security authentication of the second device, model identification information, and version information of the first model are the same as the meanings and functions of the first message, second message, first device, second device, first information, first indication information, first model, security authentication certificate of the first model, token information of the first model passing security authentication of the second device, model identification information, and version information of the first model in the method embodiment shown in Figure 2. For details, please refer to the explanation in the method embodiment shown in Figure 2, and no further details will be given here.
[0261] As an optional implementation manner, the first message carries second information, and the second information includes at least one of the following:
[0262] attribute information of the first model;
[0263] file information of the first model;
[0264] Storage information of the first model.
[0265] As an optional implementation manner, the attribute information of the first model includes at least one of the following:
[0266] version information of the first model;
[0267] parameter information of the first model;
[0268] Activation conditions of the first model
[0269] Functions supported by the first model;
[0270] Producer information of the first model;
[0271] The consumer information of the first model.
[0272] As an optional implementation manner, the method further includes:
[0273] The first device sends third information to the target device, where the third information includes at least one of the following:
[0274] File information of the target model;
[0275] Storage information of the target model;
[0276] model identification information of the target model allocated by the second device;
[0277] Version information of the target model in the second device allocation;
[0278] Second indication information, used to indicate that the target model has passed the security authentication of the second device;
[0279] Activation conditions of the target model;
[0280] The security authentication certificate of the target model, or the token information that proves that the target model has passed the security authentication of the second device;
[0281] Wherein, the first model includes the target model.
[0282] As an optional implementation manner, the first device sending third information to the target device includes:
[0283] When the first device determines, based on the first information, that the target model passes the security authentication of the second device, the first device sends third information to the target device.
[0284] As an optional implementation manner, before the first device sends the third information to the target device, the method further includes:
[0285] The first device receives a fourth message from the target device, wherein the fourth message is used to request a model in the first device, wherein the model in the first device includes the target model.
[0286] In one embodiment, after receiving the fourth message, the first device may check whether there is a newly trained or newly generated model. If the first device has a newly trained model, the first device sends sixth indication information to the target device, where the sixth indication information indicates that the first device has a newly trained model. In this way, the target device can obtain the newly trained model from the first device based on receiving the sixth indication information.
[0287] Optionally, the first device has a newly trained model, which can be understood as: the first device has a model trained after a first moment, and the first moment can be the moment when the model was last transferred to the target device.
[0288] For example: the target device periodically requests a newly trained model from the first device. In this way, if the first device has trained the model between T1 and T2, then in T2, the first device sends a sixth indication message to the target device to indicate that the first device has a newly trained model after sending the model to the target device in T1.
[0289] For another example, after receiving a registration response message from a second device, the first device notifies the target device of new model file information. The target device then obtains the new model file information from the first device in response to the notification. Alternatively, if the model file information includes model storage information, the target device downloads the model from the address, location, or storage device corresponding to the model storage information. The specific downloading method is not limited.
[0290] In an embodiment of the present application, the first model trained or provided by the first device can be uniformly registered or published through the second device, thereby realizing unified management or security verification of models from different devices, which has the same beneficial effects as the method embodiment shown in Figure 2. To avoid repetition, it will not be repeated here.
[0291] Please refer to Figure 4, which shows a third information transmission method provided by an embodiment of the present application. The execution subject of this method is a third device, such as a model management device in the RAN or CN. As shown in Figure 4, the third information transmission method may include the following steps:
[0292] Step 401: A third device receives second capability information from a target device, where the second capability information is related to a model supported by the target device.
[0293] In one implementation, the model supported by the target device may be a model owned by the target device.
[0294] Step 402: The third device sends a fifth message to the target device based on the second capability information, where the fifth message is used to trigger or activate a second model in the target device, wherein the models supported by the target device include the second model.
[0295] In one implementation, the model supported by the target device may be the target model as shown in FIG. 2 , that is, the model registered or published by the second device and acquired by the target device.
[0296] It should be noted that the meanings of the above-mentioned third device, target device, and target model in the embodiments of the present application are the same as those of the third device, target device, and target model in the method embodiment shown in Figure 2, and will not be repeated here.
[0297] In an embodiment of the present application, the third device can trigger or activate the second model in the target device according to the model supported by the target device, so that the target device can use the triggered or activated second model to perform model reasoning.
[0298] As an optional implementation manner, the second capability information includes at least one of the following:
[0299] Model identification information of the models supported by the target device, for example, a model ID list;
[0300] Version information corresponding to the model supported by the target device;
[0301] The security authentication certificate of the model supported by the target device, or the token information that the model supported by the target device has passed the security authentication of the second device.
[0302] In one embodiment, when the second capability information includes the security authentication certificate of the model supported by the target device, or the token information that the model supported by the target device has passed the security authentication of the second device, the third device can determine that the model supported by the target device has passed the security authentication of the second device, thereby triggering or activating the model supported by the target device.
[0303] In another embodiment, when the second capability information does not include the security authentication certificate of the model supported by the target device, or the token information of the model supported by the target device is securely authenticated by the second device, the third device may request the second device to verify the model supported by the target device.
[0304] For example, the method further includes:
[0305] The third device sends a sixth message to the second device, where the sixth message includes at least one of the following:
[0306] Model identification information of the models supported by the target device;
[0307] Version information of the model supported by the target device;
[0308] The third device receives sixth information from the second device, where the sixth information includes at least one of the following:
[0309] fifth indication information, used to indicate whether the model supported by the target device has passed the security authentication of the second device;
[0310] usage conditions corresponding to the model identification information or version information of the model supported by the target device;
[0311] The security authentication certificate of the model supported by the target device, or the token information of the model supported by the target device being securely authenticated by the second device.
[0312] In one embodiment, the sixth message in the embodiment of the present application has a similar function to the third message in the method embodiment shown in FIG2 , except that the third message is used to request the second device to verify the target model, and the sixth message is used to request the second device to verify the model supported by the target device. Optionally, the model supported by the target device may be the same as the target model in the method embodiment shown in FIG2 , in which case the third message is the same as the sixth message. Similarly, the sixth message in the embodiment of the present application is the same as or similar to the fourth message in the method embodiment shown in FIG2 . For the explanation of the sixth message and the sixth message, reference may be made to the explanation of the third message and the fourth message in the method embodiment shown in FIG2 , which will not be repeated here.
[0313] Optionally, when the sixth information includes: usage conditions corresponding to model identification information or version information of a model supported by the target device, the third device may activate the corresponding model according to the usage conditions corresponding to the model.
[0314] As an optional implementation manner, the method further includes:
[0315] The third device determines the second model according to the communication parameters corresponding to the target device and the second capability information.
[0316] In this embodiment, the third device determines the second model based on the communication parameters corresponding to the target device and the second capability information. The third device may trigger or activate the second model when the communication parameters corresponding to the target device (such as: time parameters: can only be activated at a certain time point or time period; location parameters: activated at a certain TA, cell, site, longitude and latitude position; channel environment parameters: antenna port, carrier frequency, bandwidth, SCS, channel characteristics (SNR, LOS / NLOS), etc.) meet the corresponding second model usage conditions.
[0317] As an optional implementation manner, the third device sends a fifth message to the target device according to the second capability information, including:
[0318] When the third device determines, based on the second capability information, that the current network environment of the target device meets the usage condition of the second model, the third device sends a fifth message to the target device.
[0319] The fifth message may be used to trigger or activate the second model so that the target device performs model reasoning using the second model.
[0320] Optionally, the fifth message includes at least one of the following:
[0321] model identification information of the second model;
[0322] Version information or version information of the second model.
[0323] Optionally, determining whether the network environment of the target device meets the usage condition of the second model includes at least one of the following:
[0324] Determining that the current time matches a time parameter in the usage conditions of the second model (such as activation at a certain time point or time period);
[0325] Determining that the location information of the target device matches the location parameters in the usage conditions of the second model (e.g., activation at a certain TA, cell, site, latitude and longitude);
[0326] Determine whether the channel of the target device matches the channel environment parameters (such as antenna port, carrier frequency, bandwidth, SCS, channel characteristics (SNR, LOS / NLOS), etc.) in the usage conditions of the second model.
[0327] As an optional implementation manner, the method further includes:
[0328] The third device receives first capability information from the target device, where the first capability information is used to indicate the AI capability of the target device;
[0329] The third device sends the first capability information to the second device, or the third device determines a target model from a first model based on the first capability information, wherein the target model includes a model applicable to the target device, and the first model comes from the first device and is registered or published through the second device.
[0330] In one implementation, the third device sends the first capability information to the second device. At this time, the second device determines the model supported by the target device, ie, the target model, according to the first capability information.
[0331] In another implementation, the third device determines the model supported by the target device according to the first capability information.
[0332] Optionally, the first capability information includes at least one of the following:
[0333] Fourth indication information, used to indicate whether the target device supports the model-based AI function;
[0334] The type of AI functionality supported by the target device;
[0335] Function identification information of the AI function supported by the target device;
[0336] The applicable conditions for each AI function supported by the target device.
[0337] In the embodiment of the present application, the process of the third device or the second device determining the models supported by the target device based on the first capability information is the same as the process of the second device determining the models supported by the target device based on the first capability information in the method embodiment shown in Figure 2, and will not be repeated here. In addition, in the embodiment of the present application, it is also possible to screen the models supported by the target device capabilities before sending the target model to the target device, thereby reducing the waste of resources caused by sending models that are not supported by the target device capabilities to the target device.
[0338] Please refer to Figure 5, which is a flowchart of a fourth information transmission method provided in an embodiment of the present application. The execution subject of this method is a target device, that is, a device that needs to schedule a model from another device, such as a UE. As shown in Figure 5, this fourth information transmission method may include the following steps:
[0339] Step 501: The target device receives third information.
[0340] Step 502: The target device obtains a target model according to the third information, where the target model includes at least one first model, which comes from the first device and is registered or published through the second device.
[0341] In one implementation, the target device may receive third information from the first device.
[0342] In another implementation, the target device may receive third information from the second device.
[0343] The third information is related to the target model, for example, the third information includes at least one of the following:
[0344] File information of the target model;
[0345] Storage information of the target model;
[0346] model identification information of the target model allocated by the second device;
[0347] version information of the target model allocated by the second device;
[0348] Second indication information, used to indicate that the target model has passed the security authentication of the second device;
[0349] activation conditions of the target model;
[0350] The security authentication certificate of the target model, or the token information that the target model passes the security authentication of the second device.
[0351] It should be noted that the meanings of the above-mentioned target device, first device, second device, target model, first model, and third information in the embodiments of the present application are the same as the meanings of the target device, first device, second device, target model, first model, and third information in the method embodiment shown in Figure 2, and will not be repeated here.
[0352] In an embodiment of the present application, the target device can obtain a model trained or provided by the first device and registered or published by the second device.
[0353] As an optional implementation manner, the method further includes:
[0354] The target device sends second capability information to a third device, wherein the second capability information is related to a model supported by the target device;
[0355] The target device receives a fifth message from the third device, where the fifth message is used to trigger or activate a second model of the target device, where the target model includes the second model.
[0356] In one implementation, the model supported by the target device may be a model possessed by the target device.
[0357] It should be noted that the meanings of the above-mentioned third device, second capability information, fifth message, and second model in the embodiment of the present application are the same as the meanings of the third device, second capability information, fifth message, and second model in the implementation of the method shown in Figure 4, and will not be repeated here.
[0358] Optionally, the method further includes:
[0359] The target device performs a model inference operation based on the second model.
[0360] Optionally, the second capability information includes at least one of the following:
[0361] Model identification information of the models supported by the target device;
[0362] Version information corresponding to the model supported by the target device;
[0363] The security authentication certificate of the model supported by the target device, or the token information that the model supported by the target device has passed the security authentication of the second device.
[0364] Optionally, the fifth message includes at least one of the following:
[0365] model identification information of the second model;
[0366] Version information of the second model.
[0367] In this embodiment, the target device reports the models it supports to the third device so that the third device can activate at least one of them accordingly. In this way, the target device can perform model inference operations based on the activated second model.
[0368] As an optional implementation manner, before the target device receives the third information, the method further includes:
[0369] The target device sends first capability information to a third device, where the first capability information is used to indicate the AI capability of the target device;
[0370] The target device receives the third information, including:
[0371] The target device receives third information from the third device or the second device, where the third information includes the fifth information.
[0372] Optionally, the content of the fifth information may be the same as the content of the third information, except that the fifth information may be determined by the second device for the target device according to the first capability information.
[0373] It should be noted that the meanings of the above-mentioned first capability information, AI capability of the target device, and third information in the embodiment of the present application are the same as the meanings of the first capability information, AI capability of the target device, and third information in the implementation of the method shown in Figures 2 and 4, and will not be repeated here.
[0374] Optionally, the fifth information includes at least one of the following:
[0375] File information of the target model;
[0376] Storage information of the target model;
[0377] model identification information of the target model allocated by the second device;
[0378] version information of the target model allocated by the second device;
[0379] activation conditions of the target model;
[0380] Second indication information, used to indicate that the target model has passed the security authentication of the second device;
[0381] The security authentication certificate of the target model, or the token information of the second model passing the security authentication of the second device.
[0382] In this embodiment, the target device reports the supported AI capabilities so that the first device or the second device can filter the registered or published models to the target device and only provide the target device with target models supported by its capabilities.
[0383] Please refer to FIG6 , which is a flowchart of a first model determination method provided in an embodiment of the present application. The execution subject is a third device. As shown in FIG6 , the first model determination method may include the following steps:
[0384] Step 601: A third device receives first capability information from a target device, where the first capability information is used to indicate the AI capability of the target device.
[0385] Step 602: The third device determines a target model according to the first capability information, wherein the target model includes a model applicable to the target device.
[0386] In one embodiment, the target model may include at least a portion of the first model from the first device and registered or published through the second device.
[0387] In another implementation manner, the target model may be a model obtained by the target device through other means, which is not specifically limited here.
[0388] It should be noted that the meanings of the above-mentioned first capability information, AI capability, and target model in the embodiments of the present application are the same as those in the method embodiments shown in Figures 2 to 5, and will not be repeated here.
[0389] Optionally, the first capability information includes at least one of the following:
[0390] Fourth indication information, used to indicate whether the target device supports the model-based AI function;
[0391] The type of AI functionality supported by the target device;
[0392] Function identification information of the AI function supported by the target device;
[0393] The applicable conditions for each AI function supported by the target device.
[0394] As an optional implementation manner, the third device determines the target model according to the first capability information, including at least one of the following:
[0395] In a case where the first capability information includes the type or function identification information of the AI function supported by the target device, the third device determines the model corresponding to the type or function identification information of the AI function as the target model, that is, if the function supported by a certain model matches the AI functionality type / ID supported by the target device, the model may be set as the model applicable to the target device;
[0396] In the case where the first capability information includes the applicable conditions of each AI function, the third device determines a model whose activation conditions match the applicable conditions of the AI function as the target model. That is, if the conditions for the use of a model (or activation conditions) match the applicable conditions included in the first capability information of the target device, the model may be set as the model applicable to the target device.
[0397] The third device determines the model whose producer information or consumer information matches the TAC or manufacturer information of the target device as the target model, that is, if the consumer information of a model includes the TAC or manufacturer information of the target device, the model may be set as the model applicable to the target device.
[0398] Optionally, the method further includes:
[0399] The third device sends fifth information to the target device, where the fifth information includes at least one of the following:
[0400] File information of the target model;
[0401] Storage information of the target model;
[0402] model identification information of the target model allocated by the second device;
[0403] version information of the target model allocated by the second device;
[0404] activation conditions of the target model;
[0405] Second indication information, used to indicate that the target model has passed the security authentication of the second device;
[0406] The security authentication certificate of the target model, or the token information that the target model passes the security authentication of the second device.
[0407] As an optional implementation manner, the third device determines the target model according to the first capability information, including:
[0408] The third device sends the first capability information to the second device;
[0409] The third device receives the fifth information from the second device;
[0410] The third device determines the target model according to the fifth information.
[0411] In this implementation, the third device forwards the first capability information to the second device, so that the second device determines the target model applicable to the target device based on the first capability information.
[0412] As another optional implementation manner, after the third device determines the target model according to the first capability information, the method further includes:
[0413] The third device sends seventh information to the second device, wherein the seventh information includes model identification information or version information of the target model, and the seventh information is used to instruct the second device to send model file information or model storage information corresponding to the model identification information or version information of the target model to the target device.
[0414] In this implementation, the third device determines a target model applicable to the target device according to the first capability information, and instructs the second device to send model file information or model storage information corresponding to the target model to the target device.
[0415] In an embodiment of the present application, the third device can filter models based on the AI capabilities reported by the target device, so as to only send models supported by its capabilities to the target device.
[0416] Please refer to FIG7 , which is a flowchart of a second model determination method provided in an embodiment of the present application. The execution subject is the target device. As shown in FIG7 , the second model determination method may include the following steps:
[0417] Step 701: The target device sends first capability information to a third device, where the first capability information is used to indicate the AI capability of the target device.
[0418] Step 702: The target device obtains a target model, wherein the target model includes a model applicable to the target device.
[0419] It should be noted that the meanings of the above-mentioned first capability information, AI capability, and target model in the embodiments of the present application are the same as those in the method embodiments shown in Figures 2 to 5, and will not be repeated here.
[0420] Optionally, the target device acquires the target model, including:
[0421] The target device obtains a target model from the third device.
[0422] Wherein, optionally, the target model is a model provided or trained by the first device.
[0423] Optionally, the target device acquires the target model, including:
[0424] The target device obtains a target model from a second device, wherein the model registered or published by the second device includes the target model.
[0425] Optionally, the target device acquires the target model, including:
[0426] The target device receives fifth information, where the fifth information includes at least one of the following:
[0427] File information of the target model;
[0428] Storage information of the target model;
[0429] model identification information of the target model allocated by the second device;
[0430] version information of the target model allocated by the second device;
[0431] activation conditions of the target model;
[0432] Second indication information, used to indicate that the target model has passed the security authentication of the second device;
[0433] The security authentication certificate of the target model, or the token information that the target model passes the security authentication of the second device.
[0434] Optionally, the first capability information includes at least one of the following:
[0435] Fourth indication information, used to indicate whether the target device supports the model-based AI function;
[0436] The type of AI functionality supported by the target device;
[0437] Function identification information of the AI function supported by the target device;
[0438] The applicable conditions for each AI function supported by the target device.
[0439] In the embodiment of the present application, the steps executed by the target device correspond to the steps executed by the third device in the method embodiment shown in Figure 6, and can achieve the same or similar beneficial effects as the method embodiment shown in Figure 6. To avoid repetition, they will not be repeated here.
[0440] Please refer to FIG8 , which is a flowchart of a third model determination method provided in an embodiment of the present application. The execution subject is the second device. As shown in FIG8 , the third model determination method may include the following steps:
[0441] Step 801: The second device obtains first capability information, where the first capability information is used to indicate the AI capability of the target device.
[0442] In one embodiment, the second device obtains the first capability information, including:
[0443] The second device obtains the first capability information from the third device.
[0444] For example, the third device receives the first capability information from the target device and forwards the first capability information to the second device.
[0445] In another embodiment, the second device obtains the first capability information, including:
[0446] The second device obtains first capability information from the target device.
[0447] Step 802: The second device determines a target model from the first model according to the first capability information, wherein the target model includes a model applicable to the target device.
[0448] It should be noted that the meanings of the above-mentioned first capability information, AI capability, and target model in the embodiments of the present application are the same as those in the method embodiments shown in Figures 2 to 5, and will not be repeated here.
[0449] Optionally, the first capability information includes at least one of the following:
[0450] Fourth indication information, used to indicate whether the target device supports the model-based AI function;
[0451] The type of AI functionality supported by the target device;
[0452] Function identification information of the AI function supported by the target device;
[0453] The applicable conditions for each AI function supported by the target device.
[0454] Optionally, the second device determines a target model from the first model according to the first capability information, including at least one of the following:
[0455] In a case where the first capability information includes a type or function identification information of an AI function supported by the target device, the second device determines a first model corresponding to the type or function identification information of the AI function as a target model;
[0456] In a case where the first capability information includes an applicable condition for each AI function, the second device determines a first model whose activation condition matches the applicable condition for the AI function as a target model;
[0457] The second device determines, as a target model, a first model whose producer information or consumer information matches the type allocation code TAC or vendor information of the target device.
[0458] Optionally, the method further includes:
[0459] The second device sends fifth information to at least one of the third device and the target device, where the fifth information includes at least one of the following:
[0460] File information of the target model;
[0461] Storage information of the target model;
[0462] model identification information of the target model allocated by the second device;
[0463] version information of the target model allocated by the second device;
[0464] activation conditions of the target model;
[0465] Second indication information, used to indicate that the target model has passed the security authentication of the second device;
[0466] The security authentication certificate of the target model, or the token information that the target model passes the security authentication of the second device.
[0467] In one embodiment, the second device may pre-acquire the first capability information of the target device. Thereafter, during the model registration or publishing process, the second device may send fifth information to the target device if it determines that the registered or published model is applicable to the target device.
[0468] In another embodiment, the second device may send the fifth information to the third device, and the third device may forward the fifth information to the target device. For example, during the model registration or publishing process, the second device may send the model file information of the registered or published model to the third device. After receiving the first capability information of the target device, the third device may select the model file information of the target model applicable to the target device from the received model file information and send it to the target device.
[0469] In the embodiment of the present application, the steps executed by the target device correspond to the steps executed by the third device in the method embodiment shown in Figure 6 and the steps executed by the target device in the method embodiment shown in Figure 7, and can achieve the same or similar beneficial effects as the method embodiments shown in Figures 6 and 7. To avoid repetition, they will not be repeated here.
[0470] To facilitate understanding of the information transmission method and model determination method provided in the embodiments of the present application, it is assumed that the first device is an OTT server, the second device is a model store, the third device is a model management device in the RAN or CN, and the target device is a UE or other consumer. The following three application scenarios are used as examples to illustrate the interaction process between the first device, the second device, the third device, and the target device:
[0471] Application scenario 1: The OTT server registers model information with the Model store, and the UE obtains the model from the OTT server and triggers it.
[0472] As shown in Figure 9a, the interaction process between the OTT server, Model store, UE, and model management equipment in the RAN or CN includes:
[0473] Step 1: UE data collection is performed through the Data Collection Application Server (DCAF).
[0474] Step 2: The OTT server trains the model based on the collected data.
[0475] Step 3. The OTT server sends a first message to the model store, requesting model registration / publishing a model configuration file (carrying: function, producer, consumer, validity condition, version);
[0476] In step 3, the OTT server registers or publishes the trained model-related information to the Model store, and the message includes the model's attribute information.
[0477] Step 4. The model store performs network security authentication, assigns model IDs, assigns model version information, and matches and records model IDs and validity conditions for the models published by the OTT server.
[0478] Step 5. The model store sends a second message (i.e., a registration response message) to the OTT server, carrying: the model ID and version ID of the model release confirmation;
[0479] Step 6. The OTT server delivers the model (allocated model ID + version ID, model file) to the UE. Optionally, there is a model indication or request process between steps 5 and 6, for example, the UE requests the model from the OTT server, or the OTT server indicates to the UE that a new model is available.
[0480] It should be noted that in this step, the OTT server may transmit model file information to the UE, such as the model file itself, or model storage address information (used to indicate to the UE the download address, URL location, or storage device of the model file). The model file includes: model structure information or model parameter information. Parameter information includes: parameter type list or parameter value.
[0481] Specifically, the AF also sends the model id+version num corresponding to the model file information to the UE, where the model ID is allocated by the model store; the model version num can be allocated by the model store or allocated by the AF itself.
[0482] One specific push method includes: the UE periodically requests the AF whether there is new model file information; when the AF has new model file information, it notifies the UE; and the UE obtains the new model file information from the AF according to the notification.
[0483] Another push method includes: after the AF obtains the registration response message of the model store, it notifies the UE that there is new model file information; the UE obtains the new model file information from the AF according to the notification.
[0484] If the model file information includes model storage information, the UE downloads the model from the address, location or storage device corresponding to the model storage information. The specific downloading method is not limited.
[0485] Step 7. The UE sends the second capability information (including model ID and version ID) to the network; the UE may receive one or more models from the OTT server. At this time, one of them needs to be activated, and different models can be activated according to different scenarios / functions.
[0486] Step 8. Verify the terminal model ID + version ID (to obtain validity conditions);
[0487] This step can be a verification between the model control device in the RAN or CN and the second device; for example: the model control device in the RAN or CN sends a verification request message to the second device, and the second device feeds back a verification response message to the model control device in the RAN or CN.
[0488] Optionally, the verification request message is used for at least one of the following purposes:
[0489] Verify that the model ID or other information reported by the UE in step 7 has been securely verified by the model store;
[0490] Gets the model usage conditions corresponding to the model ID and optional version information.
[0491] Correspondingly, the verification response message includes at least one of the following information:
[0492] First instruction information
[0493] Model usage conditions corresponding to the Model ID and optional version information.
[0494] Step 9. The model management device in the RAN or CN performs model activation management (model ID, version ID) on the UE;
[0495] In this step, when the model control device in the RAN or CN determines that the actual network environment meets the conditions for using a specific model, it sends a message to the UE to activate the model. The message carries:
[0496] The ID of the model to be activated
[0497] Model version information to be activated.
[0498] Step 10: The network and the UE exchange inference data.
[0499] After activating the specific model in step 9, the UE collects input information, and the output information should be the information obtained by the UE using the model for reasoning.
[0500] Application scenario 2: The OTT server registers model information with the model store, and the UE obtains the model from the model store and triggers it. The third device and the second device can be set up together.
[0501] As shown in Figure 9b, the interaction process between the OTT server, Model store, UE, and model management equipment in the RAN or CN includes:
[0502] Steps 1-5 are similar to those in the application scenario shown in FIG9a , except that:
[0503] In the application scenario shown in Figure 9b, in step 3, the registration message sent by the OTT server to the model store also includes the model file information. In other words, the OTT server also sends the model file information to the model store for security verification or storage. In step 4, the model store also saves the model file information.
[0504] Step 6: The model store sends the model file information obtained in step 3 to the UE.
[0505] Optionally, the model store also sends the following information corresponding to the model file information to the UE:
[0506] Model ID information assigned to the model;
[0507] Model version information;
[0508] The first indication information is used to indicate that the model information of the model has passed the verification of the model store / platform;
[0509] The security authentication certificate or token information assigned to the model.
[0510] The model store may obtain information of the target UE, such as the IP address, identifier, FQDN, TAC, etc. of the target UE, based on the consumer information of the model in step 3.
[0511] The Model Store sends model file information to the target UE in at least one of the following ways:
[0512] Sent via the CP plane signaling path;
[0513] Sent via the UP data path;
[0514] The sending path may also include a model control device in the RAN or CN. In other words, the Model Store may first send the model file information to the model control device in the RAN or CN, which then sends it to the UE.
[0515] Steps 7-10 are the same as steps 7-10 in the application scenario shown in FIG9a , and are not described again here.
[0516] Application scenario three: The OTT server registers model information with the Model store, and the UE obtains and triggers the model from the Model store or the model management device in the RAN or CN.
[0517] As shown in Figure 9c, the interaction process between the OTT server, Model store, UE, and model management equipment in the RAN or CN includes:
[0518] Steps 1-5 are the same as steps 1-5 in the application scenario shown in FIG9a or FIG9b , and are not repeated here;
[0519] Step 6: The UE sends its first capability information to the model control device in the RAN or CN.
[0520] Step 7: The model control device in the RAN or CN selects a suitable model for the UE according to the first capability information.
[0521] Specifically, if the network (model management device in RAN or CN) and the model store are separately located, then the following steps 7a and 7b are performed. If they are jointly located, then steps 7a and 7b are not required.
[0522] Step 7a: The model management and control device in the RAN or CN forwards the first capability information to the model store;
[0523] Step 7b: The model store sends at least one of the following information of the (one or more) model instances corresponding to the first capability information to the model management and control device in the network RAN or CN:
[0524] Model ID
[0525] Version Information
[0526] Model file information
[0527] Conditions of use
[0528] The first indication information is used to indicate that the model information of the model has passed the verification of the model store / platform;
[0529] The security authentication certificate or token information assigned to the model.
[0530] It should be noted that the model file information can be sent to the model control device in the RAN or CN in this step, and then forwarded to the UE by it. Alternatively, the model file information may not be sent to the model control device in the RAN or CN, that is, in step 7b, only the model-related attribute information is sent to the model control device, and the UE subsequently obtains the model file information directly from the model store.
[0531] Before executing step 7b, the model store needs to determine the model applicable to the AI functionality type / ID based on the first capability information of the UE.
[0532] Step 8: The model management device or model store sends at least one of the following information of the selected (one or more) model instances to the UE:
[0533] Model ID
[0534] Version Information
[0535] Model file information
[0536] Conditions of use
[0537] The first indication information is used to indicate that the model information of the model has passed the verification of the model store / platform;
[0538] The security authentication certificate or token information assigned to the model.
[0539] It should be noted that if the model control device or model store is located separately, there are two possible ways to send the above information:
[0540] The model control device sends the information to the UE; the model control device first obtains the above information from the model store
[0541] Optionally, the model store obtains information such as the identifier, address, and FQDN of the UE from the model management device in step 7a.
[0542] Steps 9-10. Same as steps 9-10 in application scenario 1.
[0543] The information transmission method provided in the embodiment of the present application can be executed by an information transmission device. In the embodiment of the present application, the information transmission device provided in the embodiment of the present application is described by taking the information transmission method executed by the information transmission device as an example.
[0544] Please refer to FIG. 10 . The information transmission apparatus 1000 provided in the embodiment of the present application may be an apparatus in the second device.
[0545] As shown in FIG10 , the information transmission device 1000 may include the following modules:
[0546] A first receiving module 1001 is configured to receive a first message from a first device, wherein the first message is used to register or publish a first model;
[0547] The first sending module 1002 is configured to send a second message to the first device, where the second message is a response message for registering or publishing the first model, and the second message carries first information, where the first information includes at least one of the following:
[0548] First indication information, used to indicate whether the first model passes the security authentication of the second device;
[0549] The security authentication certificate of the first model, or the token information of the first model passing the security authentication of the second device;
[0550] model identification information of the first model allocated by the second device;
[0551] Version information of the first model allocated by the second device.
[0552] Optionally, the first message carries second information, where the second information includes at least one of the following:
[0553] attribute information of the first model;
[0554] file information of the first model;
[0555] Storage information of the first model.
[0556] Optionally, the attribute information of the first model includes at least one of the following:
[0557] version information of the first model;
[0558] parameter information of the first model;
[0559] activation conditions of the first model;
[0560] Functions supported by the first model;
[0561] Producer information of the first model;
[0562] The consumer information of the first model.
[0563] Optionally, the information transmission device 1000 further includes:
[0564] A sixth sending module is configured to send third information to the target device, wherein the third information includes at least one of the following:
[0565] File information of the target model;
[0566] Storage information of the target model;
[0567] model identification information of the target model allocated by the second device;
[0568] version information of the target model allocated by the second device;
[0569] Second indication information, used to indicate that the target model has passed the security authentication of the second device;
[0570] Activation conditions of the target model;
[0571] The security authentication certificate of the target model, or the token information that proves that the target model has passed the security authentication of the second device;
[0572] Wherein, the first model includes the target model.
[0573] Optionally, the information transmission device 1000 further includes:
[0574] a sixth receiving module, configured to receive a third message from a third device, wherein the third message includes at least one of the following:
[0575] Model identification information of the target model;
[0576] Version information of the target model;
[0577] The security authentication certificate of the target model, or the token information of the target model passing the security authentication of the second device;
[0578] a seventh sending module, configured to send fourth information to the third device, wherein the fourth information includes at least one of the following:
[0579] third indication information, used to indicate whether the target model passes the security authentication of the second device;
[0580] The activation conditions of the target model.
[0581] Optionally, the information transmission device 1000 further includes:
[0582] a fourth acquisition module, configured to acquire first capability information, where the first capability information is used to indicate the AI capability of the target device;
[0583] A third determination module is configured to determine the target model according to the first capability information and the second information.
[0584] Optionally, the fourth acquisition module is specifically configured to:
[0585] Acquire first capability information from the third device.
[0586] Optionally, the first capability information includes at least one of the following:
[0587] Fourth indication information, used to indicate whether the target device supports the model-based AI function;
[0588] The type of AI functionality supported by the target device;
[0589] Function identification information of the AI function supported by the target device;
[0590] The applicable conditions for each AI function supported by the target device.
[0591] Optionally, the information transmission device 1000 further includes:
[0592] A seventh receiving module is used to receive seventh information from the third device, wherein the seventh information includes model identification information or version information of the target model, and the seventh information is used to instruct the second device to send model file information or model storage information corresponding to the model identification information or version information of the target model to the target device.
[0593] Optionally, the first device includes at least one of a third-party service server, an in-network service server, an in-network core network element, a network management system device, a base station device, and a terminal device; or,
[0594] The second device includes a model publishing platform; or,
[0595] The third device includes a model control device; or,
[0596] The target device includes at least one of a network side device and a terminal device.
[0597] The information transmission device 1000 provided in the embodiment of the present application can implement each process implemented by the method embodiment shown in Figure 2 and achieve the same technical effect. To avoid repetition, it will not be repeated here.
[0598] Please refer to Figure 11. The information transmission device 1100 provided in this embodiment of the present application can be a device in the first device.
[0599] As shown in FIG11 , the information transmission device 1100 may include the following modules:
[0600] A second sending module 1101 is configured to send a first message to a second device, wherein the first message is used to register or publish a first model;
[0601] The second receiving module 1102 is configured to receive a second message from the second device, wherein the second message is a response message for registering or publishing the first model, and the second message carries first information, where the first information includes at least one of the following:
[0602] First indication information, used to indicate whether the first model passes the security authentication of the second device;
[0603] The security authentication certificate of the first model, or the token information of the first model passing the security authentication of the second device;
[0604] model identification information of the first model allocated by the second device;
[0605] Version information of the first model allocated by the second device.
[0606] Optionally, the first message carries second information, where the second information includes at least one of the following:
[0607] attribute information of the first model;
[0608] file information of the first model;
[0609] Storage information of the first model.
[0610] Optionally, the attribute information of the first model includes at least one of the following:
[0611] version information of the first model;
[0612] parameter information of the first model;
[0613] Activation conditions of the first model
[0614] Functions supported by the first model;
[0615] Producer information of the first model;
[0616] The consumer information of the first model.
[0617] Optionally, the information transmission device 1100 further includes:
[0618] an eighth sending module, configured to send third information to the target device, wherein the third information includes at least one of the following:
[0619] File information of the target model;
[0620] Storage information of the target model;
[0621] model identification information of the target model allocated by the second device;
[0622] Version information of the target model in the second device allocation;
[0623] Second indication information, used to indicate that the target model has passed the security authentication of the second device;
[0624] Activation conditions of the target model;
[0625] The security authentication certificate of the target model, or the token information that proves that the target model has passed the security authentication of the second device;
[0626] Wherein, the first model includes the target model.
[0627] Optionally, the eighth sending module is specifically configured to:
[0628] When the first device determines, based on the first information, that the target model passes the security authentication of the second device, third information is sent to the target device.
[0629] Optionally, the information transmission device 1100 further includes:
[0630] An eighth receiving module is configured to receive a fourth message from the target device, wherein the fourth message is used to request the model in the first device, and wherein the model in the first device includes the target model.
[0631] The information transmission device 1100 provided in the embodiment of the present application can implement each process implemented by the method embodiment shown in Figure 3 and achieve the same technical effect. To avoid repetition, it will not be repeated here.
[0632] Please refer to Figure 12. The information transmission device 1200 provided in this embodiment of the present application can be a device in a third device.
[0633] As shown in FIG12 , the information transmission device 1200 may include the following modules:
[0634] A third receiving module 1201 is configured to receive second capability information from a target device, where the second capability information is related to a model supported by the target device;
[0635] The third sending module 1202 is used to send a fifth message to the target device according to the second capability information, where the fifth message is used to trigger or activate a second model in the target device, wherein the models supported by the target device include the second model.
[0636] Optionally, the second capability information includes at least one of the following:
[0637] Model identification information of the models supported by the target device;
[0638] Version information corresponding to the model supported by the target device;
[0639] The security authentication certificate of the model supported by the target device, or the token information that the model supported by the target device has passed the security authentication of the second device.
[0640] Optionally, the information transmission device 1200 further includes:
[0641] A fourth determining module is configured to determine the second model according to the communication parameters corresponding to the target device and the second capability information.
[0642] Optionally, the information transmission device 1200 further includes:
[0643] a ninth sending module, configured to send a sixth message to the second device, where the sixth message includes at least one of the following:
[0644] Model identification information of the models supported by the target device;
[0645] Version information of the model supported by the target device;
[0646] a ninth receiving module, configured to receive sixth information from the second device, where the sixth information includes at least one of the following:
[0647] fifth indication information, used to indicate whether the model supported by the target device has passed the security authentication of the second device;
[0648] usage conditions corresponding to the model identification information or version information of the model supported by the target device;
[0649] The security authentication certificate of the model supported by the target device, or the token information of the model supported by the target device being securely authenticated by the second device.
[0650] Optionally, the third sending module 1202 is specifically configured to:
[0651] When it is determined according to the second capability information that the network environment of the target device meets the usage condition of the second model, a fifth message is sent to the target device.
[0652] Optionally, determining whether the network environment of the target device meets the usage condition of the second model includes at least one of the following:
[0653] determining that the current time matches a time parameter in the usage condition of the second model;
[0654] determining that the location information of the target device matches a location parameter in the usage condition of the second model;
[0655] It is determined that the channel of the target device matches the channel environment parameter in the usage condition of the second model.
[0656] Optionally, the fifth message includes at least one of the following:
[0657] model identification information of the second model;
[0658] Version information or version information of the second model.
[0659] Optionally, the information transmission device 1200 further includes:
[0660] a tenth receiving module, configured to receive first capability information from the target device, where the first capability information is used to indicate the AI capability of the target device;
[0661] A tenth sending module is used to send the first capability information to the second device, or the third device determines a target model from the first model based on the first capability information, wherein the target model includes a model applicable to the target device, and the first model comes from the first device and is registered or published through the second device.
[0662] Optionally, the first capability information includes at least one of the following:
[0663] Fourth indication information, used to indicate whether the target device supports the model-based AI function;
[0664] The type of AI functionality supported by the target device;
[0665] Function identification information of the AI function supported by the target device;
[0666] The applicable conditions for each AI function supported by the target device.
[0667] The information transmission device 1200 provided in the embodiment of the present application can implement each process implemented by the method embodiment shown in Figure 4 and achieve the same technical effect. To avoid repetition, it will not be repeated here.
[0668] Please refer to FIG. 13 . The information transmission device 1300 provided in the embodiment of the present application may be a device within the target device.
[0669] As shown in FIG13 , the information transmission device 1300 may include the following modules:
[0670] The fourth receiving module 1301 is configured to receive third information;
[0671] The first acquisition module 1302 is configured to acquire a target model according to the third information, where the target model includes at least one first model, which is from a first device and registered or published through a second device.
[0672] Optionally, the third information includes at least one of the following:
[0673] File information of the target model;
[0674] Storage information of the target model;
[0675] model identification information of the target model allocated by the second device;
[0676] version information of the target model allocated by the second device;
[0677] Second indication information, used to indicate that the target model has passed the security authentication of the second device;
[0678] activation conditions of the target model;
[0679] The security authentication certificate of the target model, or the token information that the target model passes the security authentication of the second device.
[0680] Optionally, the information transmission device 1300 further includes:
[0681] an eleventh sending module, configured to send second capability information to a third device, wherein the second capability information is related to a model supported by the target device;
[0682] An eleventh receiving module is configured to receive a fifth message from the third device, where the fifth message is used to trigger or activate the second model of the target device, where the target model includes the second model.
[0683] Optionally, the information transmission device 1300 further includes:
[0684] An operation module is used to perform a model inference operation based on the second model.
[0685] Optionally, the second capability information includes at least one of the following:
[0686] Model identification information of the models supported by the target device;
[0687] Version information corresponding to the model supported by the target device;
[0688] The security authentication certificate of the model supported by the target device, or the token information that the model supported by the target device has passed the security authentication of the second device.
[0689] Optionally, the fifth message includes at least one of the following:
[0690] model identification information of the second model;
[0691] Version information of the second model.
[0692] Optionally, the fourth receiving module 1301 is specifically configured to:
[0693] Receive third information from the first device or the second device.
[0694] Optionally, the information transmission device 1300 further includes:
[0695] a twelfth sending module, configured to send first capability information to a third device, where the first capability information is used to indicate the AI capability of the target device;
[0696] The fourth receiving module 1301 is specifically configured to:
[0697] Receive third information from the third device or the second device, where the third information includes the fifth information.
[0698] Optionally, the fifth information includes at least one of the following:
[0699] File information of the target model;
[0700] Storage information of the target model;
[0701] model identification information of the target model allocated by the second device;
[0702] version information of the target model allocated by the second device;
[0703] activation conditions of the target model;
[0704] Second indication information, used to indicate that the target model has passed the security authentication of the second device;
[0705] The security authentication certificate of the target model, or the token information of the second model passing the security authentication of the second device.
[0706] The information transmission device 1300 provided in the embodiment of the present application can implement each process implemented by the method embodiment shown in Figure 5 and achieve the same technical effect. To avoid repetition, it will not be repeated here.
[0707] The model determination method provided in the embodiment of the present application can be executed by a model determination device. In the embodiment of the present application, the model determination device provided in the embodiment of the present application is described by taking the execution of the model determination method by the model determination device as an example.
[0708] Please refer to FIG. 14 . The model determination device 1400 provided in the embodiment of the present application may be a device within a third device.
[0709] As shown in FIG14 , the model determination device 1400 may include the following modules:
[0710] A fifth receiving module 1401 is configured to receive first capability information from a target device, where the first capability information indicates an AI capability of the target device.
[0711] The first determining module 1402 is configured to determine a target model according to the first capability information, wherein the target model includes a model applicable to the target device.
[0712] Optionally, the first capability information includes at least one of the following:
[0713] Fourth indication information, used to indicate whether the target device supports the model-based AI function;
[0714] The type of AI functionality supported by the target device;
[0715] Function identification information of the AI function supported by the target device;
[0716] The applicable conditions for each AI function supported by the target device.
[0717] Optionally, the first determining module 1402 is specifically configured to perform at least one of the following:
[0718] In a case where the first capability information includes a type or function identification information of an AI function supported by the target device, determining a model corresponding to the type or function identification information of the AI function as a target model;
[0719] In a case where the first capability information includes an applicable condition for each AI function, determining a model whose activation condition matches the applicable condition for the AI function as a target model;
[0720] A model whose producer information or consumer information matches the type allocation code TAC or manufacturer information of the target device is determined as the target model.
[0721] Optionally, the model determining device 1400 further includes:
[0722] A thirteenth sending module is configured to send fifth information to the target device, where the fifth information includes at least one of the following:
[0723] File information of the target model;
[0724] Storage information of the target model;
[0725] model identification information of the target model allocated by the second device;
[0726] version information of the target model allocated by the second device;
[0727] activation conditions of the target model;
[0728] Second indication information, used to indicate that the target model has passed the security authentication of the second device;
[0729] The security authentication certificate of the target model, or the token information that the target model passes the security authentication of the second device.
[0730] Optionally, the first determining module 1402 includes:
[0731] a first sending unit, configured to send the first capability information to the second device;
[0732] a first receiving unit, configured to receive the fifth information from the second device;
[0733] A first determining unit is configured to determine the target model according to the fifth information.
[0734] Optionally, the model determining device 1400 further includes:
[0735] A fourteenth sending module is used to send seventh information to the second device, wherein the seventh information includes model identification information or version information of the target model, and the seventh information is used to instruct the second device to send model file information or model storage information corresponding to the model identification information or version information of the target model to the target device.
[0736] The model determination device 1400 provided in the embodiment of the present application can implement each process implemented by the method embodiment shown in Figure 6 and achieve the same technical effect. To avoid repetition, it will not be repeated here.
[0737] Please refer to FIG. 15 . The model determination device 1500 provided in the embodiment of the present application may be a device within the target device.
[0738] As shown in FIG15 , the model determination device 1500 may include the following modules:
[0739] A fifth sending module 1501 is configured to send first capability information to a third device, where the first capability information is used to indicate the AI capability of the target device;
[0740] The second acquisition module 1502 is configured to acquire a target model, wherein the target model includes a model applicable to the target device.
[0741] Optionally, the second obtaining module 1502 is specifically configured to:
[0742] A target model is obtained from the third device.
[0743] Optionally, the second obtaining module 1502 is specifically configured to:
[0744] A target model is acquired from a second device, wherein a model registered or published by the second device includes the target model.
[0745] Optionally, the second obtaining module 1502 is specifically configured to receive fifth information, where the fifth information includes at least one of the following:
[0746] File information of the target model;
[0747] Storage information of the target model;
[0748] model identification information of the target model allocated by the second device;
[0749] version information of the target model allocated by the second device;
[0750] activation conditions of the target model;
[0751] Second indication information, used to indicate that the target model has passed the security authentication of the second device;
[0752] The security authentication certificate of the target model, or the token information that the target model passes the security authentication of the second device.
[0753] Optionally, the first capability information includes at least one of the following:
[0754] Fourth indication information, used to indicate whether the target device supports the model-based AI function;
[0755] The type of AI functionality supported by the target device;
[0756] Function identification information of the AI function supported by the target device;
[0757] The applicable conditions for each AI function supported by the target device.
[0758] The model determination device 1500 provided in the embodiment of the present application can implement each process implemented by the method embodiment shown in Figure 7 and achieve the same technical effect. To avoid repetition, it will not be described here.
[0759] Please refer to FIG. 16 . The model determination device 1600 provided in the embodiment of the present application may be a device within the second device.
[0760] As shown in FIG16 , the model determination device 1600 may include the following modules:
[0761] The third acquisition module 1601 is configured to acquire first capability information, where the first capability information is used to indicate the AI capability of the target device;
[0762] The second determining module 1602 is configured to determine a target model from the first model according to the first capability information, wherein the target model includes a model applicable to the target device.
[0763] Optionally, the first capability information includes at least one of the following:
[0764] Fourth indication information, used to indicate whether the target device supports the model-based AI function;
[0765] The type of AI functionality supported by the target device;
[0766] Function identification information of the AI function supported by the target device;
[0767] The applicable conditions for each AI function supported by the target device.
[0768] Optionally, the second determining module 1602 is specifically configured to perform at least one of the following:
[0769] In a case where the first capability information includes a type or function identification information of an AI function supported by the target device, determining a first model corresponding to the type or function identification information of the AI function as a target model;
[0770] In a case where the first capability information includes an applicable condition for each AI function, determining a first model whose activation condition matches the applicable condition for the AI function as a target model;
[0771] The first model whose producer information or consumer information matches the type allocation code TAC or manufacturer information of the target device is determined as the target model.
[0772] Optionally, the third acquisition module 1601 is specifically configured to:
[0773] The first capability information is obtained from the third device.
[0774] Optionally, the model determining device 1600 further includes:
[0775] A fifteenth sending module is configured to send fifth information to at least one of the third device and the target device, where the fifth information includes at least one of the following:
[0776] File information of the target model;
[0777] Storage information of the target model;
[0778] model identification information of the target model allocated by the second device;
[0779] version information of the target model allocated by the second device;
[0780] activation conditions of the target model;
[0781] Second indication information, used to indicate that the target model has passed the security authentication of the second device;
[0782] The security authentication certificate of the target model, or the token information that the target model passes the security authentication of the second device.
[0783] The model determination device 1600 provided in the embodiment of the present application can implement each process implemented by the method embodiment shown in Figure 8 and achieve the same technical effect. To avoid repetition, it will not be repeated here.
[0784] The information transmission device or model determination device in the embodiments of the present application can be an electronic device, such as an electronic device with an operating system, or a component in an electronic device, such as an integrated circuit or chip. The electronic device can be a terminal or a network-side device. For example, the terminal can include but is not limited to the types of terminal 11 listed above, and the network-side device can include but is not limited to the types of access network devices or core network devices listed above, etc., which are not specifically limited in the embodiments of the present application.
[0785] As shown in Figure 17, an embodiment of the present application also provides a communication device 1700, including a processor 1701 and a memory 1702, and the memory 1702 stores a program or instruction that can be run on the processor 1701. When the program or instruction is executed by the processor 1701, the various steps of the above-mentioned information transmission method or model determination method embodiment are implemented, and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.
[0786] The present application also provides a terminal including a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is configured to execute a program or instruction to implement the steps of the method embodiment shown in Figure 5 or Figure 7. This terminal embodiment corresponds to the above-mentioned terminal-side method embodiment, and each implementation process and implementation method of the above-mentioned method embodiment can be applied to this terminal embodiment and can achieve the same technical effect. Specifically, Figure 18 is a schematic diagram of the hardware structure of a terminal implementing an embodiment of the present application.
[0787] The terminal 1800 includes but is not limited to: a radio frequency unit 1801, a network module 1802, an audio output unit 1803, an input unit 1804, a sensor 1805, a display unit 1806, a user input unit 1807, an interface unit 1808, a memory 1809 and at least some of the components of the processor 1810.
[0788] Those skilled in the art will appreciate that the terminal 1800 may also include a power supply (such as a battery) to power various components. The power supply may be logically connected to the processor 1810 via a power management system, thereby enabling the power management system to manage charging, discharging, and power consumption. The terminal structure shown in FIG18 does not limit the terminal. The terminal may include more or fewer components than shown, or combine certain components, or have different component arrangements, which will not be described in detail here.
[0789] It should be understood that in an embodiment of the present application, the input unit 1804 may include a graphics processing unit (GPU) 18041 and a microphone 18042, and the graphics processor 18041 processes the image data of a static picture or video obtained by an image capture device (such as a camera) in a video capture mode or an image capture mode. The display unit 1806 may include a display panel 18061, and the display panel 18061 may be configured in the form of a liquid crystal display, an organic light emitting diode, etc. The user input unit 1807 includes a touch panel 18071 and at least one of other input devices 18072. The touch panel 18071 is also called a touch screen. The touch panel 18071 may include two parts: a touch detection device and a touch controller. Other input devices 18072 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 repeated here.
[0790] In the embodiment of the present application, after receiving downlink data from a network-side device, the RF unit 1801 may transmit the data to the processor 1810 for processing. Furthermore, the RF unit 1801 may send uplink data to the network-side device. Typically, the RF unit 1801 includes, but is not limited to, an antenna, an amplifier, a transceiver, a coupler, a low-noise amplifier, a duplexer, and the like.
[0791] The memory 1809 can be used to store software programs or instructions and various data. The memory 1809 may mainly include a first storage area for storing programs or instructions and a second storage area for storing data, wherein the first storage area may store an operating system, applications or instructions required for at least one function (such as a sound playback function, an image playback function, etc.). In addition, the memory 1809 may include a volatile memory or a 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. Volatile memory can be random access memory (RAM), static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDRSDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM), and direct RAM bus random access memory (DRRAM). The memory 1809 in the embodiment of the present application includes but is not limited to these and any other suitable types of memory.
[0792] Processor 1810 may include one or more processing units. Optionally, processor 1810 integrates an application processor and a modem processor. The application processor primarily handles operations related to the operating system, user interface, and application programs, while the modem processor primarily processes wireless communication signals, such as a baseband processor. It is understood that the modem processor may not be integrated into processor 1810.
[0793] In one implementation, the radio frequency unit 1801 is configured to receive third information;
[0794] Processor 1810 is configured to obtain a target model according to the third information, where the target model includes at least one first model, where the first model comes from a first device and is registered or published through a second device.
[0795] Optionally, the third information includes at least one of the following:
[0796] File information of the target model;
[0797] Storage information of the target model;
[0798] model identification information of the target model allocated by the second device;
[0799] version information of the target model allocated by the second device;
[0800] Second indication information, used to indicate that the target model has passed the security authentication of the second device;
[0801] activation conditions of the target model;
[0802] The security authentication certificate of the target model, or the token information that the target model passes the security authentication of the second device.
[0803] Optionally, the radio frequency unit 1801 is further configured to send second capability information to a third device, where the second capability information is related to a model supported by the target device;
[0804] The radio frequency unit 1801 is further configured to receive a fifth message from the third device, where the fifth message is configured to trigger or activate the second model of the target device, where the target model includes the second model.
[0805] Optionally, the processor 1810 is further configured to perform a model inference operation based on the second model.
[0806] Optionally, the second capability information includes at least one of the following:
[0807] Model identification information of the models supported by the target device;
[0808] Version information corresponding to the model supported by the target device;
[0809] The security authentication certificate of the model supported by the target device, or the token information that the model supported by the target device has passed the security authentication of the second device.
[0810] Optionally, the fifth message includes at least one of the following:
[0811] model identification information of the second model;
[0812] Version information of the second model.
[0813] Optionally, the receiving of the third information performed by the radio frequency unit 1801 includes:
[0814] Receive third information from the first device or the second device.
[0815] Optionally, before receiving the third information, the radio frequency unit 1801 is further configured to send first capability information to the third device, where the first capability information is used to indicate the AI capability of the target device;
[0816] The receiving of the third information performed by the radio frequency unit 1801 includes:
[0817] Receive third information from the third device or the second device, where the third information includes the fifth information.
[0818] Optionally, the fifth information includes at least one of the following:
[0819] File information of the target model;
[0820] Storage information of the target model;
[0821] model identification information of the target model allocated by the second device;
[0822] version information of the target model allocated by the second device;
[0823] activation conditions of the target model;
[0824] Second indication information, used to indicate that the target model has passed the security authentication of the second device;
[0825] The security authentication certificate of the target model, or the token information of the second model passing the security authentication of the second device.
[0826] It can be understood that the implementation process of each implementation method mentioned in this embodiment can refer to the relevant description of the information transmission method embodiment shown in Figure 5, and achieve the same or corresponding technical effects. To avoid repetition, it will not be repeated here.
[0827] In another embodiment, the radio frequency unit 1801 is configured to send first capability information to a third device, where the first capability information is used to indicate the AI capability of the target device;
[0828] The processor 1810 is configured to obtain a target model, where the target model includes a model applicable to the target device.
[0829] Optionally, the acquiring of the target model performed by the processor 1810 includes:
[0830] The target model is obtained from the third device through the radio frequency unit 1801.
[0831] Optionally, the acquiring of the target model performed by the processor 1810 includes:
[0832] The target model is acquired from the second device through the radio frequency unit 1801 , wherein the model registered or published by the second device includes the target model.
[0833] Optionally, the acquiring of the target model performed by the processor 1810 includes:
[0834] Fifth information is received by the radio frequency unit 1801, where the fifth information includes at least one of the following:
[0835] File information of the target model;
[0836] Storage information of the target model;
[0837] model identification information of the target model allocated by the second device;
[0838] version information of the target model allocated by the second device;
[0839] activation conditions of the target model;
[0840] Second indication information, used to indicate that the target model has passed the security authentication of the second device;
[0841] The security authentication certificate of the target model, or the token information that the target model passes the security authentication of the second device.
[0842] Optionally, the first capability information includes at least one of the following:
[0843] Fourth indication information, used to indicate whether the target device supports the model-based AI function;
[0844] The type of AI functionality supported by the target device;
[0845] Function identification information of the AI function supported by the target device;
[0846] The applicable conditions for each AI function supported by the target device.
[0847] It can be understood that the implementation process of each implementation method mentioned in this embodiment can refer to the relevant description of the model determination method embodiment shown in Figure 7, and achieve the same or corresponding technical effects. To avoid repetition, it will not be repeated here.
[0848] An embodiment of the present application further provides a network-side device, including a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is configured to execute a program or instruction to implement the steps of the method embodiment shown in at least one of Figures 2 to 8. This network-side device embodiment corresponds to the aforementioned network-side device method embodiment, and each implementation process and implementation method of the aforementioned method embodiment are applicable to this network-side device embodiment and can achieve the same technical effects.
[0849] Specifically, an embodiment of the present application also provides a network-side device. As shown in Figure 19, the network-side device 1900 includes: an antenna 1901, a radio frequency device 1902, a baseband device 1903, a processor 1904, and a memory 1905. Antenna 1901 is connected to radio frequency device 1902. In the uplink direction, radio frequency device 1902 receives information via antenna 1901 and sends the received information to baseband device 1903 for processing. In the downlink direction, baseband device 1903 processes the information to be transmitted and sends it to radio frequency device 1902. Radio frequency device 1902 processes the received information and sends it through antenna 1901.
[0850] The method executed by the network-side device in the above embodiment may be implemented in the baseband device 1903 , which includes a baseband processor.
[0851] The baseband device 1903 may, for example, include at least one baseband board, on which multiple chips are arranged, as shown in Figure 19, one of the chips is, for example, a baseband processor, which is connected to the memory 1905 through a bus interface to call the program in the memory 1905 and execute the network device operations shown in the above method embodiment.
[0852] The network side device may further include a network interface 1906 , which is, for example, a Common Public Radio Interface (CPRI).
[0853] Specifically, the network side device 1900 of the embodiment of the present application also includes: instructions or programs stored in the memory 1905 and executable on the processor 1904. The processor 1904 calls the instructions or programs in the memory 1905 to execute the method executed by each module shown in at least one of Figures 10 to 16, and achieves the same technical effect. To avoid repetition, it will not be elaborated here.
[0854] Specifically, the embodiment of the present application further provides a network side device. As shown in FIG20 , the network side device 2000 includes: a processor 2001, a network interface 2002, and a memory 2003. The network interface 2002 is, for example, a Common Public Radio Interface (CPRI).
[0855] Specifically, the network side device 2000 of the embodiment of the present application also includes: instructions or programs stored in the memory 2003 and can be run on the processor 2001. The processor 2001 calls the instructions or programs in the memory 2003 to execute the method executed by each module as shown in at least one item in Figures 10 to 16, and achieves the same technical effect. To avoid repetition, it will not be repeated here.
[0856] An embodiment of the present application also provides a readable storage medium, on which a program or instruction is stored. When the program or instruction is executed by a processor, each process of the method embodiment shown in at least one of Figures 2 to 8 is implemented, and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.
[0857] 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 disk. In some examples, the readable storage medium may be a non-transitory readable storage medium.
[0858] An embodiment of the present application further provides a chip, which includes a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is used to run programs or instructions to implement the various processes of the method embodiments shown in at least one of Figures 2 to 8, and can achieve the same technical effect. To avoid repetition, it will not be repeated here.
[0859] It should be understood that the chip mentioned in the embodiments of the present application can also be called a system-level chip, a system chip, a chip system or a system-on-chip chip, etc.
[0860] An embodiment of the present application further provides a computer program / program product, which is stored in a storage medium and is executed by at least one processor to implement the various processes of the method embodiments shown in at least one of Figures 2 to 8, and can achieve the same technical effects. To avoid repetition, they are not described here.
[0861] An embodiment of the present application also provides a communication system, including: a first device, a second device, a third device and a target device, wherein the first device can be used to execute the steps of the method embodiment shown in Figure 3, the second device can be used to execute the steps of the method embodiment shown in Figure 2 or Figure 8, the third device can be used to execute the steps of the method embodiment shown in Figure 4 or Figure 6, and the target device can be used to execute the steps of the method embodiment shown in Figure 5 or Figure 7.
[0862] It should be noted that, in this article, the terms "comprise", "include" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the presence of other identical elements in the process, method, article or device comprising the element. In addition, it should be pointed out that the scope of the methods and devices in the embodiments of the present application is not limited to performing functions in the order shown or discussed, and may also include performing functions in a substantially simultaneous manner or in the opposite order according to the functions involved. For example, the described method may be performed in an order different from that described, and various steps may also be added, omitted or combined. In addition, the features described with reference to certain examples may be combined in other examples.
[0863] Through the description of the above embodiments, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of a computer software product plus a necessary general-purpose hardware platform, or of course, by hardware. The computer software product is stored in a storage medium (such as ROM, RAM, magnetic disk, optical disk, etc.) and includes a number of instructions for enabling a terminal or network-side device to execute the methods described in each embodiment of the present application.
[0864] The embodiments of the present application are described above in conjunction with the accompanying drawings, but the present application is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the guidance of this application, ordinary technicians in this field can also make many forms of implementation methods without departing from the purpose of this application and the scope of protection of the claims. These implementation methods are all within the protection of this application.
Claims
1. An information transmission method, comprising: The second device receives a first message from the first device, wherein the first message is used to register or publish a first model; The second device sends a second message to the first device, wherein the second message is a response message for registering or publishing the first model, and the second message carries first information, and the first information includes at least one of the following: first indication information, used to indicate whether the first model passes the security authentication of the second device; The security authentication certificate of the first model, or the token information of the first model being securely authenticated by the second device; model identification information of the first model allocated by the second device; The version information of the first model allocated by the second device.
2. The method according to claim 1, wherein: The first message carries second information, where the second information includes at least one of the following: attribute information of the first model; File information of the first model; Storage information of the first model.
3. The method according to claim 2, wherein: The attribute information of the first model includes at least one of the following: version information of the first model; parameter information of the first model; activation conditions of the first model; Functions supported by the first model; Producer information of the first model; The first model includes consumer information.
4. The method according to any one of claims 1 to 3, further comprising: The second device sends third information to the target device, wherein the third information includes at least one of the following: File information of the target model; Storage information of the target model; model identification information of the target model allocated by the second device; version information of the target model allocated by the second device; Second indication information, used to indicate that the target model has passed the security authentication of the second device; Activation conditions of the target model; The security authentication certificate of the target model, or the token information that the target model has passed the security authentication of the second device; Wherein, the first model includes the target model.
5. The method according to claim 4, further comprising: The second device receives a third message from a third device, wherein the third message includes at least one of the following: Model identification information of the target model; Version information of the target model; The security authentication certificate of the target model, or the token information of the target model being securely authenticated by the second device; The second device sends fourth information to the third device, where the fourth information includes at least one of the following: third indication information, used to indicate whether the target model has passed the security authentication of the second device; The activation conditions of the target model.
6. The method according to claim 4 or 5, further comprising: The second device acquires first capability information, where the first capability information is used to indicate the AI capability of the target device; The second device determines the target model according to the first capability information and the second information.
7. The method according to claim 6, wherein: The second device acquires the first capability information, including: The second device obtains first capability information from the third device.
8. The method according to claim 6 or 7, wherein: The first capability information includes at least one of the following: Fourth indication information, used to indicate whether the target device supports the model-based AI function; The type of AI functions supported by the target device; Function identification information of the AI function supported by the target device; Applicable conditions for each AI function supported by the target device.
9. The method according to any one of claims 4 to 8, wherein: Before the second device sends the third information to the target device, the method further includes: The second device receives seventh information from the third device, wherein the seventh information includes model identification information or version information of the target model, and the seventh information is used to instruct the second device to send model file information or model storage information corresponding to the model identification information or version information of the target model to the target device.
10. The method according to any one of claims 1 to 9, wherein: The first device includes at least one of a third-party service server, a service server within the network, a core network element within the network, a network management system device, a base station device, and a terminal device; or, The second device includes a model publishing platform; or, The third device includes a model control device; or, The target device includes at least one of a network side device and a terminal device.
11. A method for transmitting information, wherein: include: The first device sends a first message to the second device, wherein the first message is used to register or publish a first model; The first device receives a second message from the second device, wherein the second message is a response message for registering or publishing the first model, and the second message carries first information, and the first information includes at least one of the following: first indication information, used to indicate whether the first model passes the security authentication of the second device; The security authentication certificate of the first model, or the token information of the first model being securely authenticated by the second device; model identification information of the first model allocated by the second device; The version information of the first model allocated by the second device.
12. The method according to claim 11, wherein: The first message carries second information, where the second information includes at least one of the following: attribute information of the first model; File information of the first model; Storage information of the first model.
13. The method according to claim 12, wherein: The attribute information of the first model includes at least one of the following: version information of the first model; parameter information of the first model; The activation condition of the first model Functions supported by the first model; Producer information of the first model; The first model includes consumer information.
14. The method according to any one of claims 11 to 13, further comprising: The first device sends third information to the target device, wherein the third information includes at least one of the following: File information of the target model; Storage information of the target model; model identification information of the target model allocated by the second device; version information of the target model in the second device allocation; Second indication information, used to indicate that the target model has passed the security authentication of the second device; Activation conditions of the target model; The security authentication certificate of the target model, or the token information that the target model has passed the security authentication of the second device; Wherein, the first model includes the target model.
15. The method according to claim 14, wherein: The first device sends third information to the target device, including: When the first device determines, based on the first information, that the target model has passed the security authentication of the second device, the first device sends third information to the target device.
16. The method according to claim 15, wherein: Before the first device sends the third information to the target device, the method further includes: The first device receives a fourth message from the target device, wherein the fourth message is used to request a model in the first device, wherein the model in the first device includes the target model.
17. An information transmission method, comprising: The third device receives second capability information from the target device, where the second capability information is related to a model supported by the target device; The third device sends a fifth message to the target device according to the second capability information, where the fifth message is used to trigger or activate a second model in the target device, wherein the models supported by the target device include the second model.
18. The method according to claim 17, wherein: The second capability information includes at least one of the following: Model identification information of the models supported by the target device; Version information corresponding to the model supported by the target device; The security authentication certificate of the model supported by the target device, or the token information of the model supported by the target device being securely authenticated by the second device.
19. The method according to claim 17 or 18, further comprising: The third device determines the second model according to the communication parameters corresponding to the target device and the second capability information.
20. The method according to any one of claims 17 to 19, further comprising: The third device sends a sixth message to the second device, where the sixth message includes at least one of the following: Model identification information of the models supported by the target device; Version information of the model supported by the target device; The third device receives sixth information from the second device, where the sixth information includes at least one of the following: fifth indication information, used to indicate whether the model supported by the target device has passed the security authentication of the second device; The usage conditions corresponding to the model identification information or version information of the model supported by the target device; The security authentication certificate of the model supported by the target device, or the token information of the model supported by the target device through security authentication of the second device.
21. The method according to any one of claims 17 to 20, wherein: The third device sends a fifth message to the target device according to the second capability information, including: When the third device determines, according to the second capability information, that the network environment of the target device meets the usage condition of the second model, the third device sends a fifth message to the target device.
22. The method according to claim 21, wherein: Determining that the network environment of the target device meets the use condition of the second model includes at least one of the following: determining that the current time matches a time parameter in the usage conditions of the second model; Determining that the location information of the target device matches the location parameter in the usage condition of the second model; It is determined that a channel of the target device matches a channel environment parameter in the usage condition of the second model.
23. The method according to any one of claims 17 to 22, wherein: The fifth message includes at least one of the following: model identification information of the second model; Version information or version information of the second model.
24. The method according to any one of claims 17 to 23, further comprising: The third device receives first capability information from the target device, where the first capability information is used to indicate the AI capability of the target device; The third device sends the first capability information to the second device, or the third device determines a target model from a first model based on the first capability information, wherein the target model includes a model applicable to the target device, and the first model comes from the first device and is registered or published through the second device.
25. The method according to claim 24, wherein: The first capability information includes at least one of the following: Fourth indication information, used to indicate whether the target device supports the model-based AI function; The type of AI functions supported by the target device; Function identification information of the AI function supported by the target device; Applicable conditions for each AI function supported by the target device.
26. A method for transmitting information, comprising: The target device receives the third information; The target device acquires a target model according to the third information, where the target model includes at least one first model, where the first model comes from a first device and is registered or published through a second device.
27. The method according to claim 26, wherein: The third information includes at least one of the following: File information of the target model; Storage information of the target model; Model identification information of the target model allocated by the second device; version information of the target model allocated by the second device; Second indication information, used to indicate that the target model has passed the security authentication of the second device; activation conditions of the target model; The security authentication certificate of the target model, or the token information that the target model has passed the security authentication of the second device.
28. The method according to claim 26 or 27, further comprising: The target device sends second capability information to a third device, wherein the second capability information is related to a model supported by the target device; The target device receives a fifth message from the third device, where the fifth message is used to trigger or activate a second model of the target device, where the target model includes the second model.
29. The method according to claim 28, further comprising: The target device performs a model inference operation based on the second model.
30. The method according to claim 28 or 29, wherein: The second capability information includes at least one of the following: Model identification information of the models supported by the target device; Version information corresponding to the model supported by the target device; The security authentication certificate of the model supported by the target device, or the token information of the model supported by the target device through security authentication of the second device.
31. The method according to any one of claims 28 to 30, wherein: The fifth message includes at least one of the following: model identification information of the second model; Version information of the second model.
32. The method according to any one of claims 26 to 31, wherein: The target device receives third information, including: The target device receives third information from the first device or the second device.
33. The method according to any one of claims 26 to 32, wherein: Before the target device receives the third information, the method further includes: The target device sends first capability information to a third device, where the first capability information is used to indicate the AI capability of the target device; The target device receives third information, including: The target device receives third information from the third device or the second device, where the third information includes fifth information.
34. The method of claim 33, wherein: The fifth information includes at least one of the following: File information of the target model; Storage information of the target model; model identification information of the target model allocated by the second device; version information of the target model allocated by the second device; activation conditions of the target model; Second indication information, used to indicate that the target model has passed the security authentication of the second device; The security authentication certificate of the target model, or the token information of the second model passing the security authentication of the second device.
35. A model determination method, comprising: The third device receives first capability information from the target device, where the first capability information is used to indicate the AI capability of the target device; The third device determines a target model according to the first capability information, wherein the target model includes a model applicable to the target device.
36. The method of claim 35, wherein: The first capability information includes at least one of the following: Fourth indication information, used to indicate whether the target device supports the model-based AI function; The type of AI functions supported by the target device; Function identification information of the AI function supported by the target device; Applicable conditions for each AI function supported by the target device.
37. The method according to claim 35 or 36, wherein: The third device determines a target model according to the first capability information, including at least one of the following: In a case where the first capability information includes a type or function identification information of an AI function supported by the target device, the third device determines a model corresponding to the type or function identification information of the AI function as a target model; In a case where the first capability information includes an applicable condition for each AI function, the third device determines a model whose activation condition matches the applicable condition for the AI function as a target model; The third device determines a model whose producer information or consumer information matches the type allocation code TAC or vendor information of the target device as a target model.
38. The method according to any one of claims 35 to 37, further comprising: The third device sends fifth information to the target device, where the fifth information includes at least one of the following: File information of the target model; Storage information of the target model; Model identification information of the target model allocated by the second device; version information of the target model allocated by the second device; activation conditions of the target model; Second indication information, used to indicate that the target model has passed the security authentication of the second device; The security authentication certificate of the target model, or the token information that the target model has passed the security authentication of the second device.
39. The method according to any one of claims 35 to 38, wherein: The third device determines a target model according to the first capability information, including: The third device sends the first capability information to the second device; The third device receives the fifth information from the second device; The third device determines the target model according to the fifth information.
40. The method according to any one of claims 35 to 38, wherein: After the third device determines the target model according to the first capability information, the method further includes: The third device sends seventh information to the second device, wherein the seventh information includes model identification information or version information of the target model, and the seventh information is used to instruct the second device to send model file information or model storage information corresponding to the model identification information or version information of the target model to the target device.
41. A model determination method, comprising: The target device sends first capability information to the third device, where the first capability information is used to indicate the AI capability of the target device; The target device acquires a target model, wherein the target model includes a model applicable to the target device.
42. The method according to claim 41, wherein: The target device acquires a target model, including: The target device acquires a target model from the third device.
43. The method of claim 41, wherein: The target device acquires a target model, including: The target device acquires a target model from a second device, wherein a model registered or published by the second device includes the target model.
44. A method according to any one of claims 41 to 43, wherein: The target device acquires a target model, including: The target device receives fifth information, where the fifth information includes at least one of the following: File information of the target model; Storage information of the target model; model identification information of the target model allocated by the second device; version information of the target model allocated by the second device; activation conditions of the target model; Second indication information, used to indicate that the target model has passed the security authentication of the second device; The security authentication certificate of the target model, or the token information that the target model has passed the security authentication of the second device.
45. The method according to any one of claims 41 to 44, wherein: The first capability information includes at least one of the following: Fourth indication information, used to indicate whether the target device supports the model-based AI function; The type of AI functions supported by the target device; Function identification information of the AI function supported by the target device; Applicable conditions for each AI function supported by the target device.
46. A model determination method, comprising: The second device acquires first capability information, where the first capability information is used to indicate the AI capability of the target device; The second device determines a target model from the first model according to the first capability information, wherein the target model includes a model applicable to the target device.
47. The method of claim 46, wherein: The first capability information includes at least one of the following: Fourth indication information, used to indicate whether the target device supports the model-based AI function; The type of AI functions supported by the target device; Function identification information of the AI function supported by the target device; Applicable conditions for each AI function supported by the target device.
48. The method according to claim 46 or 47, wherein: The second device determines, according to the first capability information, a target model from the first model, including at least one of the following: In a case where the first capability information includes a type or function identification information of an AI function supported by the target device, the second device determines a first model corresponding to the type or function identification information of the AI function as a target model; In a case where the first capability information includes an applicable condition for each AI function, the second device determines a first model whose activation condition matches the applicable condition for the AI function as a target model; The second device determines, as the target model, a first model whose producer information or consumer information matches the type allocation code TAC or the vendor information of the target device.
49. The method according to any one of claims 46 to 48, wherein: The second device acquires the first capability information, including: The second device obtains first capability information from the third device.
50. The method according to any one of claims 46 to 49, further comprising: The second device sends fifth information to at least one of the third device and the target device, where the fifth information includes at least one of the following: File information of the target model; Storage information of the target model; model identification information of the target model allocated by the second device; version information of the target model allocated by the second device; activation conditions of the target model; Second indication information, used to indicate that the target model has passed the security authentication of the second device; The security authentication certificate of the target model, or the token information that the target model has passed the security authentication of the second device.
51. An information transmission device, comprising: A first receiving module, configured to receive a first message from a first device, wherein the first message is used to register or publish a first model; A first sending module is configured to send a second message to the first device, wherein the second message is a response message for registering or publishing the first model, and the second message carries first information, and the first information includes at least one of the following: first indication information, used to indicate whether the first model passes the security authentication of the second device; The security authentication certificate of the first model, or the token information of the first model being securely authenticated by the second device; model identification information of the first model allocated by the second device; The version information of the first model allocated by the second device.
52. An information transmission device, comprising: A second sending module, configured to send a first message to a second device, wherein the first message is used to register or publish a first model; A second receiving module is configured to receive a second message from the second device, wherein the second message is a response message for registering or publishing the first model, and the second message carries first information, and the first information includes at least one of the following: first indication information, used to indicate whether the first model passes the security authentication of the second device; The security authentication certificate of the first model, or the token of the first model being securely authenticated by the second device information; model identification information of the first model allocated by the second device; The version information of the first model allocated by the second device.
53. An information transmission device, comprising: a third receiving module, configured to receive second capability information from a target device, wherein the second capability information is related to a model supported by the target device; The third sending module is used to send a fifth message to the target device according to the second capability information, wherein the fifth message is used to trigger or activate the second model in the target device, wherein the models supported by the target device include the second model.
54. An information transmission device, comprising: A fourth receiving module, used for receiving third information; The first acquisition module is used to acquire a target model according to the third information, where the target model includes at least one first model, where the first model comes from a first device and is registered or published through a second device.
55. A model determination device, comprising: a fifth receiving module, configured to receive first capability information from a target device, where the first capability information is used to indicate an AI capability of the target device; The first determination module is used to determine a target model according to the first capability information, wherein the target model includes a model applicable to the target device.
56. A model determination device, comprising: A fifth sending module, configured to send first capability information to a third device, where the first capability information is used to indicate the AI capability of the target device; The second acquisition module is used to acquire a target model, wherein the target model includes a model applicable to the target device.
57. A model determination device, comprising: A third acquisition module, used to acquire first capability information, where the first capability information is used to indicate the AI capability of the target device; The second determination module is used to determine a target model from the first model according to the first capability information, wherein the target model includes a model applicable to the target device.
58. A communication device, comprising a processor and a memory, wherein the memory stores programs or instructions that can be run on the processor, and when the programs or instructions are executed by the processor, the steps of the information transmission method described in any one of claims 1 to 34 are implemented, or the steps of the model determination method described in any one of claims 35 to 50 are implemented.
59. A readable storage medium storing a program or instruction, wherein the program or instruction, when executed by a processor, implements the steps of the information transmission method as described in any one of claims 1 to 34, or implements the steps of the model determination method as described in any one of claims 35 to 50.
Citation Information
Patent Citations
Network entity for determining a model for digitally analyzing input data
US20220337487A1
Machine learning model configuration in wireless networks
US20220400373A1
Entities and methods for trained data model selection in 5g mobile networks
WO2022174362A1
Artificial intelligence ai model transmission method and apparatus
WO2023020516A1
Model request method, model request processing method and related device
WO2023066288A1
