Information transmitting and receiving method and device

Abstract

The embodiment of the invention provides an information transmitting and receiving method and device. The method comprises the following steps that: terminal equipment sends request information for acquiring an AI model to network equipment, and receives feedback information which is sent by the network equipment and responds to the request information;

Description

Information sending and receiving method and device Technical Field

[0001] The embodiments of the present application relate to the field of communication technologies. Background Art

[0002] To support diverse application scenarios and provide different types of services, wireless networks require more intelligent design, deployment, and operations. However, with the increasing complexity of 5G New Radio (NR) networks, traditional network design, deployment, and operations methods are increasingly unable to meet these demands. Artificial Intelligence (AI) and Machine Learning (ML) technologies provide a crucial tool for optimizing 5G wireless networks.

[0003] With the development of AI / ML technology, applying AI / ML technology to the physical layer of wireless communications to optimize the delay, load, accuracy and other difficulties in existing systems has become a current technical direction.

[0004] It should be noted that the above introduction to the technical background is merely intended to provide a clear and complete description of the technical solutions of this application and facilitate understanding by those skilled in the art. Simply because these solutions are described in the background technology section of this application, it should not be assumed that the above technical solutions are well known to those skilled in the art.

[0005] Summary of the Invention

[0006] However, the inventors found that when the network stores numerous AI models with different functions, performances and / or complexities, how the terminal device obtains the appropriate AI model is a problem that needs to be solved.

[0007] To address at least one of the above problems, embodiments of the present application provide a method and apparatus for sending and receiving information.

[0008] According to one aspect of an embodiment of the present application, there is provided an information transceiver device, including:

[0009] A first sending unit, which sends request information for obtaining an AI model to a network device;

[0010] A first receiving unit is configured to receive feedback information sent by the network device in response to the request information.

[0011] According to another aspect of an embodiment of the present application, there is provided an information transceiver device, including:

[0012] A second receiving unit receives a request for obtaining an AI model from a terminal device;

[0013] The second sending unit sends feedback information in response to the request information to the terminal device.

[0014] According to another aspect of an embodiment of the present application, a communication system is provided, including a terminal device and / or a network device, wherein the terminal device includes the information transceiver device of the aforementioned aspect, and the network device includes the information transceiver device of the aforementioned aspect.

[0015] One of the beneficial effects of the embodiments of the present application is that: the terminal device sends a request for obtaining an AI model to the network device and receives feedback information sent by the network device. As a result, the terminal device can obtain a suitable AI model from the network device and can use the obtained AI model to optimize the system load and delay.

[0016] With reference to the following description and accompanying drawings, specific embodiments of the present application are disclosed in detail, indicating the manner in which the principles of the present application can be employed. It should be understood that the embodiments of the present application are not limited in scope. Within the spirit and scope of the appended claims, the embodiments of the present application include many variations, modifications and equivalents.

[0017] Features described and / or illustrated with respect to one embodiment may be used in the same or similar manner in one or more other embodiments, combined with features in other embodiments, or substituted for features in other embodiments.

[0018] It should be emphasized that the term "include / comprising" when used herein refers to the presence of features, integers, steps or components, but does not exclude the presence or addition of one or more other features, integers, steps or components. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The elements and features described in one figure or one embodiment of the present application can be combined with the elements and features shown in one or more other figures or embodiments. In addition, in the accompanying drawings, similar reference numerals represent corresponding parts in several figures and can be used to indicate corresponding parts used in more than one embodiment.

[0020] FIG1 is a schematic diagram of a communication system according to an embodiment of the present application;

[0021] FIG2 is a schematic diagram of a method for sending and receiving information according to an embodiment of the present application;

[0022] FIG3 is a schematic diagram of functional modules of a receiving / transmitting link of a terminal device according to an embodiment of the present application;

[0023] FIG4 is a schematic diagram of relevant identification information according to an embodiment of the present application;

[0024] FIG5 is a schematic diagram of a method for sending and receiving information according to an embodiment of the present application;

[0025] FIG6 is a schematic diagram of a method for sending and receiving information according to an embodiment of the present application;

[0026] FIG7 is a schematic diagram of an information transceiver device according to an embodiment of the present application;

[0027] FIG8 is a schematic diagram of an information transceiver according to an embodiment of the present application;

[0028] FIG9 is a schematic diagram of a method for sending and receiving information according to an embodiment of the present application;

[0029] FIG10 is a schematic diagram of a network device according to an embodiment of the present application;

[0030] FIG11 is a schematic diagram of a terminal device according to an embodiment of the present application. DETAILED DESCRIPTION

[0031] The above and other features of the present application will become apparent through the following description with reference to the accompanying drawings. In the description and the accompanying drawings, specific embodiments of the present application are disclosed in detail, which illustrate some embodiments in which the principles of the present application can be adopted. It should be understood that the present application is not limited to the described embodiments. On the contrary, the present application includes all modifications, variations and equivalents that fall within the scope of the appended claims.

[0032] In the embodiments of the present application, the terms "first", "second", etc. are used to distinguish different elements from the name, but do not indicate the spatial arrangement or temporal order of these elements, and these elements should not be limited by these terms. The term "and / or" includes any one and all combinations of one or more of the associated listed terms. The terms "comprising", "including", "having", etc. refer to the presence of the stated features, elements, components or components, but do not exclude the presence or addition of one or more other features, elements, components or components.

[0033] In the embodiments of this application, the singular forms "a," "the," etc. include plural forms and should be broadly understood to mean "a" or "a type" rather than being limited to "one." Furthermore, the term "said" should be understood to include both singular and plural forms, unless the context clearly indicates otherwise. Furthermore, the term "according to" should be understood to mean "at least in part based on...", and the term "based on" should be understood to mean "at least in part based on...", unless the context clearly indicates otherwise.

[0034] In the embodiments of the present application, the term "communication network" or "wireless communication network" may refer to a network that complies with any of the following communication standards, such as Long Term Evolution (LTE), enhanced Long Term Evolution (LTE-A, LTE-Advanced), Wideband Code Division Multiple Access (WCDMA), High-Speed ​​Packet Access (HSPA), etc.

[0035] Furthermore, communication between devices in the communication system may be carried out according to communication protocols of any stage, for example, including but not limited to the following communication protocols: 1G (generation), 2G, 2.5G, 2.75G, 3G, 4G, 4.5G and 5G, New Radio (NR), future 6G, etc., and / or other communication protocols currently known or to be developed in the future.

[0036] In the embodiments of the present application, the term "network device" refers to, for example, a device in a communication system that connects a terminal device to the communication network and provides services to the terminal device. Network devices may include, but are not limited to, the following devices: base station (BS), access point (AP), transmission reception point (TRP), broadcast transmitter, mobile management entity (MME), gateway, server, radio network controller (RNC), base station controller (BSC), etc.

[0037] Base stations may include, but are not limited to, NodeBs (NBs), evolved NodeBs (eNodeBs or eNBs), and 5G base stations (gNBs), among others. They may also include remote radio heads (RRHs), remote radio units (RRUs), relays, or low-power nodes (e.g., femeto, pico, etc.). The term "base station" may include some or all of their functions, and each base station may provide communication coverage for a specific geographic area. The term "cell" may refer to a base station and / or its coverage area, depending on the context in which the term is used.

[0038] In the embodiments of the present application, the term "user equipment" (UE) or "terminal equipment" (TE) refers to, for example, a device that accesses a communication network through a network device and receives network services. A terminal device can be fixed or mobile and may also be referred to as a mobile station (MS), a terminal, a subscriber station (SS), an access terminal (AT), a station, and so on.

[0039] Among them, terminal devices may include but are not limited to the following devices: cellular phones, personal digital assistants (PDAs), wireless modems, wireless communication devices, handheld devices, machine-type communication devices, laptop computers, cordless phones, smart phones, smart watches, digital cameras, etc.

[0040] For another example, in scenarios such as the Internet of Things (IoT), the terminal device can also be a machine or device for monitoring or measurement, including but not limited to: machine type communication (MTC) terminal, vehicle-mounted communication terminal, device-to-device (D2D) terminal, machine-to-machine (M2M) terminal, and so on.

[0041] In addition, the term "network side" or "network device side" refers to one side of the network, which can be a base station or one or more network devices as described above. The term "user side" or "terminal side" or "terminal device side" refers to the user or terminal side, which can be a UE or one or more terminal devices as described above. Unless otherwise specified herein, "device" can refer to either network equipment or terminal equipment.

[0042] The following describes the scenarios of the embodiments of the present application through examples, but the present application is not limited thereto.

[0043] FIG1 is a schematic diagram of a communication system according to an embodiment of the present application, schematically illustrating a situation using a terminal device and a network device as an example. As shown in FIG1 , a communication system 100 may include a network device 101 and terminal devices 102 and 103. For simplicity, FIG1 illustrates only two terminal devices and one network device as an example, but the embodiments of the present application are not limited thereto.

[0044] In the embodiment of the present application, existing services or future services can be transmitted between the network device 101 and the terminal devices 102 and 103. For example, these services may include but are not limited to: enhanced mobile broadband (eMBB), massive machine type communication (mMTC), and ultra-reliable and low-latency communication (URLLC), etc.

[0045] It is worth noting that FIG1 shows that both terminal devices 102 and 103 are within the coverage range of network device 101, but the present application is not limited thereto. Both terminal devices 102 and 103 may not be within the coverage range of network device 101, or one terminal device 102 may be within the coverage range of network device 101 while the other terminal device 103 is outside the coverage range of network device 101.

[0046] In the embodiments of the present application, the high-layer signaling may be, for example, radio resource control (RRC) signaling; for example, an RRC message, including, for example, an MIB, system information, or a dedicated RRC message; or an RRC information element (RRC IE). The high-layer signaling may also be, for example, MAC (Medium Access Control) signaling; or a MAC control element (MAC CE). However, the present application is not limited thereto.

[0047] The AI ​​model includes, but is not limited to, an input layer (input), multiple convolutional layers, a concatenation layer (concat), a fully connected layer (FC), and a quantizer. The processing results of multiple convolutional layers are merged in the concatenation layer. The specific structure of the AI ​​model can be found in existing technologies and will not be detailed here.

[0048] The inventors have discovered that AI models with different functions, parameters, and / or complexity can be trained offline. After training, due to the limited storage capacity of terminal devices, these AI models can usually be stored only in network devices. However, the current standards do not define how terminal devices can obtain AI models. To address the above issues, the embodiments of the present application provide a method and device for sending and receiving information, which are described below with reference to the accompanying figures and embodiments.

[0049] Embodiments of the first aspect

[0050] An embodiment of the present application provides a method for sending and receiving information, which is described from the perspective of a terminal device.

[0051] FIG2 is a schematic diagram of a method for sending and receiving information according to an embodiment of the present application. As shown in FIG2 , the method includes:

[0052] 201. The terminal device sends a request message for obtaining an AI model to the network device.

[0053] 202. The terminal device receives feedback information sent by the network device in response to the request information.

[0054] It is worth noting that FIG2 above is merely a schematic illustration of an embodiment of the present application, and the present application is not limited thereto. For example, the execution order of the various operations may be appropriately adjusted, and other operations may be added or some operations may be removed. Those skilled in the art may make appropriate modifications based on the above description, and are not limited to the description of FIG2 above.

[0055] In some embodiments, the network device may store multiple AI models with different functions, parameters and / or complexity, that is, multiple AI models are pre-stored in the network device.

[0056] In some embodiments, the function of the AI ​​model refers to some functions in the receiving and / or transmitting links of the terminal device. Figure 3 is a schematic diagram of the various functional modules included in the receiving and transmitting links of the terminal device in the embodiment of the present application. As shown in Figure 3, in the receiving link, it includes the following functional modules: receiving module, analog-to-digital conversion module, Fourier transform module, resource demapping module, channel state information (CSI) feedback module, beam measurement feedback module, terminal device positioning feedback module, channel estimation module, multiple input multiple output (MIMO) detection module, decoding module; in the transmitting link, it includes the following functional modules: sending module, digital-to-analog conversion module, inverse Fourier transform module, resource mapping module, precoding module, layer mapping module, modulation module, and coding module.

[0057] In some embodiments, the functions of the AI ​​model include an AI encoder model for CSI compression (or encoding) or an AI model for beam prediction or an AI model for terminal device positioning, etc.

[0058] For example, as shown in Figure 3, in the CSI feedback module, if the CSI feedback uses the type II or etype II codebook defined in existing standards, the feedback load is relatively large. Using an AI model to compress the channel coefficient matrix or the eigenvectors of the channel coefficient matrix can reduce the CSI feedback load and lower the CSI feedback overhead. Therefore, in the CSI feedback module, the terminal device can use an AI model (also called an AI encoder) to perform CSI compression (or encoding).

[0059] For example, as shown in Figure 3, in the beam measurement feedback module, beam measurement and feedback adopt the method defined by the existing standard. When beam scanning is performed on all synchronization signal blocks (SSBs), the RS load and the beam selection delay are relatively large. The AI ​​model can be used to predict the spatially optimal beam using the measurement results of a small number of beams, which can reduce the RS load and the beam selection delay. Therefore, in the beam measurement feedback module, the terminal device can use the AI ​​model to predict the optimal beam.

[0060] For example, as shown in Figure 3, in the terminal device positioning feedback module, if the terminal device is positioned using traditional methods, the terminal device cannot effectively distinguish between line-of-sight (LOS) and non-line-of-sight (NLOS) scenarios, resulting in low positioning accuracy. An AI model can be used to effectively classify whether the current terminal device is in a LOS or NLOS scenario, which can improve positioning accuracy. Therefore, in the terminal device positioning feedback module, the terminal device can use the AI ​​model to perform terminal device positioning.

[0061] The above is only an example. The AI ​​model can also be used in other functional modules in the receiving and / or transmitting links of the terminal device. That is to say, the functions of the AI ​​model can also be part of the functions in the receiving and / or transmitting links of other terminal devices other than the above examples. Examples will not be given one by one here.

[0062] In some embodiments, the parameters of the AI ​​model refer to the input parameters and output parameters of the AI ​​model, and the input parameters and output parameters include the dimensions and physical quantities of the input or output. The parameters of AI models with the same function can be the same or different (for example, the dimensions in the input / output parameters can be the same or different, and the input / output physical quantities can be the same or different). For example, for an AI encoder model used for CSI compression, the physical quantity of its input parameter can be an eigenvector representing the channel coefficient matrix, or a channel coefficient matrix with a dimension of X1×Y1×Z1×N, and the physical quantity of the output parameter can be a compressed channel eigenvector, or a channel coefficient matrix with a dimension of X2. For example, the number of transmitting antenna ports of a network device is 32, the number of receiving antenna ports of a terminal device is 2, the bandwidth of the communication system is 24 resource blocks (RBs), and the density of the channel state information-reference signal (CSI-RS) in the frequency domain is 0.5, that is, there is 1 CSI-RS signal on 2 RBs, so there are a total of 12 CSI-RS signals in the frequency domain. The physical quantity channel coefficient matrix of the input parameter has a dimension of 12×32×2×2 (i.e., the number of RSs in the frequency domain × the number of transmitting antenna ports of the network device × the number of receiving antenna ports of the terminal device × I / Q two-way). For another example, for the AI ​​model used for beam prediction, the physical quantity of its input parameter is the RSRP (Reference Signal Receiving Power) value of some beam pairs, or it can be the SINR (Signal to Interference plus Noise Ratio) value of some beam pairs. The input dimension is X1, and the physical quantity of the output parameter is the RSRP or SINR of all beam pairs. The output dimension is X2. For example, there are 12 downlink transmit beams and 8 receive beams, for a total of 96 beam pairs. Through configuration, the UE only measured the RSRP of 24 of the beam pairs. At this time, the dimension of the input parameter of the AI ​​model is 24, the physical quantity is RSRP, the dimension of the output parameter is 96, and the physical quantity is also RSRP.

[0063] In some embodiments, the complexity of the AI ​​model refers to the second amount of computing and / or second storage space actually required to deploy the AI ​​model. The computing amount can be expressed in floating-point operations per second (FLOPs). The second amount of computing required to deploy the AI ​​model is related to the input and output parameters (dimensions, channels, etc.) and convolution kernel size of the AI ​​model. The specific determination method can refer to the existing technology. The second storage space actually required to deploy the AI ​​model is related to the size of the AI ​​model (i.e., the number of bits / bytes / megabytes occupied by the deployment of the AI ​​model) and feature consumption (intermediate or final output results). The specific determination method can refer to the existing technology.

[0064] In some embodiments, different AI models mean that at least one of the functions, parameters and / or complexities of the AI ​​models is different. For example, the function of AI model A is for CSI compression, and the function of AI model B is for beam prediction, then AI model A and AI model B are different AI models. For example, the functions of AI models A and B are both for CSI compression, but the complexities and / or parameters of AI models A and B are different, then AI model A and AI model B are different AI models.

[0065] In some embodiments, the terminal device needs to use a suitable (corresponding) AI model when performing some functions in its receiving and / or transmitting link. Since multiple AI models are pre-stored in the network device, and the terminal device does not store these multiple AI models, the terminal device can obtain the required model by sending a request information for obtaining the AI ​​model to the network device. The request information includes the function identification information of the AI ​​model and / or the parameter information of the AI ​​model and / or the capability information of the AI ​​model that the terminal device can support.

[0066] In some embodiments, the function identification information of the AI ​​model is used to identify the function of the AI ​​model. For example, the function identification information is 3 bits, and different bit values ​​represent different functions of the AI ​​model. The correspondence between the bit value and the function of the AI ​​model can be predefined in the terminal device and the network device. According to the function identification information, the function of the AI ​​model required (requested) by the terminal device is indicated. For example, when the function identification information is 001, the function of the required (requested) AI model is for CSI compression, when the function identification information is 010, the function of the required (requested) AI model is for beam prediction, and when the function identification information is 011, the function of the required (requested) AI model is for terminal device positioning, or, for example, the function identification information can be a bitmap, and each bit corresponds to an AI The function of the model, when the value of the bit is 1 (or 0), it indicates that the function of the required (requested) AI model is the function of the AI ​​model corresponding to the bit. For example, the function identification information is a 3-bit bit map. The correspondence between the bit and the function of the AI ​​model can be predefined in the terminal device and the network device. According to the function identification information, the function of the required (requested) AI model of the terminal device is indicated. For example, when the function identification information is 001, the function of the required (requested) AI model is for CSI compression. When the function identification information is 010, the function of the required (requested) AI model is for beam prediction. When the function identification information is 100, the function of the required (requested) AI model is for terminal device positioning. The above is only an example, but the embodiments of the present application are not limited to this.

[0067] In some embodiments, as described above, the parameter information of the AI ​​model includes the AI ​​model input parameters and output parameter information, and the input parameters and output parameter information include first information indicating the dimensions of the input and output, and / or second information indicating the physical quantities of the input and output. Wherein, the first information indicates the number of dimensions and / or the specific numerical values ​​of each dimension. The number of dimensions can be indicated explicitly or implicitly, for example, using a first predetermined number of bits (for example, 2) to indicate the number of dimensions, where 01 indicates that the input dimension is X2, and 11 indicates that the input dimension is X1×Y1×Z1×N, and using a second predetermined number of bits to indicate the specific numerical values ​​of each dimension respectively, that is, using binary coding to represent the specific numerical values ​​of each dimension, for example, using 3 bits to indicate the value of X1, then using 3 bits to indicate the value of Y1, then using 3 bits to indicate the value of Z1, and then using 3 bits to indicate the value of N. The above is only an example, and this application is not limited to this. For example, the first predetermined number of bits can also be omitted, and the aforementioned second predetermined number of bits can be used to implicitly indicate the number of dimensions. Examples are not given here one by one. The second information is represented by a third predetermined number of bits, with different bit values ​​representing different physical quantities. The correspondence between bit values ​​and physical quantities can be predefined in the terminal device and the network device. For example, when the second information is 001, it indicates that the physical quantity is a channel coefficient matrix, and when the second information is 010, it indicates that the physical quantity is RSRP. Examples are not given here one by one. In some embodiments, the capability information includes the maximum first computing capacity and / or first storage space that the terminal device can support for the AI ​​model deployment. Similar to the above, the first computing capacity can be represented by floating-point operations per second (FLOPs) (e.g., binary encoding), and the first storage space can be represented by bits / bytes / megabytes (e.g., binary encoding). The specific values ​​of the maximum first computing capacity and / or maximum first storage space that the terminal device can support for the AI ​​model deployment are determined by the terminal device's own capabilities, such as hardware (e.g., processor and memory) performance and the currently running / executing program, service, or function. Examples are not given here one by one.

[0068] For example, after the terminal device receives the CSI-RS sent by the network device, it needs to perform CSI estimation and report. In order to reduce the load of CSI feedback and reduce the CSI feedback overhead, the terminal device needs to obtain the AI ​​model for CSI compression, and can use the AI ​​model to obtain the compressed CSI. Therefore, the terminal device can send a request information for obtaining the AI ​​model for CSI compression to the network device, or the terminal device can request the network device to obtain the AI ​​model for CSI compression. The request information includes the function identification information of the AI ​​model for CSI compression and / or the parameter information of the AI ​​model and / or the capability information of the AI ​​model for CSI compression that the terminal device can support.

[0069] For example, the terminal device receives a reference signal for beam measurement sent by the network device. In order to reduce the load of the RS and the delay of beam selection, the terminal device needs to obtain an AI model for beam prediction, use the AI ​​model to predict the optimal beam, and send the information of the optimal beam to the network device. Therefore, the terminal device can send a request information for obtaining the AI ​​model for beam prediction to the network device, or the terminal device can request the network device to obtain the AI ​​model for beam prediction. The request information includes functional identification information of the AI ​​model for beam prediction and / or parameter information of the AI ​​model and / or capability information of the AI ​​model for beam prediction that can be supported by the terminal device.

[0070] For example, in order to improve positioning accuracy, the terminal device needs to obtain an AI model for terminal device positioning, and use the AI ​​model to effectively classify the current scenario of the terminal device as LOS or NLOS. Therefore, the terminal device can send a request information for obtaining the AI ​​model for terminal device positioning to the network device, or the terminal device can request the network device to obtain the AI ​​model for terminal device positioning. The request information includes functional identification information of the AI ​​model for terminal device positioning and / or parameter information of the AI ​​model and / or capability information of the AI ​​model for terminal device positioning that can be supported by the terminal device.

[0071] In some embodiments, the request information is carried by RRC or MAC CE or UCI. For example, the request information can be a newly added information element (field) in UCI or existing RRC signaling, or the request information can also be carried by newly added RRC signaling. Examples are not given here one by one. The number of bits of each type of information in the above request information is only an example, and the embodiments of the present application are not limited thereto.

[0072] In some embodiments, after receiving the request information, the network device may send feedback information to the terminal device in response to the request information.

[0073] In some embodiments, after receiving the request information, the network device sends feedback information to the terminal device. The network device matches the multiple AI models pre-stored therein based on the request information. If no AI model that meets the terminal device request is matched (matching failure), the feedback information informs the terminal device that the terminal device request is not supported. If an AI model that meets the terminal device request is matched (matching success), the feedback information informs the terminal device that the terminal device request is supported, and informs the terminal device of relevant information about the matched AI model.

[0074] The following first explains how to match network devices with AI models.

[0075] For example, the request message includes the function identification information of the AI ​​model and / or the parameter information of the AI ​​model and / or the capability information of the AI ​​model that the terminal device can support. After receiving the request message, the network device matches the multiple AI models pre-stored therein based on the function identification information, and attempts to match an AI model with the same function as the AI ​​model indicated by the function identification information. If there is no AI model with the same function as the AI ​​model indicated by the function identification information, that is, the match fails, indicating that the network device does not support the request of the terminal device. If there are multiple AI models with the same function as the AI ​​model indicated by the function identification information, the network device then matches the multiple AI models pre-stored therein with the same function based on the parameter information of the AI ​​model in the request message, and attempts to match an AI model with the same parameters as the AI ​​model indicated by the parameter information of the AI ​​model. If there is no AI model with the same parameters as the AI ​​model indicated by the parameter information, that is, the match fails, indicating that the network device does not support the request of the terminal device. If there are multiple AI models with matching parameters (same parameters) among the multiple AI models with the same function, the second computing amount and / or second storage space of the multiple AI models with the same function and matching parameters are compared again with the first computing amount and / or first storage space in the capability information. If the second computing amount and / or second storage space of the multiple AI models with the same function and matching parameters are all greater than the first computing amount and / or first storage space, it means that the capability of the terminal device cannot support the deployment of the AI ​​model (matching failed). If the second computing amount and / or second storage space of at least one AI model is smaller than the first computing amount and / or first storage space, it means that the capability of the terminal device can support the deployment of the AI ​​model, that is, the AI ​​model that meets the request of the terminal device is matched (matching successful), and an AI model is selected from the at least one (M) AI models as the matched AI model (hereinafter also referred to as a suitable AI model). If M is equal to 1, then the one AI model is used as the matched AI model. If M is greater than 1, then an AI model can be arbitrarily selected from the M AI models as the matched AI model, or an AI model can be selected from the M AI models as the matched AI model according to a predetermined rule. For example, the predetermined rule can be the AI ​​model with the smallest second computing amount and / or second storage space or the largest AI model among the M AI models. The above is only an example and the embodiments of the present application are not limited to this.

[0076] The above matching process is only an example, and the embodiments of the present application are not limited to this. For example, when the request information includes one of the function identification information and capability information, the above partial matching process is only performed based on the function identification information or capability information, and will not be repeated here.

[0077] In some embodiments, the feedback information includes indication information of whether the request of the terminal device is supported and / or relevant identification information of the AI ​​model and / or the complexity of the AI ​​model. Wherein, the indication information includes 1 bit, when the value of the 1 bit is 1, it indicates that the network device supports the request of the terminal device (i.e., the match is successful), when the value of the 1 bit is 0, it indicates that the network device does not support the request of the terminal device (i.e., the match fails), and vice versa. This application is not limited to this.

[0078] In some embodiments, when the network device supports the request of the terminal device (i.e., the match is successful), the feedback information may also include relevant identification information of the AI ​​model and / or the complexity of the AI ​​model, and the AI ​​model is the matched AI model (suitable AI model).

[0079] In some embodiments, the relevant identification information of the AI ​​model is used to identify the function of the AI ​​model and / or parameter information of AI models with the same function and / or the serial number of the AI ​​model among multiple AI models with the same function and the same parameters. For example, the relevant identification information of the AI ​​model includes first identification information and / or second identification information and / or third identification information, where the first identification information is the function identification of the AI ​​model, the second identification information is the parameter information of the AI ​​model with the same function, and the third identification information is the serial number of the AI ​​model among multiple AI models with the same function and the same parameters. The first identification information may refer to the implementation method of the aforementioned function identification information. The second identification information may include a predetermined number of bits, and the value of the predetermined number of bits identifies the parameter information of the AI ​​model with the same function. The difference between the second identification information and the parameter information in the aforementioned request information is that when the parameter information of the AI ​​model with the same function is different, the second identification information is also different. However, when the parameter information of the AI ​​models with different functions is the same or different, the same second identification information may be used. For example, for the AI ​​model used for CSI compression, when the second identification information is 1000, it indicates that the input dimension is 8, and when the second identification information is 1010, it indicates that the input dimension is 10. For the AI ​​model used for beam prediction, when the second identification information is 1000, it indicates that the input dimension is 8, and when the second identification information is 1010, it indicates that the input dimension is 12. That is to say, the second identification information is only used to uniquely identify different parameter information of the AI ​​model with the same function. The third identification information may include a predetermined number of bits, and the value of the predetermined number of bits identifies the serial number of each AI model with the same function and the same parameters. For example, there are 4 AI models with the same function and the same parameters, and the third identification information of the 4 AI models are 00, 01, 10, and 11 respectively.

[0080] Figure 4 is a schematic diagram of the relevant identification information of the AI ​​model of an embodiment of the present application. As shown in Figure 4, the relevant identification information is 8 bits, of which the first 3 bits are the first identification information, indicating the function of the AI ​​model, the middle 3 bits are the second identification information, indicating the parameter information of the model, and the last 2 bits are the third identification information, indicating the serial number of the AI ​​model among multiple AI models with the same function and parameters.

[0081] The above number of bits is only an example, and this application is not limited to this. In addition, the relevant identification information can also be expressed in other forms. For example, the relevant identification information can include fourth identification information, and the fourth identification information is used to uniquely identify each AI model in multiple AI models. For example, the relevant identification information is 8 bits, where the 8 bits are the serial number of each AI model in multiple AI models. Examples are not given one by one here.

[0082] In some embodiments, the complexity of the AI ​​model includes the second computing amount and / or second storage space actually required to deploy the AI ​​model. For the meaning and determination method of the second computing amount and / or the second storage space, please refer to the above description. The second computing amount and / or the second storage space can be included in the feedback information after being binary-encoded, and examples will not be given one by one here.

[0083] In some embodiments, the feedback information is carried by RRC or MAC CE or DCI. For example, the feedback information can be a newly added information element (field) in DCI or existing RRC signaling, or the feedback information can also be carried by newly added RRC signaling. Examples are not given here one by one.

[0084] FIG5 is a schematic diagram of a method for sending and receiving information in an embodiment of the present application. As shown in FIG5 , the method includes:

[0085] 501. The terminal device sends a request message for obtaining an AI model to the network device.

[0086] 502. The terminal device receives feedback information sent by the network device in response to the request information.

[0087] 503. The terminal device receives the AI ​​model transmission resource allocation information sent by the network device, where the resource allocation information is used to indicate the time-frequency domain resources required to transmit the AI ​​model.

[0088] 504. The terminal device receives the AI ​​model sent by the network device on the time-frequency domain resources.

[0089] In some embodiments, the implementation of 501-502 can refer to 201-202, and the repeated parts will not be repeated.

[0090] In some embodiments, in 503, when the network device supports the request of the terminal device (matching is successful), the network device sends the resource allocation information to the terminal device, and the resource allocation information is used to indicate the time-frequency domain resources (resources on the air interface) required to transmit the AI ​​model. The size of the time-frequency domain resources can be determined based on the size (size, or second storage space) of the matched AI model. The AI ​​model can be transmitted on the PDSCH, and the resource allocation information can be carried by the DCI that schedules the PDSCH. For example, the resource allocation information can be the time domain and / or frequency resource allocation field in the DCI. For details, please refer to the prior art and will not be repeated here. When the network device does not support the request of the terminal device (matching fails), 503-504 do not need to be executed.

[0091] In some embodiments, in 504, after allocating resources for AI model transmission, the network device sends the AI ​​model to the terminal device on the allocated time-frequency domain resources, wherein sending the AI ​​model refers to sending the network structure of the AI ​​model, the number of nodes, the coefficients of each node of the AI ​​model, etc. For example, the trained multiple AI models can be saved as corresponding multiple files in a predetermined format in a predetermined storage format in a development environment such as pytorch or tensorflow, and the file contains the network structure of the corresponding AI model, the number of nodes, the coefficients of each node of the AI ​​model, etc. The multiple files in the predetermined format corresponding to the multiple AI models are pre-stored in the network device. After matching the appropriate AI model in 502, the file corresponding to the appropriate AI model is sent to the terminal device on the allocated time-frequency domain resources.

[0092] In some embodiments, the method may also include (not shown): the terminal device uses the AI ​​model to perform corresponding processing, such as CSI compression, predicting the optimal beam, positioning the terminal device (effectively classifying the current terminal device as LOS or NLOS), etc. For details, please refer to the existing technology and will not be described here one by one.

[0093] The above embodiments are merely exemplary of the present invention, but the present invention is not limited thereto. Appropriate modifications may be made based on the above embodiments. For example, the above embodiments may be used alone, or one or more of the above embodiments may be combined.

[0094] It can be seen from the above embodiments that the terminal device sends a request for obtaining an AI model to the network device and receives feedback information sent by the network device. Thus, the terminal device can obtain a suitable AI model from the network device and can use the obtained AI model to optimize the system load and delay.

[0095] Embodiments of the second aspect

[0096] An embodiment of the present application provides a method for sending and receiving information, which is explained from the perspective of a network device, and the contents that are the same as those in the embodiment of the first aspect will not be repeated.

[0097] FIG6 is a schematic diagram of a method for sending and receiving information according to an embodiment of the present application. As shown in FIG6 , the method includes:

[0098] 601. The network device receives a request for obtaining an AI model from a terminal device.

[0099] 602. The network device sends feedback information in response to the request information to the terminal device.

[0100] In some embodiments, the request information includes function identification information of the AI ​​model and / or parameter information of the AI ​​model and / or capability information of the AI ​​model that can be supported by the terminal device.

[0101] In some embodiments, the feedback information includes indication information of whether the terminal device request is supported and / or relevant identification information of the AI ​​model and / or the complexity of the AI ​​model.

[0102] Regarding the implementation of 601-602, please refer to 201-202 of the embodiment of the first aspect. Regarding the request information and feedback information, please refer to the embodiment of the first aspect, which will not be repeated here.

[0103] In some embodiments, the method further comprises:

[0104] The network device matches the AI ​​model function and / or the AI ​​model parameter information and / or the capability information requested by the terminal device with the AI ​​models stored in the network device to determine whether there is an AI model in the AI ​​model stored in the network device that meets the request of the terminal device;

[0105] Furthermore, the network device sends the feedback information based on the matching result of the processing unit.

[0106] In some embodiments, the matching process described above can be implemented with reference to the matching process of the embodiment of the first aspect. When the match is successful, it is determined that the AI ​​model stored by the network device contains an AI model that meets the request of the terminal device; when the match fails, it is determined that the AI ​​model stored by the network device does not contain an AI model that meets the request of the terminal device. The network device sends the feedback information based on the matching result of the processing unit. For details, please refer to the embodiment of the first aspect and will not be repeated here.

[0107] In some embodiments, the method further comprises:

[0108] The network device sends the AI ​​model transmission resource allocation information to the terminal device, where the resource allocation information is used to indicate the time-frequency domain resources required to transmit the AI ​​model, and sends the AI ​​model to the terminal device on the time-frequency domain resources.

[0109] It is worth noting that FIG6 above is merely a schematic illustration of an embodiment of the present application, and the present application is not limited thereto. For example, the execution order of the various operations may be appropriately adjusted, and other operations may be added or some operations may be reduced. Those skilled in the art may make appropriate modifications based on the above description, and are not limited to the description of FIG6 above.

[0110] The above embodiments are merely exemplary of the present invention, but the present invention is not limited thereto. Appropriate modifications may be made based on the above embodiments. For example, the above embodiments may be used alone, or one or more of the above embodiments may be combined.

[0111] It can be seen from the above embodiments that the network device receives a request sent by the terminal device for obtaining an AI model and sends feedback information to the terminal device. As a result, the terminal device can obtain a suitable AI model from the network device and can use the obtained AI model to optimize the system load and delay.

[0112] Embodiments of the third aspect

[0113] The embodiment of the present application provides an information transceiver device, which may be, for example, a terminal device, or one or more components or assemblies configured in the terminal device, and the same contents as those in the embodiment of the first aspect will not be repeated.

[0114] FIG7 is a schematic diagram of an information transceiver device according to an embodiment of the present application. As shown in FIG7 , the information transceiver device 700 includes:

[0115] A first sending unit 701 sends a request for obtaining an AI model to a network device;

[0116] The first receiving unit 702 receives feedback information sent by the network device in response to the request information.

[0117] In some embodiments, the request information includes function identification information of the AI ​​model and / or parameter information of the AI ​​model and / or capability information of the AI ​​model that can be supported by the terminal device.

[0118] In some embodiments, the capability information includes the maximum first computing capacity and / or first storage space that the terminal device can support for the AI ​​model deployment.

[0119] In some embodiments, the feedback information includes indication information of whether the terminal device request is supported and / or relevant identification information of the AI ​​model and / or the complexity of the AI ​​model.

[0120] In some embodiments, the relevant identification information of the AI ​​model is used to identify the function of the AI ​​model and / or parameter information of an AI model with the same function and / or the serial number of the AI ​​model among multiple AI models with the same function and parameters.

[0121] In some embodiments, the relevant identification information of the AI ​​model includes first identification information and / or second identification information and / or third identification information, the first identification information is the functional identification of the AI ​​model, the second identification information is the parameter information of the AI ​​model with the same function, and the third identification information is the serial number of the AI ​​model among multiple AI models with the same function and the same parameters.

[0122] In some embodiments, the complexity of the AI ​​model includes a second amount of computing power and / or a second storage space actually required to deploy the AI ​​model.

[0123] In some embodiments, the request information is carried by RRC or MAC CE or UCI.

[0124] In some embodiments, the feedback information is carried by RRC or MAC CE or DCI.

[0125] In some embodiments, the function of the AI ​​model refers to part of the functions in the receiving and / or transmitting link of the terminal device.

[0126] In some embodiments, the functionality of the AI ​​model includes an AI encoder model for CSI compression or an AI model for beam prediction or an AI model for terminal device positioning.

[0127] In some embodiments, the first receiving unit is further used to receive the AI ​​model transmission resource allocation information sent by the network device, where the resource allocation information is used to indicate the time-frequency domain resources required to transmit the AI ​​model.

[0128] In some embodiments, the first receiving unit is further used to receive the AI ​​model sent by the network device on the time-frequency domain resources.

[0129] In some embodiments, when the network device supports the request of the terminal device, the first receiving unit receives the resource allocation information.

[0130] The above embodiments are merely exemplary of the present invention, but the present invention is not limited thereto. Appropriate modifications may be made based on the above embodiments. For example, the above embodiments may be used alone, or one or more of the above embodiments may be combined.

[0131] It is worth noting that the above description only describes the components or modules related to the present application, but the present application is not limited thereto. The information transceiver device 700 may also include other components or modules. For the specific contents of these components or modules, reference may be made to the relevant art.

[0132] In addition, for the sake of simplicity, FIG7 only illustrates the connection relationship or signal direction between various components or modules. However, it should be clear to those skilled in the art that various related technologies such as bus connection can be used. The above-mentioned components or modules can be implemented by hardware facilities such as processors, memories, transmitters, and receivers; the implementation of this application is not limited to this.

[0133] It can be seen from the above embodiments that the terminal device sends a request for obtaining an AI model to the network device and receives feedback information sent by the network device. Thus, the terminal device can obtain a suitable AI model from the network device and can use the obtained AI model to optimize the system load and delay.

[0134] Embodiments of the fourth aspect

[0135] The embodiment of the present application provides an information transceiver device, which may be, for example, a network device, or one or more components or assemblies configured in the network device, and the contents that are the same as those in the embodiment of the second aspect will not be repeated.

[0136] FIG8 is a schematic diagram of an information transceiver device according to an embodiment of the present application. As shown in FIG8 , the information transceiver device 800 includes:

[0137] A second receiving unit 801 receives a request for obtaining an AI model from a terminal device;

[0138] The second sending unit 802 sends feedback information in response to the request information to the terminal device.

[0139] In some embodiments, the request information includes function identification information of the AI ​​model and / or parameter information of the AI ​​model and / or capability information of the AI ​​model that can be supported by the terminal device.

[0140] In some embodiments, the feedback information includes indication information of whether the terminal device request is supported and / or relevant identification information of the AI ​​model and / or the complexity of the AI ​​model.

[0141] In some embodiments, the device further includes: (not shown, optional)

[0142] a processing unit, configured to match the function of the AI ​​model requested by the terminal device and / or the parameter information and / or the capability information of the AI ​​model with each AI model stored by the network device, to determine whether any AI model stored by the network device satisfies the request of the terminal device;

[0143] Furthermore, the second sending unit sends the feedback information based on the matching result of the processing unit.

[0144] In some embodiments, the second sending unit is also used to send the AI ​​model transmission resource allocation information to the terminal device, where the resource allocation information is used to indicate the time-frequency domain resources required to transmit the AI ​​model, and to send the AI ​​model to the terminal device on the time-frequency domain resources.

[0145] The above embodiments are merely exemplary of the present invention, but the present invention is not limited thereto. Appropriate modifications may be made based on the above embodiments. For example, the above embodiments may be used alone, or one or more of the above embodiments may be combined.

[0146] It is worth noting that the above description only describes the components or modules related to the present application, but the present application is not limited thereto. The information transceiver device 800 may also include other components or modules. For the specific contents of these components or modules, reference may be made to the relevant art.

[0147] In addition, for the sake of simplicity, FIG8 only illustrates the connection relationship or signal direction between various components or modules. However, it should be clear to those skilled in the art that various related technologies such as bus connection can be used. The above-mentioned components or modules can be implemented by hardware facilities such as processors, memories, transmitters, and receivers; the implementation of this application is not limited to this.

[0148] It can be seen from the above embodiments that the network device receives a request sent by the terminal device for obtaining an AI model and sends feedback information to the terminal device. As a result, the terminal device can obtain a suitable AI model from the network device and can use the obtained AI model to optimize the system load and delay.

[0149] Embodiments of the fifth aspect

[0150] An embodiment of the present application also provides a communication system, and reference may be made to FIG1 . The contents that are the same as those in the first to fourth aspects of the embodiments will not be repeated.

[0151] In some embodiments, the communication system 100 may include at least:

[0152] The terminal device 102 sends a request message for obtaining an AI model to a network device, and receives feedback message sent by the network device in response to the request message; and

[0153] The network device 101 receives a request message sent by a terminal device for obtaining an AI model; and sends feedback information in response to the request message to the terminal device.

[0154] FIG9 is a schematic diagram of a method for sending and receiving information according to an embodiment of the present application. As shown in FIG9 , the method includes:

[0155] 901, the terminal device sends a request message for obtaining an AI model to the network device;

[0156] 902. The network device matches an AI model (selects an AI model) according to the request information.

[0157] 903, the network device sends feedback information to the terminal device according to the matching result;

[0158] 904. The network device sends the AI ​​model transmission resource allocation information to the terminal device.

[0159] 905. The network device sends the AI ​​model to the terminal device on the time-frequency domain resources.

[0160] 906. The terminal device uses the AI ​​model to perform corresponding functions (part of the receiving and / or transmitting links).

[0161] Regarding the implementation of 901-906, reference can be made to the aforementioned embodiments of the first and second aspects, which will not be repeated here.

[0162] An embodiment of the present application further provides a network device, which may be, for example, a base station, but the present application is not limited thereto and may also be other network devices.

[0163] Figure 10 is a schematic diagram illustrating the structure of a network device according to an embodiment of the present application. As shown in Figure 10 , network device 1000 may include a processor 1010 (e.g., a central processing unit (CPU)) and a memory 1020; memory 1020 is coupled to processor 1010. Memory 1020 may store various data and may also store an information processing program 1030, which is executed under the control of processor 1010.

[0164] For example, the processor 1010 may be configured to execute a program to implement the information sending and receiving method as described in the embodiment of the second aspect. For example, the processor 1010 may be configured to perform the following control: receiving a request message sent by a terminal device for obtaining an AI model; sending feedback information in response to the request message to the terminal device;

[0165] In addition, as shown in FIG10 , the network device 1000 may further include: a transceiver 1040 and an antenna 1050; wherein, the functions of the above components are similar to those in the prior art and are not described in detail here. It is worth noting that the network device 1000 does not necessarily include all the components shown in FIG10 ; in addition, the network device 1000 may also include components not shown in FIG10 , and reference may be made to the prior art for details.

[0166] The embodiment of the present application also provides a terminal device, but the present application is not limited thereto and may also be other devices.

[0167] Figure 11 is a schematic diagram of a terminal device according to an embodiment of the present application. As shown in Figure 11 , terminal device 1100 may include a processor 1110 and a memory 1120. Memory 1120 stores data and programs and is coupled to processor 1110. It should be noted that this diagram is exemplary; other types of structures may be used to supplement or replace this structure to implement telecommunication or other functions.

[0168] For example, the processor 1110 may be configured to execute a program to implement the information sending and receiving method as described in the embodiment of the first aspect. For example, the processor 1110 may be configured to perform the following control: sending a request message for obtaining an AI model to a network device; and receiving feedback information sent by the network device in response to the request message.

[0169] As shown in Figure 11 , the terminal device 1100 may further include: a communication module 1130, an input unit 1140, a display 1150, and a power supply 1160. The functions of these components are similar to those in the prior art and are not described in detail here. It is worth noting that the terminal device 1100 does not necessarily include all of the components shown in Figure 11 , and these components are not essential. Furthermore, the terminal device 1100 may also include components not shown in Figure 11 , for which reference may be made to the prior art.

[0170] An embodiment of the present application also provides a computer program, wherein when the program is executed in a terminal device, the program enables the terminal device to execute the information sending and receiving method described in the embodiment of the first aspect.

[0171] An embodiment of the present application also provides a storage medium storing a computer program, wherein the computer program enables a terminal device to execute the information sending and receiving method described in the embodiment of the first aspect.

[0172] An embodiment of the present application also provides a computer program, wherein when the program is executed in a network device, the program causes the network device to execute the information sending and receiving method described in the embodiment of the second aspect.

[0173] An embodiment of the present application also provides a storage medium storing a computer program, wherein the computer program enables a network device to execute the information sending and receiving method described in the embodiment of the second aspect.

[0174] The above devices and methods of the present application can be implemented by hardware or by a combination of hardware and software. The present application relates to such a computer-readable program that, when executed by a logic component, enables the logic component to implement the devices or components described above, or enables the logic component to implement the various methods or steps described above. The present application also relates to a storage medium for storing the above program, such as a hard disk, a magnetic disk, an optical disk, a DVD, a flash memory, etc.

[0175] The method / device described in conjunction with the embodiments of the present application can be directly embodied as hardware, a software module executed by a processor, or a combination of the two. For example, one or more of the functional block diagrams shown in the figure and / or one or more combinations of functional block diagrams can correspond to various software modules of the computer program flow or to various hardware modules. These software modules can respectively correspond to the various steps shown in the figure. These hardware modules can be implemented by solidifying these software modules, for example, using a field programmable gate array (FPGA).

[0176] The software module may be located in RAM memory, flash memory, ROM memory, EPROM memory, EEPROM memory, registers, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art. A storage medium may be coupled to a processor so that the processor can read information from the storage medium and write information to the storage medium; or the storage medium may be an integral part of the processor. The processor and the storage medium may be located in an ASIC. The software module may be stored in the memory of the mobile terminal or in a memory card that can be inserted into the mobile terminal. For example, if the device (such as a mobile terminal) uses a large-capacity MEGA-SIM card or a large-capacity flash memory device, the software module may be stored in the MEGA-SIM card or the large-capacity flash memory device.

[0177] One or more of the functional blocks and / or one or more combinations of functional blocks described in the accompanying drawings may be implemented as a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic device, a discrete gate or transistor logic device, a discrete hardware component, or any appropriate combination thereof for performing the functions described in this application. One or more of the functional blocks and / or one or more combinations of functional blocks described in the accompanying drawings may also be implemented as a combination of computing devices, such as a combination of a DSP and a microprocessor, multiple microprocessors, one or more microprocessors in communication with a DSP, or any other such configuration.

[0178] The present application has been described above in conjunction with specific embodiments. However, those skilled in the art should understand that these descriptions are merely illustrative and are not intended to limit the scope of protection of the present application. Those skilled in the art may make various modifications and variations to the present application based on the spirit and principles of the present application, and such modifications and variations are also within the scope of the present application.

[0179] Regarding the implementation methods including the above embodiments, the following additional notes are also disclosed:

[0180] 1. A method for sending and receiving information, characterized in that the method comprises:

[0181] The terminal device sends a request message to the network device to obtain the AI ​​model;

[0182] The terminal device receives feedback information sent by the network device in response to the request information.

[0183] 2. The method according to Note 1, wherein the request information includes function identification information of the AI ​​model and / or parameter information of the AI ​​model and / or capability information of the AI ​​model that the terminal device can support.

[0184] 3. The method according to Note 2, wherein the capability information includes the maximum first computing capacity and / or first storage space that the terminal device can support for the AI ​​model deployment.

[0185] 4. The method according to any one of Notes 1 to 3, wherein the feedback information includes indication information of whether the terminal device request is supported and / or relevant identification information of the AI ​​model and / or the complexity of the AI ​​model.

[0186] 5. The method according to Note 4, wherein the relevant identification information of the AI ​​model is used to identify the function of the AI ​​model and / or the parameter information of the AI ​​model with the same function and / or the serial number of the AI ​​model among multiple AI models with the same function and parameters.

[0187] 6. The method according to Note 5, wherein the relevant identification information of the AI ​​model includes first identification information and / or second identification information and / or third identification information, the first identification information is the functional identification of the AI ​​model, the second identification information is the parameter information of the AI ​​model with the same function, and the third identification information is the serial number of the AI ​​model among multiple AI models with the same function and the same parameters.

[0188] 7. The method according to any one of Notes 4 to 6, wherein the complexity of the AI ​​model includes a second computing amount and / or a second storage space actually required to deploy the AI ​​model.

[0189] 8. The method according to any one of Notes 1 to 7, wherein the request information is carried by RRC or MAC CE or UCI.

[0190] 9. The method according to any one of Notes 1 to 8, wherein the feedback information is carried by RRC or MAC CE or DCI.

[0191] 10. The method according to any one of Note 1 to 1, wherein the function of the AI ​​model refers to part of the functions in the receiving and / or transmitting link of the terminal device.

[0192] 11. The method according to Note 10, wherein the functions of the AI ​​model include an AI encoder model for CSI compression, an AI model for beam prediction, or an AI model for terminal device positioning.

[0193] 12. The method according to any one of Notes 1 to 11, wherein the method further comprises:

[0194] The terminal device receives the AI ​​model transmission resource allocation information sent by the network device, where the resource allocation information is used to indicate the time-frequency domain resources required to transmit the AI ​​model.

[0195] 13. The method according to Supplementary Note 12, further comprising:

[0196] The terminal device also receives the AI ​​model sent by the network device on the time-frequency domain resources.

[0197] 14. The method according to Note 12, wherein when the network device supports the request of the terminal device, the terminal device receives the resource allocation information.

[0198] 15. A method for sending and receiving information, characterized in that the method comprises:

[0199] The network device receives a request for obtaining an AI model from the terminal device;

[0200] The network device sends feedback information in response to the request information to the terminal device.

[0201] 16. The method according to Note 15, wherein the request information includes function identification information of the AI ​​model and / or parameter information of the AI ​​model and / or capability information of the AI ​​model that can be supported by the terminal device.

[0202] 17. The method according to Note 15 or 16, wherein the feedback information includes indication information of whether the terminal device request is supported and / or relevant identification information of the AI ​​model and / or the complexity of the AI ​​model.

[0203] 18. The method according to Supplement 16 or 17, wherein the method further comprises:

[0204] The network device matches the function of the AI ​​model requested by the terminal device and / or the parameter information of the AI ​​model and / or the capability information with each AI model stored in the network device to determine whether there is an AI model in the AI ​​model stored in the network device that meets the request of the terminal device;

[0205] Furthermore, the network device sends the feedback information based on the matching result.

[0206] 19. The method according to any one of Notes 15 to 18, wherein the method further comprises:

[0207] The network device sends the AI ​​model transmission resource allocation information to the terminal device, where the resource allocation information is used to indicate the time-frequency domain resources required to transmit the AI ​​model, and sends the AI ​​model to the terminal device on the time-frequency domain resources.

[0208] 20. A network device comprising a memory and a processor, wherein the memory stores a computer program, and the processor is configured to execute the computer program to implement the method as described in any one of Notes 15 to 19.

[0209] 21. A terminal device comprising a memory and a processor, wherein the memory stores a computer program, and the processor is configured to execute the computer program to implement the method as described in any one of Notes 1 to 14.

Claims

1. An information transceiver device, applied to a terminal device, characterized in that: The device comprises: A first sending unit, which sends request information for obtaining an AI model to a network device; A first receiving unit is configured to receive feedback information sent by the network device in response to the request information.

2. The device according to claim 1, wherein The request information includes function identification information of the AI ​​model and / or parameter information of the AI ​​model and / or capability information of the AI ​​model that can be supported by the terminal device.

3. The device according to claim 2, wherein The capability information includes the maximum first computing capacity and / or first storage space that the terminal device can support for the AI ​​model deployment.

4. The device according to claim 1, wherein The feedback information includes indication information of whether the terminal device request is supported and / or relevant identification information of the AI ​​model and / or the complexity of the AI ​​model.

5. The device according to claim 4, wherein The relevant identification information of the AI ​​model is used to identify the function of the AI ​​model and / or parameter information of AI models with the same function and / or the serial number of the AI ​​model among multiple AI models with the same function and parameters.

6. The device according to claim 5, wherein The relevant identification information of the AI ​​model includes first identification information and / or second identification information and / or third identification information, the first identification information is the functional identification of the AI ​​model, the second identification information is the parameter information of the AI ​​model with the same function, and the third identification information is the serial number of the AI ​​model among multiple AI models with the same function and parameters.

7. The device according to claim 4, wherein The complexity of the AI ​​model includes a second computing amount and / or a second storage space actually required to deploy the AI ​​model.

8. The device according to claim 1, wherein The request information is carried by RRC or MAC CE or UCI.

9. The device according to claim 1, wherein The feedback information is carried by RRC or MAC CE or DCI.

10. The device according to claim 1, wherein The functions of the AI ​​model refer to some functions in the receiving and / or transmitting links of the terminal device.

11. The device according to claim 10, wherein The functions of the AI ​​model include an AI encoder model for CSI compression, an AI model for beam prediction, or an AI model for terminal device positioning.

12. The device according to claim 1, wherein The first receiving unit is further used to receive the AI ​​model transmission resource allocation information sent by the network device, where the resource allocation information is used to indicate the time-frequency domain resources required to transmit the AI ​​model.

13. The device according to claim 12, wherein The first receiving unit is further used to receive the AI ​​model sent by the network device on the time-frequency domain resources.

14. The device according to claim 12, wherein When the network device supports the request of the terminal device, the first receiving unit receives the resource allocation information.

15. An information transceiver device, applied to a network device, characterized in that: The device comprises: A second receiving unit receives a request for obtaining an AI model from a terminal device; The second sending unit sends feedback information in response to the request information to the terminal device.

16. The device according to claim 15, wherein The request information includes function identification information of the AI ​​model and / or parameter information of the AI ​​model and / or capability information of the AI ​​model that can be supported by the terminal device.

17. The device according to claim 15, wherein The feedback information includes indication information of whether the terminal device request is supported and / or relevant identification information of the AI ​​model and / or the complexity of the AI ​​model.

18. The device according to claim 16, wherein The device further comprises: a processing unit, configured to match the function of the AI ​​model requested by the terminal device and / or the parameter information and / or the capability information of the AI ​​model with each AI model stored by the network device, to determine whether there is an AI model in the AI ​​model stored by the network device that meets the request of the terminal device; Furthermore, the second sending unit sends the feedback information based on the matching result of the processing unit.

19. The device according to claim 15, wherein The second sending unit is also used to send the AI ​​model transmission resource allocation information to the terminal device, where the resource allocation information is used to indicate the time-frequency domain resources required to transmit the AI ​​model, and to send the AI ​​model to the terminal device on the time-frequency domain resources.

20. A communication system comprising a terminal device and / or a network device, wherein the terminal device comprises the information transceiver device according to claim 1, and the network device comprises the information transceiver device according to claim 15.

Images