AI Model Information Transmission Method and Communication Device

Abstract

This application discloses an AI model information transmission method, apparatus, and device, belonging to the field of communication technologies. The AI model information transmission method according to the embodiments of this application includes a first communication device transmitting first AI model information to a second communication device, where the first AI model information is used to indicate a first AI model and / or related information of the first AI model. The first AI model is an AI model stored in a terminal. Here, the first communication device is the terminal, the second communication device is the communication counterpart of the terminal, or the first communication device is the source cell for the terminal's handover, the second communication device is the target cell for the terminal's handover, or the first communication device is the cell with access history in the RRC recovery process of the terminal, and the second communication device is the new access cell in the RRC recovery process of the terminal.

Description

Technical Field

[0001] (Cross - reference to Related Applications) This application claims the priority of a Chinese patent application filed on July 12, 2022, with the application number 202210822805.9 and the invention title "AI Model Information Transmission Method, Apparatus, and Device", and all of its content is incorporated herein by reference.

[0002] This application belongs to the field of communication technologies, and specifically relates to an AI model information transmission method, apparatus, and device.

Background Art

[0003] Artificial Intelligence (AI) is currently widely applied in various fields. Integrating AI into communication networks to significantly improve technical indicators such as throughput, latency, and user capacity is an important optimization direction for future communication networks.

[0004] The AI model inference function is deployed on the terminal. The terminal may preset or store the AI model in advance, thereby reducing the interaction of the AI model between the terminal and the network. However, when the network side or the communication partner side is unknown about the related information of the AI model preset or stored in the terminal, the network side or the communication partner side cannot perform appropriate management such as configuration, update, activation, de - activation, etc. on the AI model, and there may be a possibility of repeatedly configuring the same model or models with the same function on the terminal, resulting in a decrease in the management efficiency of the AI model and waste of resources.

Summary of the Invention

Problems to be Solved by the Invention

[0005] Embodiments of this application provide an AI model information transmission method, apparatus, and device that can solve the problem of the decrease in the management efficiency of the AI model and waste of resources.

Means for Solving the Problems

[0006] According to a first aspect, there is provided an AI model information transmission method, the method including: a first communication device transmits first AI model information to a second communication device, the first AI model information being used to indicate a first AI model and / or related information of the first AI model, the first AI model being an AI model stored in a terminal; wherein the first communication device is the terminal, the second communication device is a communication partner of the terminal, or the first communication device is a source cell for handover of the terminal, the second communication device is a target cell for handover of the terminal, or the first communication device is a cell with an access history in an RRC recovery process of the terminal, the second communication device is a new access cell in the RRC recovery process of the terminal.

[0007] According to a second aspect, there is provided an AI model information transmission method, the method including: a second communication device receives first AI model information from a first communication device, the first AI model information being used to indicate a first AI model and / or related information of the first AI model, the first AI model being an AI model stored in a terminal; wherein the first communication device is the terminal, the second communication device is a communication partner of the terminal, or the first communication device is a source cell for handover of the terminal, the second communication device is a target cell for handover of the terminal, or the first communication device is a cell with an access history in an RRC recovery process of the terminal, the second communication device is a new access cell in the RRC recovery process of the terminal.

[0008] According to a third aspect, there is provided an AI model information transmission apparatus, the apparatus including: A first transmission module for transmitting first AI model information to a second communication device, wherein the first AI model information is used to indicate a first AI model and / or related information of the first AI model, and the first AI model is an AI model stored in a terminal, wherein the first communication device is the terminal, the second communication device is a communication partner of the terminal, or the first communication device is a source cell for switching of the terminal, the second communication device is a target cell for switching of the terminal, or the first communication device is a cell with an access history in an RRC recovery process of the terminal, and the second communication device is a new access cell in the RRC recovery process of the terminal.

[0009] According to a fourth aspect, an AI model information transmission device is provided, and this device includes a first reception module for receiving first AI model information from a first communication device, wherein the first AI model information is used to indicate a first AI model and / or related information of the first AI model, and the first AI model is an AI model stored in a terminal, wherein the first communication device is the terminal, the second communication device is a communication partner of the terminal, or the first communication device is a source cell for switching of the terminal, the second communication device is a target cell for switching of the terminal, or the first communication device is a cell with an access history in an RRC recovery process of the terminal, and the second communication device is a new access cell in the RRC recovery process of the terminal.

[0010] According to a fifth aspect, a first communication device including a processor and a memory is provided, the memory stores a program or instruction that can run on the processor, and when the program or instruction is executed by the processor, the steps of the method described in the first aspect are realized.

[0011] According to a sixth aspect, a first communication device including a processor and a communication interface is provided, where the communication interface is used to transmit first AI model information to a second communication device, and the first AI model information is used to indicate a first AI model and / or related information of the first AI model. The first AI model is an AI model stored in a terminal, where the first communication device is the terminal, the second communication device is a communication partner of the terminal, or the first communication device is a source cell for switching of the terminal, the second communication device is a target cell for switching of the terminal, or the first communication device is a cell with an access history in an RRC recovery process of the terminal, and the second communication device is a new access cell in the RRC recovery process of the terminal.

[0012] According to a seventh aspect, a second communication device including a processor and a memory is provided. The memory stores a program or instruction that can run on the processor. When the program or instruction is executed by the processor, the steps of the method described in the second aspect are realized.

[0013] According to an eighth aspect, a second communication device including a processor and a communication interface is provided, where the communication interface is used to receive first AI model information from a first communication device. The first AI model information is used to indicate a first AI model and / or related information of the first AI model. The first AI model is an AI model stored in a terminal, where the first communication device is the terminal, the second communication device is a communication partner of the terminal, or the first communication device is a source cell for switching of the terminal, the second communication device is a target cell for switching of the terminal, or The first communication device is a cell with access history in the RRC recovery process of the terminal, and the second communication device is a new access cell in the RRC recovery process of the terminal.

[0014] According to a ninth aspect, there is further provided an AI model information transmission system including a first communication device and a second communication device. The first communication device may be used to execute the steps of the AI model information transmission method described in the first aspect, and the second communication device may be used to execute the steps of the AI model information transmission method described in the second aspect.

[0015] According to a tenth aspect, there is provided a readable storage medium, in 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 realized, or the steps of the method described in the second aspect are realized.

[0016] According to an eleventh aspect, there is provided a chip, which includes a processor and a communication interface. The communication interface is coupled to the processor, and the processor runs a program or instruction and is used to realize the method described in the first aspect or the method described in the second aspect.

[0017] According to a twelfth aspect, there is provided a computer program / program product, which is stored in a storage medium. The computer program / program product is executed by at least one processor to realize the method described in the first aspect or the method described in the second aspect.

Advantages of the Invention

[0018] In an embodiment of the present application, the first AI model information stored in the terminal by the first communication device is transmitted to the second communication device, thereby instructing the network side or the communication partner side to store the first AI model and / or related information of the first AI model in the terminal, so that the network side or the communication partner side can timely perform management such as appropriate configuration, update, activation, deactivation, etc. on the first AI model stored in the terminal, improving the management efficiency of the AI model, avoiding the terminal from being repeatedly configured with the same model or models with the same function, and saving resources.

Brief Description of Drawings

[0019]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Figure 10

Figure 11

Figure 12

Figure 13

Modes for Carrying Out the Invention

[0020] The following clearly and completely describes the technical solutions in the embodiments of the present application in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are some of the embodiments of the present application, not all of them. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art shall fall within the protection scope of the present application.

[0021] Terms such as "first" and "second" in the specification and claims of the present application are used to distinguish similar objects and are not for describing a specific order or sequence. It should be understood that such terms are interchangeable when appropriate, so that the embodiments of the present application can be implemented in an order other than that illustrated or described herein, and the objects distinguished by "first" and "second" generally belong to the same type, without limiting the number of objects. For example, the first object may be one or more. In addition, "and / or" in the specification and claims represents at least one of the connected objects, and the character " / " generally represents that the related objects before and after are in an "or" relationship.

[0022] It should be noted that the technology described in the embodiments of this application is not limited to the Long Term Evolution (LTE) / LTE-Advanced (LTE-A) system, but can also be applied to 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), and other systems. The terms "system" and "network" in the embodiments of this application are always used interchangeably, and the described technology may be used in the systems and radio technologies mentioned above, or may also be used in other systems and radio technologies. The following description describes the New Radio (NR) system for illustrative purposes and uses NR terms in most of the following descriptions. However, these technologies may also be applied to applications other than NR system applications, such as the Sixth Generation (6 th Generation, 6G) communication system.

[0023] FIG. 1 shows a block diagram of a wireless communication system to which the embodiments of the present application are applicable. The wireless communication system includes a terminal 11 and a network-side device 12. Here, the terminal 11 may be a mobile phone, a tablet personal computer, a laptop computer (or called a notebook computer), a personal digital assistant (PDA), a palm-top computer, a netbook, an ultra-mobile personal computer (UMPC), a mobile Internet device (MID), an augmented reality (AR) / virtual reality (VR) device, a robot, a wearable device, a vehicle user equipment (VUE), a pedestrian user equipment (PUE), a smart home (a home device having a wireless communication function, such as a refrigerator, a television, a washing machine or furniture, etc.), a game machine, a personal computer (PC), a deposit / withdrawal machine or a self-service machine, etc. The wearable device may include a smart watch, a smart band, smart earphones, smart glasses, a smart accessory (a smart bracelet, a smart bracelet, a smart ring, a smart necklace, a smart anklet, etc.), a smart list band, a smart clothing, etc. It should be noted that in the embodiments of the present application, the specific type of the terminal 11 is not limited. The network-side device 12 may include an access network device or a core network device. Here, the access network device 12 may be called a wireless access network device, a radio access network (RAN), a wireless access network function or a wireless access network unit.The access network device may include a base station, a WLAN access point, or a WiFi node, etc. The base station may be called a Node B, an evolved Node B (eNB), an access point, a Base Transceiver Station (BTS), a radio base station, a radio transceiver, a Basic Service Set (BSS), an Extended Service Set (ESS), a home B node, a home evolved B node, a Transmitting Receiving 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 terms. For the sake of explanation, only the base station in the NR system in the embodiments of this application is taken as an example, but it does not limit the specific type of the base station.The core network device may include, but is not limited to, at least one of a core network node, a core network function, a Mobility Management Entity (MME), an Access and Mobility Management Function (AMF), a Session Management Function (SMF), a User Plane Function (UPF), a Policy Control Function (PCF), a Policy and Charging Rules Function unit (PCRF), an Edge Application Server Discovery Function (EASDF), a Unified Data Management (UDM), a Unified Data Repository (UDR), a Home Subscriber Server (HSS), a Centralized network configuration (CNC), a Network Repository Function (NRF), a Network Exposure Function (NEF), a Local NEF (L-NEF), a Binding Support Function (BSF), an Application Function (AF), etc. It should be noted that in the embodiments of this application, only the core network device in the NR system is taken as an example, but the specific type of the core network device is not limited.

[0024] First, the following content will be described.

[0025] (1) The combination of Artificial Intelligence (AI) and a communication network Figure 2 is a flowchart of AI-based communication network optimization according to the related art. As shown in Figure 2, the model training function and the model inference function are important functions in the overall flow of AI-based communication network optimization. Here, the model training function generates an AI model based on training data. After completing the model effectiveness test, the model is deployed to the model inference function. In the process of generating the AI model, the model training function needs to acquire and analyze a large amount of data, and has high requirements for hardware performance and computing power. It is mainly deployed on network-side devices, such as Operation Administration and Maintenance (OAM) nodes and base stations.

[0026] The model inference function takes inference data as input and obtains AI inference outputs, such as air interface indicator predictions, based on the above model. The requirements for hardware performance and computing power of the model inference function are lower than those of the model training function. With the continuous improvement of terminal capabilities, and the increasing number of AI dedicated chips, Neural Processing Units (NPUs), and the continuous improvement of AI-driven efficiency, it becomes possible to perform model inference on the terminal side and even perform some model training.

[0027] (2) The capability report of the User Equipment (UE) (such as a terminal). The cellular radio communication system depends on accurate and efficient cooperative interworking between the base station and the UE. Among them, the terminal capability interaction is an important part of the cooperation between the base station and the UE. The base station can only perform accurate scheduling for the UE after knowing the UE capability. When the UE supports a certain function, the base station can configure this function for this UE. When the UE does not support a certain function, the base station cannot configure this function for this UE.

[0028] Figure 3 is a flowchart of UE capability reporting according to the related art. As shown in Figure 3, the terminal capability (UE Capability) mainly relates to two flows: the UE Capability request and the UE Capability report. When the base station determines that the UE needs to report the UE Capability, the base station sends a terminal capability request (UECapabilityEnquiry) command to the UE. After receiving the UECapabilityEnquiry command, the UE sends terminal capability information (UECapabilityInformation) based on the command.

[0029] The base station performs screening according to the filtering conditions (filter) in the UECapabilityEnquiry signaling to indicate which UE Capability the base station wants to obtain.

[0030] UE Capability is divided into capabilities at different levels, and the UE Capability signaling structure includes the following.

[0031] UE specific UE Capability: Each UE may have different capabilities, and such UE capabilities are applicable to all bands and band combinations supported by the UE.

[0032] UE Capability at the Band Combination level: Each Band Combination may have different capabilities. For example, the Band Combination of Band3 + Band77 supports a certain UE capability, while the Band Combination of Band1 + Band78 may not support this UE capability.

[0033] UE Capability at the Band level: Each Band may have different capabilities. For example, Band 77 supports a certain UE capability, while Band78 may not support this UE capability.

[0034] Another method for classifying UE capabilities is classification based on the protocol stack. When the UE Capability is actually reported, it is also reported hierarchically based on the protocol stack. The UE Capability report includes PDCP-Parameters: UE Capability corresponding to the PDCP (Packet Data Convergence Protocol) layer, and RLC-Parameters: UE Capability corresponding to the RLC (Radio Link Control) layer, and MAC-Parameters: UE Capability corresponding to the MAC (Media Access Control) layer, and PHY-Parameters: UE Capability corresponding to the PHY (Physical) layer, and RF-Parameters: UE Capability related to RF (Radio Frequency), and is divided into these.

[0035] Hereinafter, in conjunction with the drawings, the AI model information transmission method according to the embodiments of the present application will be described in detail by means of several embodiments and their application scenarios.

[0036] FIG. 4 is one of the flowcharts of the AI model information transmission method according to the embodiments of the present application. As shown in FIG. 4, this method includes the following flow.

[0037] In step 400, the first communication device transmits first AI model information to the second communication device. The first AI model information is used to indicate the first AI model and / or related information of the first AI model. The first AI model is an AI model stored in the terminal. Here, the first communication device is the terminal, and the second communication device is the communication partner of the terminal, or The first communication device is the source cell for the switching of the terminal, and the second communication device is the target cell for the switching of the terminal, or The first communication device is a cell with an access history in the radio resource control (RRC) recovery process of the terminal, and the second communication device is a new access cell in the RRC recovery process of the terminal.

[0038] Optionally, the first communication device may be a terminal, and the first AI model may be an AI model stored in this terminal. Accordingly, the second communication device may be a communication partner of the terminal, such as a network-side device or another terminal. Optionally, the terminal can send the first AI model and / or related information of the first AI model to a network-side device, whereby the network-side device can realize management such as appropriate configuration, update, activation, deactivation, etc. for the first AI model. Optionally, the terminal can send the first AI model and / or related information of the first AI model to another terminal, whereby the other terminal can transfer the first AI model and / or related information of the first AI model to the network-side device, whereby the network-side device can realize management such as appropriate configuration, update, activation, deactivation, etc. for the first AI model. Optionally, the network-side device may include a base station, a core network function, a core network element, or OAM. Optionally, the terminal can send the first AI model and / or related information of the first AI model to another terminal, whereby the other terminal can realize management such as appropriate configuration, update, activation, deactivation, etc. for the first AI model. Optionally, the first communication device may be the source cell during the switching of the terminal storing the first AI model, and the second communication device may be the target cell during the switching of this terminal storing the first AI model. Optionally, during the switching of the terminal that stores the first AI model, the source cell may store the first AI model and / or related information of the first AI model. For example, this terminal may report it to the source cell before switching. During the switching, the source cell can send the first AI model and / or related information of the first AI model to the target cell, thereby completing the switching. After the terminal accesses the target cell, the target cell can realize management such as appropriate configuration, update, activation, and deactivation of the first AI model. Optionally, the first AI model and / or related information of the first AI model may be stored in the cell with access history during the RRC recovery process of the terminal that stores the first AI model. For example, this may be what this terminal previously sent to the cell with access history. In that case, during the RRC recovery process, the cell with access history can send the first AI model and / or related information of the first AI model to the new access cell, thereby enabling the new access cell to realize management such as appropriate configuration, update, activation, and deactivation of the first AI model after RRC recovery. Optionally, the AI model stored in the terminal may refer to the AI model preset or stored in the terminal.

[0039] In the embodiments of the present application, the first AI model information stored in the terminal by the first communication device is sent to the second communication device, thereby instructing the network side or the communication partner side to store the first AI model and / or related information of the first AI model in the terminal. Thereby, the network side or the communication partner side can timely perform management such as appropriate configuration, update, activation, and deactivation of the first AI model stored in the terminal, improve the management efficiency of the AI model, avoid the terminal being repeatedly configured with the same model or models with the same function, and save resources.

[0040] Optionally, the first AI model information is The model identifier of the first AI model for uniquely identifying the first AI model, the model function of the first AI model, the model activation condition of the first AI model, the model active state of the first AI model, the model data size of the first AI model, the model authentication information of the first AI model for the second communication device to identify or authenticate the first AI model, and includes at least one of the model structure information of the first AI model.

[0041] Optionally, the first AI model information may include the model identifier of the first AI model, and the model identifier of the first AI model may be used to uniquely identify the first AI model. Optionally, the first AI model information may include the model function of the first AI model, and the model function of the first AI model may be used to represent the function or action of this first AI model, such as compression or reporting of channel state information (CSI), beam management, or mobility management. Optionally, the first AI model information may include the model activation condition of the first AI model, and the model activation condition of the first AI model may refer to that the first AI model is activated only by this model activation condition. Optionally, the first AI model information may include the model active state of the first AI model. Optionally, the model active state of the first AI model may include activation or deactivation. Optionally, the first AI model information may include the model data size of the first AI model. Optionally, the first AI model information may include the model authentication information of the first AI model, and the model authentication information of the first AI model may be used for the second communication device to identify or authenticate the first AI model. Optionally, the first AI model information may include the model structure information of the first AI model. Optionally, the model structure information of the first AI model may include a neural network structure, such as the number of neural network layers, etc. Optionally, the model structure information of the first AI model may include any one of the above information, or any combination of multiple ones.

[0042] Optionally, the model activation condition is an activation area, an activation time, an activation configuration, and at least one of activation channel environment parameters.

[0043] Optionally, the model activation condition of the first AI model may include an activation area. For example, when the terminal is within this activation area, this first AI model is activated, and when the terminal moves outside this activation area, this first AI model is deactivated. Optionally, the model activation condition of the first AI model may include an activation time. For example, if it is within the activation time, this first AI model is activated, and if it is outside the activation time, this first AI model is deactivated. Optionally, the model activation condition of the first AI model may include an activation configuration. For example, when the network configuration matches this activation configuration, this first AI model is activated, and when the network configuration does not match this activation configuration, this first AI model is deactivated. Optionally, the activation configuration is a reference signal space area configuration, an antenna port configuration, a reference signal frequency area configuration, and may include at least one configuration of a time domain configuration of the reference signal.

[0044] Optionally, the model enabling condition of the first AI model may include an enabling channel environment parameter, and the enabling channel environment parameter may include the value range of all channel environment parameters that can enable the first AI model. For example, if the channel environment parameter of the location where the terminal is located is within the range of the enabling channel environment parameter, this first AI model is enabled; otherwise, this first AI model is disabled. Optionally, the disabling of the first AI model may refer to the disabling of the related information of the first AI model. Optionally, the enabling of the first AI model may refer to the enabling of the related information of the first AI model. Optionally, the disabling of the first AI model may refer to the disabling of the configuration information of the first AI model. Optionally, the enabling of the first AI model may refer to the enabling of the configuration information of the first AI model. Optionally, the disabling of the first AI model may refer to the disabling of the first AI model information corresponding to the first AI model. Optionally, the enabling of the first AI model may refer to the enabling of the first AI model information corresponding to the first AI model.

[0045] Optionally, the enabling channel environment parameter may include at least one category of parameters among the environment type, line-of-sight / non-line-of-sight type, delay spread, angle spread, Doppler spread, Doppler shift, Rice K factor, shadow attenuation, reference signal time difference of arrival, reference signal round-trip time, reference signal received power, reference signal departure angle, and reference signal arrival angle.

[0046] Optionally, before the first communication device transmits first AI model information to a second communication device, the method further includes: The first communication device further receives an AI model information request, which is used to request the first AI model information.

[0047] Optionally, the first communication device receives an AI model information request sent from the second communication device, and based on the AI model information request, can transmit a first AI model and / or related information of the first AI model.

[0048] Optionally, the AI model information request an AI model corresponding to a specific model identifier range and / or related information of an AI model corresponding to a specific model identifier range, an AI model with a specific model function and / or related information of an AI model with a specific model function, an AI model activated within a specific area and / or related information of an AI model activated within a specific area, an AI model activated with a specific network configuration and / or related information of an AI model activated with a specific network configuration, an AI model activated with specific channel environment parameters and / or related information of an AI model activated with specific channel environment parameters, an AI model in an activated state and / or related information of an AI model in an activated state, an AI model in an active state and / or related information of an AI model in an active state, an AI model in an inactive state and / or related information of an AI model in an inactive state, is used to request at least one of all AI models stored in the terminal and / or related information of all AI models stored in the terminal.

[0049] Optionally, the specification may be in the designated sense or may be specific, that is, the second communication device may send an AI model information request and use it to request an AI model and / or related information of the AI model that meets the screening conditions in the AI model information request (for example, one or more of a specific model identifier range, specific model functions, activation within a specific area, activation in a specific network configuration, activation with specific channel environment parameters, being in an activated state, being in an active state, being in an inactive state, etc.). Optionally, what the first communication device sends to the second communication device may be all AI models stored in the terminal and / or related information of all AI models stored in the terminal. Optionally, what the first communication device sends to the second communication device may be some AI models stored in the terminal and / or related information of some AI models stored in the terminal. Optionally, the first communication device may determine the characteristics of the first AI model and / or the related information of the first AI model to be sent to the second communication device based on the screening conditions in the AI model request, that is, based on the screening conditions in the AI model request, screen out some AI models and / or related information of some AI models that meet the screening conditions from all AI models stored in the terminal and / or related information of all AI models stored in the terminal, and send them as the first AI model and / or the related information of the first AI model.

[0050] Optionally, the AI model information request can request the first AI model within a specific model identifier range and / or the related information of the first AI model within a specific model identifier range among all the AI models stored in the terminal. After receiving the AI model information request, the first communication device can check whether there is one or more first AI models belonging to the specific model identifier range among all the AI models stored in the terminal. If so, it can send this one or more first AI models and / or the related information of the one or more first AI models to the second communication device.

[0051] Optionally, the AI model information request may request the first AI model with a specific model function and / or the related information of the first AI model with a specific model function among all the AI models stored in the terminal. After receiving the AI model information request, the first communication device can check whether there is one or more first AI models with the specific model function among all the AI models stored in the terminal. If so, it can send this one or more first AI models and / or the related information of the one or more first AI models to the second communication device.

[0052] Optionally, the AI model information request may request the first AI model to be activated within a specific area and / or the related information of the first AI model to be activated within a specific area among all the AI models stored in the terminal. After receiving the AI model information request, the first communication device can check whether there is one or more first AI models to be activated within the specific area among all the AI models stored in the terminal. If so, it can send this one or more first AI models and / or the related information of the one or more first AI models to the second communication device.

[0053] Optionally, the AI model information request may request, among all the AI models stored in the terminal, the first AI model to be enabled with a specific network configuration and / or the related information of the first AI model to be enabled with a specific network configuration. After receiving the AI model information request, the first communication device can check whether there is one or more first AI models to be enabled with a specific network configuration among all the AI models stored in the terminal. If so, the first communication device can send this one or more first AI models and / or the related information of the one or more first AI models to the second communication device.

[0054] Optionally, the AI model information request may request, among all the AI models stored in the terminal, the first AI model to be enabled with specific channel environment parameters and / or the related information of the first AI model to be enabled with specific channel environment parameters. After receiving the AI model information request, the first communication device can check whether there is one or more first AI models to be enabled with specific channel environment parameters among all the AI models stored in the terminal. If so, the first communication device can send this one or more first AI models and / or the related information of the one or more first AI models to the second communication device.

[0055] Optionally, the AI model information request may request, among all the AI models stored in the terminal, the first AI model in an enabled state and / or the related information of the first AI model in an enabled state. After receiving the AI model information request, the first communication device can check whether there is one or more first AI models in an enabled state among all the AI models stored in the terminal. If so, the first communication device can send this one or more first AI models and / or the related information of the one or more first AI models to the second communication device.

[0056] Optionally, the AI model information request may request the first AI model in an active state and / or the related information of the first AI model in an active state among all the AI models stored in the terminal. After receiving the AI model information request, the first communication device can check whether there is one or more first AI models in an active state among all the AI models stored in the terminal. If so, the first communication device can send the one or more first AI models and / or the related information of the one or more first AI models to the second communication device.

[0057] Optionally, the AI model information request may request the first AI model in an inactive state and / or the related information of the first AI model in an inactive state among all the AI models stored in the terminal. After receiving the AI model information request, the first communication device can check whether there is one or more first AI models in an inactive state among all the AI models stored in the terminal. If so, the first communication device can send the one or more first AI models and / or the related information of the one or more first AI models to the second communication device.

[0058] Optionally, the AI model information request may request all the AI models stored in the terminal and / or the related information of all the AI models stored in the terminal. After receiving the AI model information request, the first communication device may send all the AI models stored in the terminal and / or the related information of all the AI models stored in the terminal to the second communication device.

[0059] Optionally, when the first communication device is the terminal and the second communication device is the communication partner of the terminal, before the first communication device sends the first AI model information to the second communication device, the method The first communication device further includes determining second AI model information, where the second AI model information is used to indicate a second AI model and / or related information of the second AI model, and the second AI model is an AI model supported by the second communication device.

[0060] Optionally, the first communication device may first determine a second AI model supported by the second communication device and / or related information of the second AI model supported by the second communication device.

[0061] Optionally, the terminal may first determine second AI model information, where the second AI model information is used to indicate a second AI model and / or related information of the second AI model, and the second AI model is an AI model supported by a network-side device.

[0062] Optionally, after the first communication device determines the second AI model information, the method further includes: The first communication device further includes transmitting first instruction information to the second communication device, where the first instruction information is used to characterize that the second AI model exists in the first communication device and / or an AI model that matches the related information of the second AI model exists.

[0063] Optionally, the first communication device may first determine a second AI model supported by the second communication device and / or related information of the second AI model supported by the second communication device. If the first communication device discovers that the second AI model is included in all the AI models stored in itself, the first communication device may transmit the first instruction information to the second communication device and notify the second communication device that the second AI model exists in the first communication device and / or an AI model that conforms to the related information of the second AI model exists.

[0064] Optionally, after receiving the first instruction information, the second communication device can send an AI model information request to the first communication device, thereby requesting the first AI model and / or related information of the first AI model. After the first communication device receives the AI model information request, it can send the first AI model and / or related information of the first AI model to the second communication device. For example, after receiving the first instruction information, the network-side device can send an AI model information request to the terminal, thereby requesting the first AI model and / or related information of the first AI model. After the terminal receives the AI model information request, it can send the first AI model and / or related information of the first AI model to the network side.

[0065] Optionally, the first communication device determining the second AI model information is the first communication device receives the broadcast information from the second communication device, and the first communication device includes determining the second AI model information based on the broadcast information.

[0066] Optionally, the method by which the first communication device determines the second AI model and / or related information of the second AI model supported by the second communication device may be determined by the first communication device based on the broadcast information of the second communication device. For example, the network-side device can send, by broadcast, the related information of the second AI model supported by the network-side device and / or the second AI model supported by the second communication device. After receiving this broadcast information, the terminal can determine the second AI model supported by the second communication device and / or the related information of the second AI model supported by the second communication device. If the terminal discovers that the second AI model is included in all the AI models stored in itself, the terminal can send first instruction information to the network-side device, and can notify the network-side device that the second AI model exists and / or an AI model that matches the related information of the second AI model exists. After receiving the first instruction information, the network-side device can send an AI model information request to the terminal, thereby requesting the first AI model and / or the related information of the first AI model. After receiving the AI model information request, the terminal can send the first AI model and / or the related information of the first AI model to the network side.

[0067] Optionally, the method further includes the first communication device further sending second instruction information to the second communication device, where the second instruction information is used to characterize that an AI model exists in the terminal and / or the terminal has model inference capabilities.

[0068] Optionally, the first communication device may pre-send the second instruction information to the second communication device to notify the second communication device that an AI model exists in the first communication device. Optionally, after receiving the second instruction information, the second communication device can send an AI model information request to the first communication device, thereby requesting the first AI model and / or the related information of the first AI model. After receiving the AI model information request, the first communication device can send the first AI model and / or the related information of the first AI model to the second communication device.

[0069] Optionally, the second instruction information is used to instruct that the AI model is already stored in the terminal or the terminal has model inference capabilities.

[0070] Optionally, when the first communication device is the source cell of the handover and the second communication device is the target cell of the handover, the first AI model information is included in the handover request.

[0071] Optionally, when the first communication device is a cell with an access history in the RRC recovery process and the second communication device is a new access cell in the RRC recovery process, the first AI model information is included in the terminal context information.

[0072] In the embodiments of the present application, the first AI model information stored in the terminal by the first communication device is transmitted to the second communication device, thereby instructing the network side or the communication partner side of the first AI model and / or related information of the first AI model stored in the terminal. Thereby, the network side or the communication partner side can timely perform management such as appropriate configuration, update, activation, deactivation, etc. on the first AI model stored in the terminal, improve the management efficiency of the AI model, and avoid the terminal being repeatedly configured with the same model or models with the same function, saving resources.

[0073] FIG. 5 is a second flowchart of the AI model information transmission method according to the embodiments of the present application. As shown in FIG. 5, this method includes the following flow.

[0074] In step 500, the second communication device receives the first AI model information from the first communication device. The first AI model information is used to instruct the first AI model and / or related information of the first AI model. The first AI model is an AI model stored in the terminal. Here, the first communication device is the terminal, and the second communication device is the communication partner side of the terminal, or The first communication device is the source cell for the switching of the terminal, and the second communication device is the target cell for the switching of the terminal, or The first communication device is a cell with access history in the RRC recovery process of the terminal, and the second communication device is a new access cell in the RRC recovery process of the terminal.

[0075] Optionally, the first communication device may be a terminal, and the first AI model may be an AI model stored in this terminal. Accordingly, the second communication device may be a communication partner of the terminal, such as a network-side device or another terminal. Optionally, the network-side device can receive the first AI model and / or related information of the first AI model transmitted from the terminal, and can further implement management such as appropriate configuration, update, activation, deactivation, etc. for the first AI model. Optionally, another terminal can receive the first AI model and / or related information of the first AI model transmitted by the terminal, and further, another terminal can transfer the first AI model and / or related information of the first AI model to the network-side device, whereby the network-side device can implement management such as appropriate configuration, update, activation, deactivation, etc. for the first AI model. Optionally, the network-side device may include a base station, a core network function, a core network element, or OAM. Optionally, another terminal can receive the first AI model and / or related information of the first AI model transmitted by the terminal, and can further implement management such as appropriate configuration, update, activation, deactivation, etc. for the first AI model. Optionally, the first communication device may be the source cell during the switching of the terminal storing the first AI model, and the second communication device may be the target cell during the switching of this terminal storing the first AI model. Optionally, during the switching of the terminal that stores the first AI model, the source cell may store the first AI model and / or related information of the first AI model. For example, this terminal may report it to the source cell before switching. During the switching, the source cell can send the first AI model and / or related information of the first AI model to the target cell, thereby completing the switching. After the terminal accesses the target cell, the target cell can implement management such as appropriate configuration, update, activation, and deactivation for the first AI model. Optionally, the first AI model and / or related information of the first AI model may be stored in the cell with access history during the RRC recovery process of the terminal that stores the first AI model. For example, this may be what this terminal previously sent to the cell with access history. In that case, during the RRC recovery process, the cell with access history can send the first AI model and / or related information of the first AI model to the new access cell, thereby enabling the new access cell to implement management such as appropriate configuration, update, activation, and deactivation for the first AI model after RRC recovery. Optionally, the AI model stored in the terminal may refer to the AI model preset or stored in the terminal.

[0076] In the embodiments of the present application, the first AI model information stored in the terminal by the first communication device is sent to the second communication device, thereby instructing the network side or the communication partner side of the first AI model and / or related information of the first AI model stored in the terminal. Thereby, the network side or the communication partner side can timely perform management such as appropriate configuration, update, activation, and deactivation for the first AI model stored in the terminal, improve the management efficiency of the AI model, avoid the terminal being repeatedly configured with the same model or models with the same function, and save resources.

[0077] Optionally, the first AI model information is The model identifier of the first AI model for uniquely identifying the first AI model, The model function of the first AI model, The model activation condition of the first AI model, The model active state of the first AI model, The model data size of the first AI model, The model authentication information of the first AI model for the second communication device to identify or authenticate the first AI model, Includes at least one of the model structure information of the first AI model.

[0078] Optionally, the first AI model information may include the model identifier of the first AI model, and the model identifier of the first AI model may be used to uniquely identify the first AI model. Optionally, the first AI model information may include the model function of the first AI model, and the model function of the first AI model may be used to represent the function or action of this first AI model, such as CSI compression or reporting, beam management, or mobility management, etc. Optionally, the first AI model information may include the model activation condition of the first AI model, and the model activation condition of the first AI model may, by itself, indicate that the first AI model is activated. Optionally, the first AI model information may include the model active state of the first AI model. Optionally, the model active state of the first AI model may include activation or deactivation. Optionally, the first AI model information may include the model data size of the first AI model. Optionally, the first AI model information may include the model authentication information of the first AI model, and the model authentication information of the first AI model may be used by the second communication device to identify or authenticate the first AI model. Optionally, the first AI model information may include the model structure information of the first AI model. Optionally, the model structure information of the first AI model may include a neural network structure, such as the number of neural network layers, etc. Optionally, the model structure information of the first AI model may include any one of the above information, or any combination of multiple ones.

[0079] Optionally, the model activation condition is an activation region, an activation time, an activation configuration, and at least one of activation channel environment parameters.

[0080] Optionally, the model activation condition of the first AI model may include an activation region. For example, when the terminal is within this activation region, this first AI model is activated, and when the terminal moves outside this activation region, this first AI model is deactivated. Optionally, the model activation condition of the first AI model may include an activation time. For example, if it is within the activation time, this first AI model is activated, and if it is outside the activation time, this first AI model is deactivated. Optionally, the model activation condition of the first AI model may include an activation configuration. For example, when the network configuration matches this activation configuration, this first AI model is activated, and when the network configuration does not match this activation configuration, this first AI model is deactivated. Optionally, the activation configuration is a reference signal space region configuration, an antenna port configuration, a reference signal frequency region configuration, and may include at least one configuration of the time domain configuration of the reference signal.

[0081] Optionally, the model enabling condition of the first AI model may include an enabling channel environment parameter, and the enabling channel environment parameter may include the value range of all channel environment parameters that can enable the first AI model. For example, when the channel environment parameter of the location where the terminal is located is within the range of the enabling channel environment parameter, this first AI model is enabled; otherwise, this first AI model is disabled. Optionally, the disabling of the first AI model may refer to the disabling of the related information of the first AI model. Optionally, the enabling of the first AI model may refer to the enabling of the related information of the first AI model. Optionally, the disabling of the first AI model may refer to the disabling of the configuration information of the first AI model. Optionally, the enabling of the first AI model may refer to the enabling of the configuration information of the first AI model. Optionally, the disabling of the first AI model may refer to the disabling of the first AI model information corresponding to the first AI model. Optionally, the enabling of the first AI model may refer to the enabling of the first AI model information corresponding to the first AI model.

[0082] Optionally, the enabling channel environment parameter may include at least one category of parameters among environment type, line-of-sight / non-line-of-sight type, delay spread, angle spread, Doppler spread, Doppler shift, Rice K factor, shadow attenuation, reference signal time difference of arrival, reference signal round-trip time, reference signal received power, reference signal departure angle, and reference signal arrival angle.

[0083] Optionally, before the second communication device receives the first AI model information from the first communication device, the method further includes: The second communication device further includes transmitting an AI model information request to the first communication device, and the AI model information request is used to request the first AI model information.

[0084] Optionally, the second communication device can transmit an AI model information request to the first communication device, and the first communication device can transmit the first AI model and / or related information of the first AI model based on the AI model information request.

[0085] Optionally, the AI model information request AI models corresponding to a specific model identifier range and / or related information of AI models corresponding to a specific model identifier range, AI models with specific model functions and / or related information of AI models with specific model functions, AI models activated within a specific area and / or related information of AI models activated within a specific area, AI models activated with a specific network configuration and / or related information of AI models activated with a specific network configuration, AI models activated with specific channel environment parameters and / or related information of AI models activated with specific channel environment parameters, AI models in an activated state and / or related information of AI models in an activated state, AI models in an active state and / or related information of AI models in an active state, AI models in a non-active state and / or related information of AI models in a non-active state, is used to request at least one of all AI models stored in the terminal and / or related information of all AI models stored in the terminal.

[0086] Optionally, the specification may be in a designated sense or specific, that is, the second communication device may send an AI model information request and use it to request an AI model and / or related information of the AI model that meets the screening conditions (for example, one or more of a specific model identifier range, specific model functions, activation within a specific area, activation in a specific network configuration, activation with specific channel environment parameters, being in an activated state, being in an active state, being in an inactive state, etc.) in the AI model information request. Optionally, what the first communication device sends to the second communication device may be all AI models stored in the terminal and / or related information of all AI models stored in the terminal. Optionally, what the first communication device sends to the second communication device may be some AI models stored in the terminal and / or related information of some AI models stored in the terminal. Optionally, the first communication device may determine the characteristics of the first AI model and / or the related information of the first AI model to be sent to the second communication device based on the screening conditions in the AI model request, that is, based on the screening conditions in the AI model request, screen out some AI models and / or related information of some AI models that meet the screening conditions from all AI models stored in the terminal and / or related information of all AI models stored in the terminal, and send them as the first AI model and / or the related information of the first AI model.

[0087] Optionally, the AI model information request can request the first AI model within a specific model identifier range and / or the related information of the first AI model within a specific model identifier range among all the AI models stored in the terminal. After receiving the AI model information request, the first communication device can check whether there is one or more first AI models belonging to the specific model identifier range among all the AI models stored in the terminal. If so, it can send this one or more first AI models and / or the related information of one or more first AI models to the second communication device.

[0088] Optionally, the AI model information request may request the first AI model with a specific model function and / or the related information of the first AI model with a specific model function among all the AI models stored in the terminal. After receiving the AI model information request, the first communication device can check whether there is one or more first AI models with the specific model function among all the AI models stored in the terminal. If so, it can send this one or more first AI models and / or the related information of one or more first AI models to the second communication device.

[0089] Optionally, the AI model information request may request the first AI model activated within a specific area and / or the related information of the first AI model activated within a specific area among all the AI models stored in the terminal. After receiving the AI model information request, the first communication device can check whether there is one or more first AI models activated within the specific area among all the AI models stored in the terminal. If so, it can send this one or more first AI models and / or the related information of one or more first AI models to the second communication device.

[0090] Optionally, the AI model information request may request, among all the AI models stored in the terminal, the first AI model to be activated with a specific network configuration and / or the related information of the first AI model to be activated with a specific network configuration. After receiving the AI model information request, the first communication device can check whether there is one or more first AI models to be activated with a specific network configuration among all the AI models stored in the terminal. If so, the first communication device can send this one or more first AI models and / or the related information of the one or more first AI models to the second communication device.

[0091] Optionally, the AI model information request may request, among all the AI models stored in the terminal, the first AI model to be activated with specific channel environment parameters and / or the related information of the first AI model to be activated with specific channel environment parameters. After receiving the AI model information request, the first communication device can check whether there is one or more first AI models to be activated with specific channel environment parameters among all the AI models stored in the terminal. If so, the first communication device can send this one or more first AI models and / or the related information of the one or more first AI models to the second communication device.

[0092] Optionally, the AI model information request may request, among all the AI models stored in the terminal, the first AI model in an activated state and / or the related information of the first AI model in an activated state. After receiving the AI model information request, the first communication device can check whether there is one or more first AI models in an activated state among all the AI models stored in the terminal. If so, the first communication device can send this one or more first AI models and / or the related information of the one or more first AI models to the second communication device.

[0093] Optionally, the AI model information request may request the first AI model in an active state and / or related information of the first AI model in an active state among all the AI models stored in the terminal. After receiving the AI model information request, the first communication device can check whether one or more first AI models in an active state exist among all the AI models stored in the terminal. If they exist, the first communication device can send this one or more first AI models and / or related information of the one or more first AI models to the second communication device.

[0094] Optionally, the AI model information request may request the first AI model in an inactive state and / or related information of the first AI model in an inactive state among all the AI models stored in the terminal. After receiving the AI model information request, the first communication device can check whether one or more first AI models in an inactive state exist among all the AI models stored in the terminal. If they exist, the first communication device can send this one or more first AI models and / or related information of the one or more first AI models to the second communication device.

[0095] Optionally, the AI model information request may request all the AI models stored in the terminal and / or related information of all the AI models stored in the terminal. After receiving the AI model information request, the first communication device may send all the AI models stored in the terminal and / or related information of all the AI models stored in the terminal to the second communication device.

[0096] Optionally, when the first communication device is the terminal and the second communication device is the communication partner side of the terminal, the method includes The second communication device further includes broadcasting second AI model information, where the second AI model information is used to indicate a second AI model and / or related information of the second AI model, and the second AI model is an AI model supported by the second communication device.

[0097] Optionally, the second communication device may broadcast the second AI model information, enabling the first communication device to determine the second AI model supported by the second communication device and / or related information of the second AI model supported by the second communication device. Optionally, after the second communication device broadcasts the second AI model information, the method includes: The second communication device receives first instruction information from the first communication device. The second communication device further includes determining, based on the first instruction information, that the second AI model exists in the first communication device and / or that an AI model matching the related information of the second AI model exists.

[0098] Optionally, the first communication device may first determine the second AI model supported by the second communication device and / or related information of the second AI model supported by the second communication device. If the first communication device discovers that the second AI model is included in all the AI models stored in itself, the first communication device may send first instruction information to the second communication device and notify the second communication device that the second AI model exists in the first communication device and / or that an AI model conforming to the related information of the second AI model exists.

[0099] Optionally, after receiving the first instruction information, the second communication device can send an AI model information request to the first communication device, thereby requesting the first AI model and / or related information of the first AI model. After the first communication device receives the AI model information request, the first communication device can send the first AI model and / or related information of the first AI model to the second communication device. For example, after receiving the first instruction information, the network-side device can send an AI model information request to the terminal, thereby requesting the first AI model and / or related information of the first AI model. After the terminal receives the AI model information request, the terminal can send the first AI model and / or related information of the first AI model to the network side.

[0100] For example, the network-side device can transmit, by broadcast, the related information of the second AI model supported by the network-side device and / or the second AI model supported by the second communication device. After receiving this broadcast information, the terminal can determine the second AI model supported by the second communication device and / or the related information of the second AI model supported by the second communication device. When the terminal discovers that the second AI model is included in all the AI models stored in itself, the terminal can send first instruction information to the network-side device, and can notify the network-side device that the second AI model exists and / or an AI model that matches the related information of the second AI model exists. After receiving the first instruction information, the network-side device can send an AI model information request to the terminal, thereby requesting the first AI model and / or the related information of the first AI model. After receiving the AI model information request, the terminal can send the first AI model and / or the related information of the first AI model to the network side.

[0101] Optionally, the method The second communication device receives second instruction information from the first communication device, The second communication device further includes that there exists an AI model in the terminal and / or the terminal has model inference capabilities based on the second instruction information.

[0102] Optionally, the first communication device may pre-transmit the second instruction information to the second communication device to notify the second communication device that there exists an AI model in the first communication device. Optionally, after receiving the second instruction information, the second communication device can send an AI model information request to the first communication device, thereby requesting the first AI model and / or the related information of the first AI model. After receiving the AI model information request, the first communication device can send the first AI model and / or the related information of the first AI model to the second communication device.

[0103] Optionally, when the first communication device is the source cell for the handover and the second communication device is the target cell for the handover, the first AI model information is included in the handover request.

[0104] Optionally, when the first communication device is the cell with access history in the RRC recovery process and the second communication device is the latest access cell in the RRC recovery process, the first AI model information is included in the terminal context information.

[0105] In an embodiment of the present application, the first AI model information stored in the terminal by the first communication device is transmitted to the second communication device, thereby instructing the network side or the communication partner side of the first AI model stored in the terminal and / or related information of the first AI model, so that the network side or the communication partner side can timely perform management such as appropriate configuration, update, activation, deactivation, etc. on the first AI model stored in the terminal, improve the management efficiency of the AI model, avoid the terminal from being repeatedly configured with the same model or models with the same function, and save resources.

[0106] In one embodiment, taking the first communication device as the terminal and the second communication device as the network side device as an example, the first AI model and / or related information of the first AI model may be reported in the form of terminal capability information. FIG. 6 is one of the schematic diagrams of AI model information transmission according to the embodiment of the present application. As shown in FIG. 6, the following steps may be included.

[0107] Step (1) The network sends a terminal capability request to the terminal, and the terminal capability request may include an AI model information request, that is, the content included in the terminal capability request is the AI model corresponding to a specific model identifier range and / or the related information of the AI model corresponding to a specific model identifier range, and the AI model with a specific model function and / or the related information of the AI model with a specific model function, and The AI model activated within a specific area and / or related information of the AI model activated within a specific area, and The AI model activated with a specific network configuration and / or related information of the AI model activated with a specific network configuration, and The AI model activated with specific channel environment parameters and / or related information of the AI model activated with specific channel environment parameters, and The AI model in an activated state and / or related information of the AI model in an activated state, and The AI model in an active state and / or related information of the AI model in an active state, and The AI model in an inactive state and / or related information of the AI model in an inactive state, and It is used to request at least one of all the AI models stored in the terminal and / or related information of all the AI models stored in the terminal.

[0108] Step (2) The terminal sends terminal capability feedback to the network-side device and is used to feedback conventional AI model information that includes the first AI model information and meets the screening conditions. The model identifier of the first AI model for uniquely identifying the first AI model, and The model function of the first AI model, and The model activation condition of the first AI model, and The model active state of the first AI model, and The model data size of the first AI model, and The model authentication information of the first AI model for the second communication device to identify or authenticate the first AI model, and It includes at least one of the model structure information of the first AI model.

[0109] Here, the model activation condition is The activation area, and The activation time, and The activation configuration, and It includes at least one of the activation channel environment parameters.

[0110] After the terminal feeds back the terminal capabilities in step (3), if the terminal-side AI model and / or the related information of the AI model are changed, the network-side device can be sent a terminal capability update. The update can be performed based on the model identifier, such as adding, changing, or deleting the AI model and / or the related information of the AI model.

[0111] In one embodiment, taking the example that the first communication device is a terminal and the second communication device is a network-side device, the first AI model and / or the related information of the first AI model may be reported in a form fed back by the terminal after combining the capability instruction with the network-side device request. FIG. 7 is the second schematic diagram of AI model information transmission according to the embodiment of the present application. As shown in FIG. 7, the following steps may be included.

[0112] Step (1) The network sends a terminal capability request to the terminal. Step (2) The terminal may indicate in the terminal capability feedback that the AI model is already stored or the terminal has model inference capabilities.

[0113] Optionally, it may be an instruction based on the function granularity. For example, the terminal may include second instruction information in the terminal capability feedback. Optionally, the second instruction information is used to indicate that the AI model is already stored in the terminal or the terminal has model inference capabilities.

[0114] Step (3) The network sends a terminal information request to the terminal, which may include an AI model information request. That is, the content included in the terminal capability request is the AI model corresponding to a specific model identifier range and / or the related information of the AI model corresponding to a specific model identifier range, and The AI model with specific model functions and / or the related information of the AI model with specific model functions, and The AI model activated within a specific area and / or the related information of the AI model activated within a specific area, and The AI model activated with a specific network configuration and / or the related information of the AI model activated with a specific network configuration, and The AI model activated with specific channel environment parameters and / or the related information of the AI model activated with specific channel environment parameters, and The AI model in an activated state and / or the related information of the AI model in an activated state, and The AI model in an active state and / or the related information of the AI model in an active state, and The AI model in an inactive state and / or the related information of the AI model in an inactive state, and It is used to request at least one of all the AI models stored in the terminal and / or the related information of all the AI models stored in the terminal.

[0115] Step (4) The terminal may send terminal information feedback to the network-side device, which may include the first AI model information. After the terminal feeds back its terminal capabilities, if the terminal-side AI model and / or the related information of the AI model are changed, the terminal can send a terminal capability update to the network-side device. The update can perform operations such as adding, changing, or deleting the AI model and / or the related information of the AI model based on the model identifier.

[0116] In one embodiment, taking the example where the first communication device is a terminal and the second communication device is a network-side device, the first AI model and / or the related information of the first AI model may be reported in a form where the terminal feeds back after combining the RRC message instruction with the network-side device request. FIG. 8 is the third schematic diagram of AI model information transmission according to the embodiment of the present application. As shown in FIG. 8, the following steps may be included.

[0117] Step (1) The base station broadcasts second AI model information, which may include at least one of the supported AI functions, the network configuration related to the supported AI functions, the channel environment parameters related to the supported AI functions, and the list of supported AI model identifiers.

[0118] After receiving the broadcast information, the terminal can determine the related information of the second AI model supported by the base station and / or the second AI model supported by the second communication device. Optionally, the terminal may include the first indication information or the second indication information in the RRC message. Optionally, the first indication information is used to indicate that the second AI model supported by the base station is stored in the terminal and / or there exists an AI model that matches the related information of the second AI model. Optionally, the first indication information is used to indicate that an AI model is already stored in the terminal or the terminal has model inference capabilities. Optionally, the terminal may further indicate the already stored AI model and / or the update of the AI model (via the first indication information or the second indication information) upon completion of RRC establishment / reconfiguration / resumption. Optionally, the terminal may include the first indication information or the second indication information in the RRC message. Optionally, the first indication information is used to indicate that the second AI model supported by the base station is stored in the terminal and / or there exists an AI model that matches the related information of the second AI model. Optionally, the first indication information is used to indicate that an AI model is already stored in the terminal or the terminal has model inference capabilities. Optionally, the terminal may further indicate the already stored AI model and / or the update of the AI model (via the first indication information or the second indication information) upon completion of RRC establishment / reconfiguration / resumption.

[0119] Step (3) The network sends a terminal information request to the terminal, which may include an AI model information request. That is, the content included in the terminal capability request is the AI model corresponding to a specific model identifier range and / or the related information of the AI model corresponding to a specific model identifier range, the AI model with a specific model function and / or the related information of the AI model with a specific model function, the AI model to be activated within a specific area and / or the related information of the AI model to be activated within a specific area, and AI models enabled in a specific network configuration and / or related information of AI models enabled in a specific network configuration, and AI models enabled in specific channel environment parameters and / or related information of AI models enabled in specific channel environment parameters, and AI models in an enabled state and / or related information of AI models in an enabled state, and AI models in an active state and / or related information of AI models in an active state, and AI models in a non-active state and / or related information of AI models in a non-active state, and It is used to request at least one of all AI models stored in the terminal and / or related information of all AI models stored in the terminal.

[0120] Step (4) The terminal may send terminal information feedback to the network-side device and include first AI model information.

[0121] In the embodiments of the present application, the first AI model information stored in the terminal by the first communication device is sent to the second communication device, thereby instructing the network side or the communication partner side of the first AI model stored in the terminal and / or related information of the first AI model. Thereby, the network side or the communication partner side can timely perform management such as appropriate configuration, update, activation, deactivation, etc. on the first AI model stored in the terminal, improve the management efficiency of the AI model, and avoid the terminal from repeatedly configuring the same model or models with the same function, saving resources.

[0122] FIG. 9 is one of the schematic structural diagrams of the AI model information transmission device according to the embodiments of the present application. As shown in FIG. 9, the AI model information transmission device 900 includes a first transmission module 910, where The first transmission module 910 is used to transmit first AI model information to a second communication device, where the first AI model information is used to indicate a first AI model and / or related information of the first AI model, and the first AI model is an AI model stored in a terminal. Here, the first communication device is the terminal, and the second communication device is a communication partner of the terminal, or the first communication device is a source cell for switching of the terminal, and the second communication device is a target cell for switching of the terminal, or the first communication device is a cell with an access history in an RRC recovery process of the terminal, and the second communication device is a new access cell in the RRC recovery process of the terminal.

[0123] The AI model information transmission device according to the embodiments of the present application realizes each process realized by the above method embodiments and can achieve the same technical effects. To avoid repetition of the description, it will not be described further here.

[0124] In the embodiments of the present application, the first communication device transmits first AI model information stored in a terminal to a second communication device, thereby instructing a first AI model stored in the terminal and / or related information of the first AI model to the network side or the communication partner side, so that the network side or the communication partner side can timely perform management such as appropriate configuration, update, activation, deactivation, etc. on the first AI model stored in the terminal, improve the management efficiency of the AI model, avoid the terminal from being repeatedly configured with the same model or models with the same function, and save resources.

[0125] Optionally, the first AI model information is a model identifier of the first AI model for uniquely identifying the first AI model, and a model function of the first AI model, and model activation conditions of the first AI model, and The model active state of the first AI model, and the model data size of the first AI model, and the model authentication information of the first AI model for the second communication device to identify or authenticate the first AI model, and at least one of the model structure information of the first AI model.

[0126] Optionally, the model activation condition is an activation area, and an activation time, and an activation configuration, and at least one of the activation channel environment parameters.

[0127] Optionally, the device further includes a second receiving module for receiving an AI model information request before the first communication device transmits the first AI model information to the second communication device, and the AI model information request is used to request the first AI model information.

[0128] Optionally, the AI model information request is the AI model corresponding to a specific model identifier range and / or the related information of the AI model corresponding to a specific model identifier range, and the AI model with a specific model function and / or the related information of the AI model with a specific model function, and the AI model to be activated within a specific area and / or the related information of the AI model to be activated within a specific area, and the AI model to be activated with a specific network configuration and / or the related information of the AI model to be activated with a specific network configuration, and the AI model to be activated with specific channel environment parameters and / or the related information of the AI model to be activated with specific channel environment parameters, and the AI model in an activated state and / or the related information of the AI model in an activated state, and the AI model in an active state and / or the related information of the AI model in an active state, and The AI model in the inactive state and / or the related information of the AI model in the inactive state, and is used to request at least one of all the AI models stored in the terminal and / or the related information of all the AI models stored in the terminal.

[0129] Optionally, when the first communication device is the terminal and the second communication device is the communication partner of the terminal, the apparatus further includes a first determination module for determining second AI model information before the first communication device transmits the first AI model information to the second communication device, and the second AI model information is used to indicate a second AI model and / or related information of the second AI model, and the second AI model is an AI model supported by the second communication device.

[0130] Optionally, the apparatus further includes a second transmission module for transmitting first instruction information to the second communication device after the first communication device determines the second AI model information, and the first instruction information is used to characterize that the second AI model exists in the first communication device and / or an AI model that matches the related information of the second AI model exists.

[0131] Optionally, the first determination module receives broadcast information from the second communication device, and is used to determine the second AI model information based on the broadcast information.

[0132] Optionally, the apparatus further includes a third transmission module for transmitting second instruction information to the second communication device, and the second instruction information is used to characterize that an AI model exists in the terminal and / or the terminal has model inference capabilities.

[0133] Optionally, when the first communication device is the source cell for the handover and the second communication device is the target cell for the handover, the first AI model information is included in the handover request.

[0134] Optionally, when the first communication device is a cell with an access history in the RRC recovery process and the second communication device is a new access cell in the RRC recovery process, the first AI model information is included in the terminal context information.

[0135] In an embodiment of the present application, the first AI model information stored in the terminal by the first communication device is transmitted to the second communication device, thereby instructing the network side or the communication partner side about the first AI model stored in the terminal and / or related information of the first AI model. As a result, the network side or the communication partner side can timely perform management such as appropriate configuration, update, activation, deactivation, etc. on the first AI model stored in the terminal, improving the management efficiency of the AI model, avoiding the terminal from being repeatedly configured with the same model or models with the same function, and saving resources.

[0136] The AI model information transmission device in the embodiment of the present application may be an electronic device, for example, an electronic device having an operating system, or may be a component in the electronic device, for example, an integrated circuit or a chip. This electronic device may be a terminal or may be other devices other than the terminal. Exemplarily, the terminal may include the types of terminal 11 listed above, but is not limited thereto. Other devices may be a server, a Network Attached Storage (NAS), etc., and the embodiments of the present application do not specifically limit this.

[0137] The AI model information transmission device according to the embodiment of the present application realizes each process realized by the method embodiments in FIGS. 4 to 8 and can achieve the same technical effects. To avoid repeated description, it will not be described further here.

[0138] Figure 10 is the second schematic diagram of the structure of the AI model information transmission device according to the embodiment of the present application. As shown in Figure 10, the AI model information transmission device 1000 includes a first receiving module 1010. Here, The first receiving module 1010 is used to receive the first AI model information from the first communication device. The first AI model information is used to indicate the first AI model and / or the related information of the first AI model. The first AI model is an AI model stored in the terminal. Here, the first communication device is the terminal, and the second communication device is the communication partner side of the terminal, or The first communication device is the source cell of the terminal's handover, and the second communication device is the target cell of the terminal's handover, or The first communication device is the cell with access history in the RRC recovery process of the terminal, and the second communication device is the new access cell in the RRC recovery process of the terminal.

[0139] The AI model information transmission device according to the embodiment of the present application realizes each process realized by the above method embodiments and can achieve the same technical effects. To avoid repeated description, it will not be described further here.

[0140] In the embodiment of the present application, the first communication device transmits the first AI model information stored in the terminal to the second communication device, thereby indicating the first AI model and / or the related information of the first AI model stored in the terminal to the network side or the communication partner side. Thereby, the network side or the communication partner side can timely perform management such as appropriate configuration, update, activation, and deactivation on the first AI model stored in the terminal, improve the management efficiency of the AI model, avoid the terminal from being repeatedly configured with the same model or models with the same function, and save resources.

[0141] Optionally, the first AI model information is The model identifier of the first AI model for uniquely identifying the first AI model, The model function of the first AI model, The model activation condition of the first AI model, The model active state of the first AI model, The model data size of the first AI model, The model authentication information of the first AI model for the second communication device to identify or authenticate the first AI model, At least one of the model structure information of the first AI model.

[0142] Optionally, the model activation condition An activation area, An activation time, An activation configuration, At least one of the activation channel environment parameters.

[0143] Optionally, the device Before the second communication device receives the first AI model information from the first communication device, further includes a fourth transmission module for transmitting an AI model information request to the first communication device, and the AI model information request is used to request the first AI model information.

[0144] Optionally, the AI model information request The AI model corresponding to a specific model identifier range and / or the related information of the AI model corresponding to a specific model identifier range, The AI model with a specific model function and / or the related information of the AI model with a specific model function, The AI model activated within a specific area and / or the related information of the AI model activated within a specific area, The AI model activated with a specific network configuration and / or the related information of the AI model activated with a specific network configuration, The AI model enabled with specific channel environment parameters and / or related information of the AI model enabled with specific channel environment parameters, and The AI model in the enabled state and / or related information of the AI model in the enabled state, and The AI model in the active state and / or related information of the AI model in the active state, and The AI model in the inactive state and / or related information of the AI model in the inactive state, and It is used to request at least one of all the AI models stored in the terminal and / or related information of all the AI models stored in the terminal.

[0145] Optionally, when the first communication device is the terminal and the second communication device is the communication partner of the terminal, the apparatus Further includes a broadcast module for broadcasting second AI model information, where the second AI model information is used to indicate a second AI model and / or related information of the second AI model, and the second AI model is an AI model supported by the second communication device.

[0146] Optionally, the apparatus A third receiving module for receiving first instruction information from the first communication device after the second communication device broadcasts the second AI model information, and Based on the first instruction information, further includes a second determination module for determining that the second AI model exists in the first communication device and / or an AI model that matches the related information of the second AI model exists.

[0147] Optionally, the apparatus A fourth receiving module for receiving second instruction information from the first communication device, and Based on the second instruction information, further includes a third determination module for determining that an AI model exists in the terminal and / or the terminal has model inference capabilities.

[0148] Optionally, when the first communication device is the source cell of the handover and the second communication device is the target cell of the handover, the first AI model information is included in the handover request.

[0149] Optionally, when the first communication device is the cell with access history in the RRC recovery process and the second communication device is the latest access cell in the RRC recovery process, the first AI model information is included in the terminal context information.

[0150] The AI model information transmission method according to the embodiments of the present application may have an execution entity as an AI model information transmission device. In the embodiments of the present application, taking the example that the AI model information transmission device executes the AI model information transmission method, the AI model information transmission device according to the embodiments of the present application will be described.

[0151] The AI model information transmission device in the embodiments of the present application may be an electronic device, such as an electronic device having an operating system, or a component in the electronic device, such as an integrated circuit or a chip. This electronic device may be a terminal or other device other than the terminal. Exemplarily, the terminal may include, but is not limited to, the types of the terminals 11 listed above, and other devices may be a server, a Network Attached Storage (NAS), etc., and the embodiments of the present application do not specifically limit this.

[0152] The AI model information transmission device according to the embodiments of the present application realizes each process realized by the method embodiments in FIGS. 5 to 8 and can achieve the same technical effects, and for the sake of avoiding repeated description, it will not be described further here.

[0153] Optionally, FIG. 11 is a schematic structural diagram of a communication device according to an embodiment of the present application. As shown in FIG. 11, the embodiment of the present application further provides a communication device 1100, which includes a processor 1101 and a memory 1102. The memory 1102 stores a program or instruction that can be executed on the processor 1101. For example, when this communication device 1100 is a first communication device, when this program or instruction is executed by the processor 1101, each step of the embodiment of the above AI model information transmission method can be realized, and the same technical effect can be achieved. When this communication device 1100 is a second communication device, when this program or instruction is executed by the processor 1101, each step of the embodiment of the above AI model information transmission method can be realized, and the same technical effect can be achieved. To avoid repetition of the description, it will not be described further here.

[0154] The embodiment of the present application further provides a first communication device including a processor and a communication interface. Here, the communication interface is used to transmit first AI model information to a second communication device. The first AI model information is used to indicate a first AI model and / or related information of the first AI model. The first AI model is an AI model stored in a terminal. Here, the first communication device is the terminal, and the second communication device is the communication partner side of the terminal, or the first communication device is the source cell of the terminal's handover, and the second communication device is the target cell of the terminal's handover, or the first communication device is a cell with an access history in the RRC recovery process of the terminal, and the second communication device is a new access cell in the RRC recovery process of the terminal.

[0155] This first embodiment of the communication device corresponds to the embodiment of the first communication device side method. Each implementation process and realization method of the embodiment of the method can be applied to this first embodiment of the communication device and can achieve the same technical effect. FIG. 12 is a schematic diagram of the hardware structure of the first communication device for realizing the embodiment of the present application.

[0156] The first communication device may be the terminal 1200, and this terminal 1200 includes at least some of the components such as a radio frequency unit 1201, a network module 1202, an audio output unit 1203, an input unit 1204, a sensor 1205, a display unit 1206, a user input unit 1207, an interface unit 1208, a memory 1209, and a processor 1210, but is not limited thereto.

[0157] As can be understood by those skilled in the art, the terminal 1200 may further include a power source (for example, a battery) for supplying power to each component. The power source may be logically connected to the processor 1210 by a power management system, so that functions such as charge and discharge management and power consumption management can be realized by the power management system. The terminal structure shown in FIG. 12 does not constitute a limitation on the terminal. The terminal may include more or fewer components than the number of components shown in the figure, or a combination of some components, or a configuration of different components, which will not be described further here.

[0158] It should be understood that, in the embodiments of the present application, the input unit 1204 may include a graphics processing unit (GPU) 12041 and a microphone 12042. The graphics processing unit 12041 processes the image data of a still image or video obtained by an image capture device (e.g., a camera) in a video capture mode or an image capture mode. The display unit 1206 may include a display panel 12061, and the display panel 12061 may be configured in the form of a liquid crystal display, an organic light-emitting diode, etc. The user input unit 1207 includes at least one of a touch panel 12071 and other input devices 12072. The touch panel 12071 is also called a touch screen. The touch panel 12071 may include two parts, a touch detection device and a touch controller. The other input devices 12072 may include, but are not limited to, a physical keyboard, function keys (e.g., volume control buttons, switch buttons, etc.), a trackball, a mouse, an operation lever, and will not be described further herein.

[0159] In the embodiments of the present application, after receiving the downlink data from the network-side device, the radio frequency unit 1201 can transmit it to the processor 1210 for processing, and the radio frequency unit 1201 can also transmit the uplink data to the network-side device. Generally, the radio frequency unit 1201 includes, but is not limited to, an antenna, an amplifier, a transceiver, a coupler, a low-noise amplifier, a duplexer, etc.

[0160] Memory 1209 may be used to store software programs or instructions, and various types of data. Memory 1209 may mainly include a first storage area for storing programs or instructions and a second storage area for storing data. Here, the first storage area can store an operating system, application programs or instructions required for at least one function (for example, audio playback function, image playback function, etc.). Also, Memory 1209 may include volatile memory or non-volatile memory, or Memory 1209 may include both volatile and non-volatile memory. Here, the non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may be a random access memory (RAM), a static random access memory (SRAM), a dynamic random access memory (DRAM), a synchronous dynamic random access memory (SDRAM), a double data rate synchronous dynamic random access memory (DDR SDRAM), an enhanced synchronous dynamic random access memory (ESDRAM), a synchronous link dynamic random access memory (SLDRAM), and a direct rambus random access memory (DRRAM). The Memory 1209 in the embodiments of the present application includes these and any other suitable types of memory, but is not limited thereto.

[0161] Processor 1210 may include one or more processing units. Optionally, processor 1210 integrates an application processor and a modem processor. Here, the application processor mainly processes operations related to the operating system, user interface, application programs, etc., and the modem processor mainly processes wireless communication signals, for example, a baseband processor. As can be understood, the above modem processor may not be integrated into processor 1210.

[0162] Optionally, processor 1210 is used to transmit first AI model information to a second communication device, where the first AI model information is used to indicate a first AI model and / or related information of the first AI model, and the first AI model is an AI model stored in the terminal. Here, the first communication device is the terminal, and the second communication device is the communication partner of the terminal, or the first communication device is the source cell for the terminal's handover, and the second communication device is the target cell for the terminal's handover, or the first communication device is a cell with an access history in the RRC recovery process of the terminal, and the second communication device is a new access cell in the RRC recovery process of the terminal.

[0163] In an embodiment of the present application, the first AI model information stored in the terminal by the first communication device is transmitted to the second communication device, thereby instructing the network side or the communication partner side of the first AI model and / or related information of the first AI model stored in the terminal, so that the network side or the communication partner side can timely perform management such as appropriate configuration, update, activation, deactivation, etc. on the first AI model stored in the terminal, improve the management efficiency of the AI model, avoid the terminal from being repeatedly configured with the same model or models with the same function, and save resources.

[0164] Optionally, the first AI model information includes a model identifier of the first AI model for uniquely identifying the first AI model, a model function of the first AI model, a model activation condition of the first AI model, a model active state of the first AI model, a model data size of the first AI model, model authentication information of the first AI model for the second communication device to identify or authenticate the first AI model, and at least one of model structure information of the first AI model.

[0165] Optionally, the model activation condition includes an activation area, an activation time, an activation configuration, and at least one of activation channel environment parameters.

[0166] Optionally, the processor 1210 is used to receive an AI model information request before the first communication device transmits the first AI model information to the second communication device, and the AI model information request is used to request the first AI model information.

[0167] Optionally, the AI model information request includes an AI model corresponding to a specific model identifier range and / or related information of an AI model corresponding to a specific model identifier range, an AI model with a specific model function and / or related information of an AI model with a specific model function, an AI model to be activated within a specific area and / or related information of an AI model to be activated within a specific area, an AI model to be activated with a specific network configuration and / or related information of an AI model to be activated with a specific network configuration. ​AI models enabled by specific channel environment parameters and / or related information of AI models enabled by specific channel environment parameters, and AI models in an enabled state and / or related information of AI models in an enabled state, and AI models in an active state and / or related information of AI models in an active state, and AI models in a non-active state and / or related information of AI models in a non-active state, and It is used to request at least one of all AI models stored in the terminal and / or related information of all AI models stored in the terminal.

[0168] Optionally, when the first communication device is the terminal and the second communication device is the communication partner side of the terminal, the processor 1210 is used to determine second AI model information before the first communication device transmits the first AI model information to the second communication device, and the second AI model information is used to indicate a second AI model and / or related information of the second AI model, and the second AI model is an AI model supported by the second communication device.

[0169] Optionally, the processor 1210 After the first communication device determines the second AI model information, it transmits first instruction information to the second communication device, and the first instruction information is used to characterize that the second AI model exists in the first communication device and / or an AI model that matches the related information of the second AI model exists.

[0170] Optionally, the processor 1210 receives broadcast information from the second communication device, and is used to determine the second AI model information based on the broadcast information.

[0171] Optionally, the processor 1210 Send second instruction information to the second communication device, where the second instruction information is used to characterize that an AI model exists in the terminal and / or the terminal has model inference capabilities.

[0172] Optionally, when the first communication device is the source cell for the handover and the second communication device is the target cell for the handover, the first AI model information is included in the handover request.

[0173] Optionally, when the first communication device is a cell with an access history in the RRC recovery process and the second communication device is a new access cell in the RRC recovery process, the first AI model information is included in the terminal context information.

[0174] In an embodiment of the present application, the first AI model information stored in the terminal by the first communication device is sent to the second communication device, thereby instructing the network side or the communication partner side of the first AI model and / or related information of the first AI model stored in the terminal, so that the network side or the communication partner side can timely perform management such as appropriate configuration, update, activation, deactivation, etc. on the first AI model stored in the terminal, improve the management efficiency of the AI model, avoid the terminal being repeatedly configured with the same model or models with the same function, and save resources.

[0175] The embodiment of the present application further provides a second communication device including a processor and a communication interface, where the communication interface receives the first AI model information from the first communication device, and the first AI model information is used to instruct the first AI model and / or related information of the first AI model, and the first AI model is an AI model stored in the terminal, where the first communication device is the terminal, the second communication device is the communication partner side of the terminal, or The first communication device is the source cell for the switching of the terminal, and the second communication device is the target cell for the switching of the terminal, or The first communication device is a cell with access history in the RRC recovery process of the terminal, and the second communication device is a new access cell in the RRC recovery process of the terminal.

[0176] This embodiment of the second communication device corresponds to the embodiment of the second communication device method. Each implementation process and realization method of the embodiment of the method can be applied to this embodiment of the second communication device, and the same technical effect can be achieved.

[0177] Specifically, the embodiment of the present application further provides a second communication device. FIG. 13 is a schematic hardware structure diagram for realizing the second communication device of the embodiment of the present application. As shown in FIG. 13, this second device 1300 includes a processor 1301, a network interface 1302, and a memory 1303. Here, the network interface 1302 is, for example, a common public radio interface (CPRI).

[0178] Specifically, the second device 1300 of the embodiment of the present invention further includes instructions or programs stored in the memory 1303 and executable on the processor 1301. The processor 1301 calls the instructions or programs in the memory 1303 to execute the method executed by each module shown in FIG. 10, and the same technical effect can be achieved. To avoid repetition of the description, it will not be described further here.

[0179] Optionally, the processor 1301 receives first AI model information from the first communication device, and the first AI model information is used to indicate a first AI model and / or related information of the first AI model. The first AI model is an AI model stored in the terminal. Here, the first communication device is the terminal, the second communication device is the communication partner side of the terminal, or the first communication device is the source cell for the terminal's handover, the second communication device is the target cell for the terminal's handover, or the first communication device is the cell with access history in the RRC recovery process of the terminal, and the second communication device is the new access cell in the RRC recovery process of the terminal.

[0180] In the embodiments of the present application, the first AI model information stored in the terminal by the first communication device is transmitted to the second communication device, thereby instructing the network side or the communication partner side to obtain the first AI model stored in the terminal and / or related information of the first AI model. As a result, the network side or the communication partner side can timely perform management such as appropriate configuration, update, activation, deactivation, etc. on the first AI model stored in the terminal, improve the management efficiency of the AI model, avoid the terminal from being repeatedly configured with the same model or models with the same function, and save resources.

[0181] Optionally, the first AI model information includes the model identifier of the first AI model for uniquely identifying the first AI model, and the model function of the first AI model, and the model activation condition of the first AI model, and the model active state of the first AI model, and the model data size of the first AI model, and the model authentication information of the first AI model for the second communication device to identify or authenticate the first AI model, and at least one of the model structure information of the first AI model.

[0182] Optionally, the model activation condition includes the activation area, and the activation time, and the activation configuration, including at least one of the activation channel environment parameters.

[0183] Optionally, the processor 1301 is used to send an AI model information request to the first communication device before the second communication device receives the first AI model information from the first communication device, and the AI model information request is used to request the first AI model information.

[0184] Optionally, the AI model information request is used to request at least one of the AI model corresponding to a specific model identifier range and / or the related information of the AI model corresponding to a specific model identifier range, the AI model of a specific model function and / or the related information of the AI model of a specific model function, the AI model to be activated within a specific area and / or the related information of the AI model to be activated within a specific area, the AI model to be activated with a specific network configuration and / or the related information of the AI model to be activated with a specific network configuration, the AI model to be activated with specific channel environment parameters and / or the related information of the AI model to be activated with specific channel environment parameters, the AI model in an activated state and / or the related information of the AI model in an activated state, the AI model in an active state and / or the related information of the AI model in an active state, the AI model in an inactive state and / or the related information of the AI model in an inactive state, is used to request at least one of all the AI models stored in the terminal and / or the related information of all the AI models stored in the terminal.

[0185] Optionally, when the first communication device is the terminal and the second communication device is the communication partner side of the terminal, the processor 1301 It is used to broadcast the second AI model information, and the second AI model information is used to indicate the second AI model and / or related information of the second AI model, and the second AI model is an AI model supported by the second communication device.

[0186] Optionally, the processor 1301 After the second communication device broadcasts the second AI model information, it receives first instruction information from the first communication device, Based on the first instruction information, it is used to determine that the second AI model exists in the first communication device and / or an AI model that matches the related information of the second AI model exists.

[0187] Optionally, the processor 1301 is used to receive second instruction information from the first communication device, Based on the second instruction information, it is determined that an AI model exists in the terminal and / or the terminal has model inference capabilities.

[0188] Optionally, when the first communication device is the source cell for the handover and the second communication device is the target cell for the handover, the first AI model information is included in the handover request.

[0189] Optionally, when the first communication device is a cell with an access history in the RRC recovery process and the second communication device is the latest access cell in the RRC recovery process, the first AI model information is included in the terminal context information.

[0190] The AI model information transmission method according to the embodiments of the present application may have an AI model information transmission device as the execution subject. In the embodiments of the present application, taking the AI model information transmission device executing the AI model information transmission method as an example, the AI model information transmission device according to the embodiments of the present application is described.

[0191] Embodiments of the present application further provide a readable storage medium, on which a program or instructions are stored. When the program or instructions are executed by a processor, each process of the embodiments of the above AI model information transmission method can be realized, and the same technical effect can be achieved. To avoid repetition of the description, it will not be described further here.

[0192] Here, the processor is the processor in the terminal in the above embodiments. The readable storage medium includes computer-readable storage media, such as computer read-only memory ROM, random access memory RAM, magnetic disk or optical disk, etc.

[0193] Embodiments of the present application further provide a chip, which includes a processor and a communication interface. The communication interface is coupled to the processor. The processor is used to run a program or instructions to realize each process of the embodiments of the above AI model information transmission method, and the same technical effect can be achieved. To avoid repetition of the description, it will not be described further here.

[0194] It should be understood that the chip mentioned in the embodiments of the present application may also be called a system-level chip, system chip, chip system or system-on-chip, etc.

[0195] Embodiments of the present application further provide a computer program / program product, which is stored in a storage medium. When the computer program / program product is executed by at least one processor, each process of the embodiments of the above AI model information transmission method can be realized, and the same technical effect can be achieved. To avoid repetition of the description, it will not be described further here.

[0196] An embodiment of the present application further provides an AI model information transmission system including a first communication device and a second communication device. The first communication device may be used to execute the steps of the above AI model information transmission method, and the second communication device may be used to execute the steps of the above AI model information transmission method.

[0197] It should be noted that in this specification, the term "including", "being included", or any other deformation thereof is intended to cover non-exclusive "including", whereby a process, method, article, or device including a series of elements includes not only those elements but also other elements not explicitly listed, or elements specific to such a process, method, article, or device. When there is no further limitation, for an element limited by the phrase "including one...", it is not excluded that there are other same elements in the process, method, article, or device including this element. It should be pointed out that the scope of the methods and devices in the embodiments of the present application is not limited to executing functions in the order shown or discussed, and may include executing functions in a basically simultaneous manner or in a reverse order based on the related functions. For example, a method described in a procedure different from that described may be executed, and additions, omissions, or combinations may be made for various steps. Also, features described with reference to some examples can be combined in other examples.

[0198] As can be clearly understood by those skilled in the art from the description of the above embodiments, the method of the above embodiments can be implemented by means of software and the necessary general-purpose hardware platform. Of course, it may also be implemented by hardware, but in many cases, the former is a more preferred embodiment. Based on such an understanding, the technical solution of this application may, in essence, or the part that contributes to the prior art may be embodied in the form of a computer software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes several instructions for causing a terminal (which may be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in each embodiment of this application.

[0199] The above has described the embodiments of this application in conjunction with the drawings, but this application is not limited to the above specific embodiments. The above specific embodiments are merely illustrative and not restrictive. Those skilled in the art can make many forms without departing from the spirit of this application and the scope protected by the claims, and all belong to the protection scope of this application.

Claims

1. An AI model information transmission method, comprising: a first communication device transmitting first AI model information to a second communication device, where the first AI model information is used to indicate a first AI model and / or related information of the first AI model, and the first AI model is an artificial intelligence (AI) model stored in a terminal; wherein the first communication device is the terminal, and the second communication device is a communication partner of the terminal, or the first communication device is a source cell for switching of the terminal, and the second communication device is a target cell for switching of the terminal, or the first communication device is a cell with an access history in a radio resource control (RRC) recovery process of the terminal, and the second communication device is a new access cell in the RRC recovery process of the terminal. The AI model information transmission method.

2. The first AI model information includes: a model identifier of the first AI model for uniquely identifying the first AI model; a model function of the first AI model; a model activation condition of the first AI model; a model active state of the first AI model; a model data size of the first AI model; model authentication information of the first AI model for the second communication device to identify or authenticate the first AI model; and at least one of model structure information of the first AI model. The AI model information transmission method according to claim 1.

3. The model activation condition includes at least one of: an activation area; an activation time; an activation configuration; and an activation channel environment parameter. The AI model information transmission method according to claim 2.

4. Before the first communication device transmits the first AI model information to the second communication device, the method further includes: the first communication device receiving an AI model information request, where the AI model information request is used to request the first AI model information. The AI model information transmission method according to any one of claims 1 to 3.

5. The AI model information request includes: an AI model corresponding to a specific model identifier range and / or related information of an AI model corresponding to a specific model identifier range; and an AI model with a specific model function and / or related information of an AI model with a specific model function. The AI model activated within a specific area and / or the related information of the AI model activated within a specific area, and The AI model activated with a specific network configuration and / or the related information of the AI model activated with a specific network configuration, and The AI model activated with specific channel environment parameters and / or the related information of the AI model activated with specific channel environment parameters, and The AI model in an activated state and / or the related information of the AI model in an activated state, and The AI model in an active state and / or the related information of the AI model in an active state, and The AI model in a non-active state and / or the related information of the AI model in a non-active state, and The AI model information transmission method according to claim 4, which is used to request at least one of all the AI models stored in the terminal and / or the related information of all the AI models stored in the terminal.

6. When the first communication device is the terminal and the second communication device is the communication partner side of the terminal, before the first communication device transmits the first AI model information to the second communication device, the method includes: The first communication device further includes determining second AI model information, where the second AI model information is used to indicate a second AI model and / or related information of the second AI model, and the second AI model is an AI model supported by the second communication device. The AI model information transmission method according to any one of claims 1 to 5.

7. After the first communication device determines the second AI model information, the method includes: The first communication device further includes transmitting first instruction information to the second communication device, where the first instruction information is used to characterize that the second AI model exists in the first communication device and / or an AI model that matches the related information of the second AI model exists. The AI model information transmission method according to claim 6.

8. The determination of the second AI model information by the first communication device includes: The first communication device receives broadcast information from the second communication device, and The first communication device determines the second AI model information based on the broadcast information. The AI model information transmission method according to claim 6 or 7.

9. The method includes: The first communication device further includes transmitting second instruction information to the second communication device, where the second instruction information is used to characterize that an AI model exists in the terminal and / or the terminal has model inference capabilities. The AI model information transmission method according to any one of claims 1 to 8.

10. When the first communication device is the source cell of the handover and the second communication device is the target cell of the handover, the first AI model information is included in the handover request. The AI model information transmission method according to any one of claims 1 to 5.

11. When the first communication device is a cell with access history in the RRC recovery process and the second communication device is a new access cell in the RRC recovery process, the first AI model information is included in the terminal context information. The AI model information transmission method according to any one of claims 1 to 5.

12. An AI model information transmission method, wherein the second communication device includes receiving first AI model information from the first communication device, and the first AI model information is used to indicate a first AI model and / or related information of the first AI model, and the first AI model is an AI model stored in the terminal. Here, the first communication device is the terminal, and the second communication device is the communication partner side of the terminal, or the first communication device is the source cell of the handover of the terminal, and the second communication device is the target cell of the handover of the terminal, or the first communication device is a cell with access history in the RRC recovery process of the terminal, and the second communication device is a new access cell in the RRC recovery process of the terminal. The AI model information transmission method.

13. The first AI model information includes a model identifier of the first AI model for uniquely identifying the first AI model, a model function of the first AI model, a model activation condition of the first AI model, a model active state of the first AI model, a model data size of the first AI model, model authentication information of the first AI model for the second communication device to identify or authenticate the first AI model, The AI model information transmission method according to claim 12, including at least one of the model structure information of the first AI model.

14. The model activation condition is an activation area, an activation time, an activation configuration, The AI model information transmission method according to claim 13, including at least one of activation channel environment parameters.

15. Before the second communication device receives the first AI model information from the first communication device, the method further includes the second communication device further sending an AI model information request to the first communication device, and the AI model information request is used to request the first AI model information. The AI model information transmission method according to any one of claims 12 to 14.

16. The AI model information request is an AI model corresponding to a specific model identifier range and / or related information of an AI model corresponding to a specific model identifier range, an AI model with a specific model function and / or related information of an AI model with a specific model function, an AI model activated within a specific area and / or related information of an AI model activated within a specific area, an AI model activated with a specific network configuration and / or related information of an AI model activated with a specific network configuration, an AI model activated with specific channel environment parameters and / or related information of an AI model activated with specific channel environment parameters, an AI model in an activated state and / or related information of an AI model in an activated state, an AI model in an active state and / or related information of an AI model in an active state, an AI model in a non-active state and / or related information of an AI model in a non-active state, The AI model information transmission method according to claim 15, used to request at least one of all AI models stored in the terminal and / or related information of all AI models stored in the terminal.

17. When the first communication device is the terminal and the second communication device is the communication partner side of the terminal, the method The second communication device further includes broadcasting second AI model information, where the second AI model information is used to indicate a second AI model and / or related information of the second AI model, and the second AI model is an AI model supported by the second communication device. The AI model information transmission method according to any one of claims 12 to 16.

18. After the second communication device broadcasts the second AI model information, the method includes: The second communication device receives first instruction information from a first communication device. The second communication device further includes determining, based on the first instruction information, that the second AI model exists in the first communication device and / or an AI model that matches the related information of the second AI model exists. The AI model information transmission method according to claim 17.

19. The method includes: The second communication device receives second instruction information from a first communication device. The second communication device further includes determining, based on the second instruction information, that an AI model exists in the terminal and / or the terminal has model inference capabilities. The AI model information transmission method according to any one of claims 12 to 18.

20. When the first communication device is a source cell for handover and the second communication device is a target cell for the handover, the first AI model information is included in a handover request. The AI model information transmission method according to any one of claims 12 to 16.

21. When the first communication device is a cell with an access history in an RRC recovery process and the second communication device is the latest access cell in the RRC recovery process, the first AI model information is included in terminal context information. The AI model information transmission method according to any one of claims 12 to 16.

22. An AI model information transmission device, comprising: A first transmission module for transmitting first AI model information to a second communication device, where the first AI model information is used to indicate a first AI model and / or related information of the first AI model, and the first AI model is an AI model stored in a terminal. Here, the first communication device is the terminal, and the second communication device is a communication partner of the terminal, or The first communication device is the source cell for the switching of the terminal, the second communication device is the target cell for the switching of the terminal, or The first communication device is a cell with an access history in the RRC recovery process of the terminal, and the second communication device is a new access cell in the RRC recovery process of the terminal, an AI model information transmission device.

23. The first AI model information includes a model identifier of the first AI model for uniquely identifying the first AI model, a model function of the first AI model, a model activation condition of the first AI model, a model active state of the first AI model, a model data size of the first AI model, model authentication information of the first AI model for the second communication device to identify or authenticate the first AI model, and at least one of model structure information of the first AI model, the AI model information transmission device according to claim 22.

24. The model activation condition includes: an activation area, an activation time, an activation configuration, and at least one of activation channel environment parameters, the AI model information transmission device according to claim 23.

25. An AI model information transmission device, comprising a first receiving module for receiving first AI model information from a first communication device, the first AI model information being used to indicate a first AI model and / or related information of the first AI model, the first AI model being an AI model stored in a terminal, wherein the first communication device is the terminal, the second communication device is the communication partner side of the terminal, or the first communication device is the source cell for the switching of the terminal, the second communication device is the target cell for the switching of the terminal, or the first communication device is a cell with an access history in the RRC recovery process of the terminal, and the second communication device is a new access cell in the RRC recovery process of the terminal, an AI model information transmission device.

26. A first communication device, comprising a processor and a memory, the memory storing a program or instruction that can run on the processor, and when the program or instruction is executed by the processor, realizing the steps of the AI model information transmission method according to any one of claims 1 to 11.

27. A second communication device comprising a processor and a memory, the memory storing a program or instructions executable on the processor, and when the program or instructions are executed by the processor, realizing the steps of the AI model information transmission method according to any one of claims 12 to 21.

28. A readable storage medium storing a program or instructions, and when the program or instructions are executed by a processor, realizing the steps of the AI model information transmission method according to any one of claims 1 to 11 or the steps of the AI model information transmission method according to any one of claims 12 to 21.

Images