Communication method and device, equipment and storage medium

Abstract

The invention provides a communication method and apparatus, a device and a storage medium. The method comprises the steps of indicating model related information of a first device to a second device; the model related information comprises at least one of the following: at least one AI model supported by the first equipment; the AI functions are respectively associated with at least one AI model supported by the first equipment; the first device supports at least one AI function; at least one AI function supported by the first equipment is associated with an AI model. The method unifies the understanding of the first device and the second device on the AI model on the first device, ensures that the second device can successfully manage the AI model on the first device subsequently, and improves the stability of AI model management.

Description

Communication method, device, equipment and storage medium Technical Field

[0001] The present disclosure relates to the field of communication technology, and in particular to a communication method, apparatus, device, and storage medium. Background Art

[0002] With the continuous development of artificial intelligence (AI) technology, its application areas are becoming increasingly broad. The 3rd Generation Partnership Project (3GPP) has also introduced AI technology, such as AI models to implement AI-based CSI enhancement, AI-based beam management, and AI-based positioning.

[0003] Optionally, AI models are deployed on terminal devices, and network devices also need to participate in the management of AI models. Therefore, network devices and terminal devices need to have a unified understanding of the relevant information of the AI ​​models on the terminal devices. Therefore, a model identification method between terminal devices and network devices is urgently needed to unify the network and terminal devices' understanding of the AI ​​models on the terminal devices.

[0004] Summary of the Invention

[0005] The present disclosure provides a communication method, apparatus, device, and storage medium.

[0006] In a first aspect, an embodiment of the present disclosure provides a communication method, which is executed by a first device and includes:

[0007] indicating model-related information of the first device to the second device;

[0008] The model-related information includes at least one of the following:

[0009] At least one artificial intelligence (AI) model supported by the first device;

[0010] an AI function respectively associated with at least one AI model supported by the first device;

[0011] at least one AI function supported by the first device;

[0012] an AI model associated with at least one AI function supported by the first device.

[0013] In a second aspect, an embodiment of the present disclosure provides a communication method, which is executed by a second device, including:

[0014] determining model-related information of the first device based on the indication of the first device;

[0015] The model-related information includes at least one of the following:

[0016] at least one AI model supported by the first device;

[0017] an AI function respectively associated with at least one AI model supported by the first device;

[0018] at least one AI function supported by the first device;

[0019] an AI model associated with at least one AI function supported by the first device.

[0020] In a third aspect, an embodiment of the present disclosure provides a communication device, including:

[0021] A transceiver module, configured to indicate model-related information of the first device to a second device;

[0022] The model-related information includes at least one of the following:

[0023] at least one AI model supported by the first device;

[0024] an AI function respectively associated with at least one AI model supported by the first device;

[0025] at least one AI function supported by the first device;

[0026] an AI model associated with at least one AI function supported by the first device.

[0027] In a fourth aspect, an embodiment of the present disclosure provides a communication device, including:

[0028] a processing module, configured to determine model-related information of the first device based on an indication of the first device;

[0029] The model-related information includes at least one of the following:

[0030] at least one AI model supported by the first device;

[0031] an AI function respectively associated with at least one AI model supported by the first device;

[0032] at least one AI function supported by the first device;

[0033] an AI model associated with at least one AI function supported by the first device.

[0034] In a fifth aspect, an embodiment of the present disclosure provides a communication device, which includes a processor. When the processor calls a computer program in a memory, it executes any method described in the first or second aspect above.

[0035] In a sixth aspect, an embodiment of the present disclosure provides a communication device, which includes a processor and an interface circuit, wherein the interface circuit is used to receive code instructions and transmit them to the processor, and the processor is used to run the code instructions to enable the device to execute any of the methods described in the first or second aspects above.

[0036] In the seventh aspect, an embodiment of the present disclosure provides a communication system, which includes the communication device described in any one of the third to fourth aspects, or the system includes the communication device described in the fifth aspect, or the system includes the communication device described in the sixth aspect.

[0037] In an eighth aspect, an embodiment of the present invention provides a computer-readable storage medium for storing instructions for the above-mentioned network device, and when the instructions are executed, the terminal device executes any one of the methods described in the first or second aspect above.

[0038] In a ninth aspect, the present disclosure further provides a computer program product comprising a computer program, which, when executed on a computer, enables the computer to execute any of the methods described in the first or second aspect above.

[0039] In a tenth aspect, the present disclosure provides a chip system comprising at least one processor and an interface for supporting a network device in implementing the functions described in any one of the methods described in the first or second aspects, such as determining or processing at least one of the data and information involved in the aforementioned methods. In one possible design, the chip system further comprises a memory for storing computer programs and data necessary for the source slave node. The chip system may be composed of a chip or may include a chip and other discrete components.

[0040] In an eleventh aspect, the present disclosure provides a computer program, which, when executed on a computer, enables the computer to execute any one of the methods described in the first or second aspect above. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] The above and / or additional aspects and advantages of the present disclosure will become apparent and readily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0042] FIG1 is a schematic diagram of the architecture of a communication system provided by an embodiment of the present disclosure;

[0043] FIG2 is a flow chart of a communication method provided by an embodiment of the present disclosure;

[0044] FIG3 is a flow chart of a communication method provided by an embodiment of the present disclosure;

[0045] FIG4 is a flow chart of a communication method provided by yet another embodiment of the present disclosure;

[0046] FIG5 is a flow chart of a communication method provided by yet another embodiment of the present disclosure;

[0047] FIG6 is a flow chart of a communication method provided by yet another embodiment of the present disclosure;

[0048] FIG7 is a flow chart of a communication method provided by yet another embodiment of the present disclosure;

[0049] FIG8 is a schematic flow chart of a communication method provided by yet another embodiment of the present disclosure;

[0050] FIG9 is a flow chart of a communication method provided by yet another embodiment of the present disclosure;

[0051] FIG10 is a flow chart of a communication method provided by yet another embodiment of the present disclosure;

[0052] FIG11 is a flow chart of a communication method provided in yet another embodiment of the present disclosure;

[0053] FIG12 is a schematic structural diagram of a communication device provided in yet another embodiment of the present disclosure;

[0054] FIG13 is a schematic structural diagram of a communication device provided by yet another embodiment of the present disclosure;

[0055] FIG14 is a schematic structural diagram of a communication device provided in an embodiment of the present disclosure;

[0056] FIG15 is a schematic structural diagram of a chip provided in accordance with an embodiment of the present disclosure. DETAILED DESCRIPTION

[0057] Exemplary embodiments will be described in detail herein, with examples illustrated in the accompanying drawings. In the following description, when referring to the drawings, identical numerals in different figures represent identical or similar elements, unless otherwise indicated. The embodiments described in the following exemplary embodiments are not intended to represent all possible implementations consistent with the present disclosure. Rather, they are merely examples of apparatuses and methods consistent with certain aspects of the present disclosure, as detailed in the appended claims.

[0058] The terms used in the embodiments of the present disclosure are for the purpose of describing specific embodiments only and are not intended to limit the embodiments of the present disclosure. The singular forms "a," "an," and "the" used in the embodiments of the present disclosure and the appended claims are also intended to include plural forms unless the context clearly indicates otherwise. It should also be understood that the term "and / or" as used herein refers to and includes any or all possible combinations of one or more associated listed items.

[0059] It should be understood that although the terms first, second, third, etc. may be used to describe various information in the embodiments of the present disclosure, such information should not be limited to these terms. These terms are only used to distinguish signals of the same type from each other. For example, without departing from the scope of the embodiments of the present disclosure, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Depending on the context, the words "if" and "if" as used herein may be interpreted as "at the time of" or "when" or "in response to determining".

[0060] The embodiments of the present disclosure are described in detail below, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present disclosure, and should not be understood as limiting the present disclosure.

[0061] In order to better understand a communication method disclosed in an embodiment of the present disclosure, the communication system to which the embodiment of the present disclosure is applicable is first described below.

[0062] Please refer to Figure 1, which is a schematic diagram of the architecture of a communication system provided by an embodiment of the present disclosure. The communication system may include but is not limited to at least one first device and at least one second device, wherein the first device may be a device on which an AI model is deployed, and the second device may be a device that is to interact with the first device in relation to the AI ​​model. Optionally, the first device may be a terminal device or a network device, and the second device may be a terminal device or a network device. The number and form of devices shown in Figure 1 are for example only and do not constitute a limitation on the embodiments of the present disclosure. An application may include one or more first devices, or one or more second devices. The communication system shown in Figure 1 takes an example including a first device, a terminal device, a second device, and a network device.

[0063] It should be noted that the technical solutions of the embodiments of the present disclosure can be applied to various communication systems, such as long-term evolution (LTE) systems, fifth-generation (5G) mobile communication systems, 5G new radio (NR) systems, or other future new mobile communication systems.

[0064] The terminal device in the embodiments of the present disclosure can be an entity on the user side for receiving or transmitting signals, such as a mobile phone. The terminal device can also be called a terminal, terminal device, mobile station (MS), mobile terminal (MT), etc. The terminal device can be a car with communication function, a smart car, a mobile phone, a wearable device, a tablet computer (Pad), a computer with wireless transceiver function, a virtual reality (VR) terminal, an augmented reality (AR) terminal, a wireless terminal in industrial control (industrial control), a wireless terminal in self-driving, a wireless terminal in remote medical surgery, a wireless terminal in smart grid (smart grid), a wireless terminal in transportation safety (transportation safety), a wireless terminal in smart city (smart city), a wireless terminal in smart home (smart home), etc. The embodiments of the present disclosure do not limit the specific technology and specific device form adopted by the terminal device.

[0065] The network device in the embodiment of the present disclosure may be an entity on the network side for transmitting or receiving signals. For example, the network device may be an evolved NodeB (eNB), a transmission reception point (TRP), a radio remote head (RRH), a next generation NodeB (gNB) in an NR system, a base station in other future mobile communication systems, or an access node in a wireless fidelity (WiFi) system. The embodiment of the present disclosure does not limit the specific technology and specific device form adopted by the base station. The base station provided in the embodiment of the present disclosure may be composed of a central unit (CU) and a distributed unit (DU), wherein the CU may also be referred to as a control unit. The CU-DU structure may be used to split the base station, such as the protocol layer of the base station, and the functions of some protocol layers are placed in the CU for centralized control, while the functions of the remaining part or all of the protocol layers are distributed in the DU, and the DU is centrally controlled by the CU.

[0066] It can be understood that the communication system described in the embodiment of the present disclosure is for the purpose of more clearly illustrating the technical solution of the embodiment of the present disclosure, and does not constitute a limitation on the technical solution provided by the embodiment of the present disclosure. Ordinary technicians in this field can know that with the evolution of the system architecture and the emergence of new business scenarios, the technical solution provided by the embodiment of the present disclosure is also applicable to similar technical problems.

[0067] In addition, in order to facilitate understanding of the embodiments of the present disclosure, the following points are explained.

[0068] First, in the present disclosure, unless there is any contradiction, each step in any embodiment or example can be implemented as an independent embodiment, and the steps can be arbitrarily combined. For example, a solution after removing some steps in a certain embodiment or example can also be implemented as an independent embodiment, and the order of the steps in a certain embodiment or example can be arbitrarily exchanged. In addition, the optional methods or optional examples in a certain embodiment or example can be arbitrarily combined; in addition, the various embodiments or examples can be arbitrarily combined. For example, some or all steps of different embodiments or examples can be arbitrarily combined, and a certain embodiment or example can be arbitrarily combined with the optional methods or optional examples of other embodiments or examples.

[0069] Second, regarding the description methods of the present disclosure such as "A or B", "A and / or B", "at least one of A and B", "A in one case, B in another case", "in response to one case A, in response to another case B", etc., at least one of the following schemes may be included according to the situation: executing A independently of B, that is, A in some embodiments; executing B independently of A, that is, B in some embodiments; selectively executing A and B, that is, selecting to execute from A and B in some embodiments; executing both A and B, that is, A and B in some embodiments.

[0070] Third, each element, each row, or each column in the table involved in the present disclosure can be implemented as an independent embodiment, and the combination of any elements, any rows, and any columns can also be implemented as an independent embodiment.

[0071] Fourth, in some implementation modes or examples, “including A”, “comprising A”, “used to indicate A” and “carrying A” in this disclosure can be interpreted as directly carrying A or indirectly indicating A.

[0072] Fifth, in some implementation modes or examples, "in response to...", "in the case of...", "at the time of...", "when...", "if...", "if...", etc. in the present disclosure can be replaced with each other.

[0073] FIG2 is a flow chart of a communication method provided by an embodiment of the present disclosure. The method is executed by a first device. As shown in FIG2 , the communication method may include the following steps:

[0074] Step 201: Indicate model-related information of a first device to a second device.

[0075] Optionally, in some embodiments, the first device may be a device that deploys or stores a model (such as an AI model), and the second device may be a device that interacts with the first device regarding the AI ​​model. For example, the second device may be a device that needs to manage (e.g., monitor, activate, or switch) the AI ​​model in the first device. Optionally, the first device may be a terminal device or a network device, and the second device may be a terminal device or a network device.

[0076] Optionally, in some embodiments, the model-related information may include at least one of the following:

[0077] At least one AI model supported by the first device;

[0078] AI functionality associated with at least one AI model supported by the first device;

[0079] at least one AI function supported by the first device;

[0080] An AI model associated with at least one AI function supported by the first device.

[0081] Optionally, the above-mentioned “at least one AI model supported by the first device” can be understood as: at least one AI model deployed in the first device, and / or at least one AI model stored in the first device.

[0082] The following is an introduction to the "AI model" in the embodiments of the present disclosure.

[0083] Optionally, in some embodiments, the AL model described above may be used to implement at least one AL function under at least one specific configuration. Optionally, the specific configuration may be, for example, a specific beam configuration or a specific reference signal configuration; the AI ​​function may be, for example, channel state information reference signal (CSI) enhancement, CSI compression, time-domain CSI prediction, AI-based spatial beam prediction, AI-based positioning, etc. Also, optionally, there is a correlation between the AI ​​model and the AI ​​function that the AI ​​model can implement.

[0084] For example, assume that two AI functions are defined for "AI-based spatial beam prediction": AI functionality 1 and AI functionality 2. These two AI functions are targeted at different beam configurations, where AI functionality 1 corresponds to beam configuration 1 and AI functionality 2 corresponds to beam configuration 2. AI functionality 1 can be understood as implementing AI-based spatial beam prediction under beam configuration 1, and AI functionality 2 can be understood as implementing AI-based spatial beam prediction under beam configuration 2. In this case, if AI model 1 is defined to implement AI functionality 1 and AI model 2 is defined to implement AI functionality 2, then it is considered that AI model 1 is associated with AI functionality 1, and AI model 2 is associated with AI functionality 2.

[0085] Optionally, in other embodiments, different AI models can also be used to implement AL functions under the same configuration in different application scenarios.

[0086] For example, assume that two AI functions are defined for "AI-based airspace beam prediction": AI functionality 1 and AI functionality 2. These two AI functions are targeted at different beam configurations, where AI functionality 1 corresponds to beam configuration 1 and AI functionality 2 corresponds to beam configuration 2. Two AI models can be defined for AI functionality 1, such as AI model 3 for implementing AI functionality 1 in low-speed scenarios and AI model 4 for implementing AI functionality 1 in high-speed scenarios. Similarly, two AI models can be defined for AI functionality 2, such as AI model 5 for implementing AI functionality 2 in low-speed scenarios and AI model 6 for implementing AI functionality 2 in high-speed scenarios. In this case, AI model 3 and AI model 4 are considered to be associated with AI functionality 1, and AI model 5 and AI model 6 are considered to be associated with AI functionality 2.

[0087] Optionally, the above-mentioned “association relationship between the AI ​​model and the AI ​​function” can be a one-to-one association relationship, or a one-to-many association relationship, or a many-to-one association relationship.

[0088] It should be noted that the above-mentioned “AI model” is only an exemplary name. It can also be a machine learning (ML) model or other models with similar functions, and this disclosure does not limit it here.

[0089] Further, optionally, the “AI functions respectively associated with at least one AI model supported by the first device” in the above-mentioned model-related information can be understood as: the AI ​​functions respectively implementable by at least one AI model supported by the first device.

[0090] Optionally, the “at least one AI function supported by the first device” in the above model-related information can be understood as: the AI ​​functions respectively implemented by at least one AI model supported by the first device.

[0091] Optionally, the “AI models associated with at least one AI function supported by the first device” in the above-mentioned model-related information can be understood as: an AI model supported by the first device and capable of implementing at least one AI function supported by the first device.

[0092] It can be seen from the above content that the above-mentioned model-related information can reflect the association relationship between the AI ​​model supported by the first device and the AI ​​function supported by the first device. Therefore, in some embodiments, when the first device indicates the model-related information of the first device to the second device, the second device can determine the association relationship between the AI ​​model supported by the first device and the AI ​​function supported by the first device based on the model-related information indicated by the first device, and then determine which AI functions each AI model supported by the first device is used to implement, so that the second device's understanding of the AI ​​model on the first device can be aligned with the actual situation of the AI ​​model of the first device, that is, the first device and the second device's understanding of the AI ​​model on the first device are unified, so that the second device can successfully manage the AI ​​model on the first device subsequently.

[0093] Optionally, in some embodiments, the above-mentioned "model-related information" can also include the application scenario of at least one AI model supported by the first device. Thus, when the first device indicates the model-related information of the first device to the second device, the second device can know the application scenario of at least one AI model supported by the first device, so that the second device can subsequently accurately manage the AI ​​model on the first device based on the application scenario of the AI ​​model.

[0094] Optionally, in some embodiments, the model-related information may be indicated to the second device when the first device needs to perform model identification with the second device. Optionally, the "first device needs to perform model identification with the second device" may include: when the second device instructs the first device to perform model identification, or when the first device meets a trigger condition for model identification, and optionally, the trigger condition may be pre-set.

[0095] Optionally, in some embodiments, when a first device indicates model-related information of the first device to a second device, the first device may indicate the model-related information to the second device based on a predefined "association between AI models and AI functions." For an introduction to the "association between AI models and AI functions," please refer to the aforementioned description.

[0096] In summary, in the communication method provided by the embodiment of the present disclosure, the first device indicates the model-related information of the first device to the second device; the model-related information includes at least one of the following: at least one AI model supported by the first device; the AI ​​functions respectively associated with the at least one AI model supported by the first device; at least one AI function supported by the first device; the AI ​​models respectively associated with the at least one AI function supported by the first device. It can be seen that the model-related information can reflect the association relationship between the AI ​​models supported by the first device and the AI ​​functions supported by the first device. Then, by sending the model-related information of the first device to the second device, the first device can determine which AI functions each AI model supported by the first device is used to implement based on the model-related information indicated by the first device, so that the second device's understanding of the AI ​​model on the first device can be aligned with the actual situation of the AI ​​model of the first device, unifying the understanding of the AI ​​model on the first device by the first and second devices, ensuring that the second device can successfully manage the AI ​​model on the first device in the future, and improving the stability of AI model management.

[0097] FIG3 is a flow chart of a communication method provided by an embodiment of the present disclosure. The method is executed by a first device. As shown in FIG3 , the communication method may include the following steps:

[0098] Step 301: Send at least one first information to a second device.

[0099] Optionally, in some embodiments, the first information may indicate an AI function supported by the first device, and different first information may indicate different AI functions supported by the first device. Optionally, in some embodiments, the first device may indicate the AI ​​function supported by the first device by including the name and / or serial number (IDentifier, ID) of the AI ​​function supported by the first device in the first information. Optionally, the name or ID of the AI ​​function supported by the first device may be pre-set, for example, the name or ID of the AI ​​function supported by the first device may be set autonomously by the first device, or may be determined by the second device and indicated to the first device.

[0100] Optionally, in some embodiments, the first information may further include at least one second information. Optionally, the second information included in the first information may be used to indicate: an AI model associated with the AI ​​function indicated by the first information and supported by the first device. In other words, the second information included in the first information may be used to indicate: an AI model supported by the first device for implementing the AI ​​function indicated by the first information. Different second information included in the first information is used to indicate different AI models. Optionally, the first device may indicate the AI ​​model by including the name and / or ID of the AI ​​model in the second information. Optionally, the name or ID of the AI ​​model may be pre-set, for example, the name or ID of the AI ​​model may be autonomously set by the first device, or may be determined by the second device and indicated to the first device.

[0101] For example, the format of the first information is exemplified below. In some embodiments, it is assumed that two AI functions (AI functionality) are defined for "AI-based spatial beam prediction", namely AI functionality 1 and AI functionality 2. The two AI functions are respectively for different beam configurations, where AI functionality 1 corresponds to beam configuration 1 and AI functionality 2 corresponds to beam configuration 2. In addition, two AI models (AI model) are defined for AI functionality 1, such as AI model x is defined to implement AI functionality 1 in low-speed scenarios, and AI model y is defined to implement AI functionality 1 in high-speed scenarios; at the same time, two AI models can also be defined for AI functionality 2, such as AI model m is defined to implement AI functionality 2 in low-speed scenarios, and AI model n is defined to implement AI functionality 2 in high-speed scenarios. It can be known that: AI model x, AI model y are associated with AI functionality 1; AI model m, AI model n are associated with AI functionality 2. At this time, if the AI ​​functions supported by the first device include AI functionality 1 and AI functionality 2, the format of the first information can be:

[0102] Support of functionality 1

[0103] {support of AI model x;

[0104] Support of AI model y:

[0105] }

[0106] Alternatively, the format of the first information may be:

[0107] Support of functionality 2

[0108] {support of AI model m;

[0109] Support of AI model n:

[0110] }

[0111] Optionally, in some embodiments, the second information included in different first information may be the same or different. Optionally, when an AI model can implement multiple functionalities, the second information included in the first information indicating the multiple functionalities may be the same. For example, assuming that the first device supports AI model m, and the AI ​​model m can support both AI functionality 1 and AI functionality 2, the format of the first information indicating AI functionality 1 may be:

[0112] Support of functionality 1

[0113] {support of AI model m;

[0114] }

[0115] The format of the first information indicating the AI ​​functionality 2 may be:

[0116] Support of functionality 2

[0117] {support of AI model m;

[0118] }

[0119] Optionally, it should be noted that, in some embodiments, the aforementioned first information can essentially be understood as information obtained after the model identification information is included in the functionality identification information. Optionally, the functionality identification information can be information transmitted during the functionality identification process. For example, when a first device performs functionality identification on a second device, the first device can send functionality identification information to the second device, and the functionality identification information can indicate the AI ​​functions supported by the first device. Optionally, the aforementioned model identification information can be information transmitted during the model identification process. For example, when a first device performs model identification on a second device, the first device can send model identification information to the second device, and the model identification information can indicate the AI ​​models supported by the first device. Based on this, in some embodiments, the method for constructing the aforementioned first information can be: by adding the associated model identification information for each AI function indicated by the functionality identification information to the original functionality identification information to construct the aforementioned at least one first information. Optionally, when the first device constructs the first information in the above manner, the AI ​​functions and AI models supported by the first device and having an associated relationship will be included in the same first information. Thus, when the first device sends the first information to the second device, the second device can determine the association between the AI ​​functions supported by the first device and the AI ​​models supported by the first device based on the received first information (such as it can be determined that the AI ​​functions and AI models contained in the same first information have an associated relationship). The second device's understanding of the AI ​​model on the first device can be aligned with the actual situation of the AI ​​model of the first device, thereby unifying the first and second devices' understanding of the AI ​​model on the first device and ensuring that the second device can subsequently successfully manage the AI ​​model on the first device.

[0120] Optionally, in some embodiments, the above-mentioned first information may be sent by the first device to the second device via Radio Resource Control (RRC) information and / or Medium Access Control (MAC) layer information.

[0121] To sum up, in the communication method provided by the embodiments of the present disclosure, the first device will send at least one first information to the second device. The first information can reflect the association between the AI ​​model supported by the first device and the AI ​​function supported by the first device. After the second device receives the first information sent by the first device, it can determine, based on the first information, which AI functions each AI model supported by the first device is used to implement. In this way, the second device's understanding of the AI ​​model on the first device can be aligned with the actual situation of the AI ​​model of the first device, unifying the first and second devices' understanding of the AI ​​model on the first device, ensuring that the second device can subsequently successfully manage the AI ​​model on the first device, and improving the stability of AI model management.

[0122] FIG4 is a flow chart of a communication method provided by an embodiment of the present disclosure. The method is executed by a first device. As shown in FIG4 , the communication method may include the following steps:

[0123] Step 401: In response to a predefined association relationship between an AI model and an AI function, at least one third information and / or at least one fourth information is sent to a second device.

[0124] Optionally, in some embodiments, the aforementioned “the association relationship between the AI ​​model and the AI ​​function is predefined” may be understood as: both the first device and the second device are pre-aware of the association relationship between the AI ​​model and the AI ​​function. For example, “the association relationship between the AI ​​model and the AI ​​function is predefined” may include: the association relationship between the AI ​​model and the AI ​​function is predefined by a protocol, or the association relationship between the AI ​​model and the AI ​​function is indicated by the first device to the second device, or the association relationship between the AI ​​model and the AI ​​function is indicated by the second device to the first device.

[0125] Optionally, in some embodiments, the third information may indicate an AI function supported by the first device, and the fourth information may indicate an AI model supported by the first device. Different third information may be used to indicate different AI functions supported by the first device, and different fourth information may be used to indicate different AI models supported by the first device.

[0126] Optionally, in some embodiments, when the association relationship between AI models and AI functions has been predefined, it means that both the first device and the second device already know which AI models are used to implement which AI functions. On this basis, the first device may no longer need to indicate to the second device the association relationship between the AI ​​models and AI functions supported by the first device. Instead, it only needs to indicate to the second device the AI ​​models supported by the first device and / or indicate the AI ​​functions supported by the first device, so that the second device can know which AI models in the first device are used to implement which AI functions.

[0127] Optionally, in some embodiments, when the first device indicates to the second device the AI ​​models supported by the first device (i.e., when the first device sends the above-mentioned fourth information to the second device), since the second device already knows the association between the AI ​​model and the AI ​​function, when the second device knows which AI models are supported by the first device based on the indication of the first device, the second device can directly infer which AI functions the various AI models supported by the first device are used to implement based on the association between the AI ​​model and the AI ​​function.

[0128] For example, assuming that the association relationship between AI models and AI functions is: AI model 1 is associated with AI functionality 1 (i.e., AI model 1 can be used to implement AI functionality 1), AI model 2 is associated with AI functionality 2 (i.e., AI model 2 can be used to implement AI functionality 2), and AI model 3 is associated with AI functionality 3 (i.e., AI model 3 can be used to implement AI functionality 3). At this time, if the first device supports AI models 1 and AI model 2, and supports AI functionality 1 and AI functionality 2, the first device may send at least one fourth information to the second device to indicate that the AI ​​models supported by the first device are AI model 1 and AI model 2. In addition, when the second device knows, based on the fourth information sent by the first device, that the AI ​​models supported by the first device are AI model 1 and AI model 2, based on the above-mentioned association between the AI ​​model and the AI ​​function, it can be determined that AI model 1 is used to implement AI functionality 1 and AI model 2 is used to implement AI functionality 2. Therefore, the second device can infer that the AI ​​functions supported by the first device are: AI functionality 1 and AI functionality 2, and that AI functionality 1 is implemented by AI model 1 and AI functionality 2 is implemented by AI model 2, thereby achieving alignment between the second device's understanding of the AI ​​model on the first device and the actual situation of the AI ​​model of the first device.

[0129] Similarly, in some embodiments, when the first device indicates to the second device the AI ​​functions supported by the first device (i.e., when the first device sends the above-mentioned third information to the second device), since the second device already knows the association between the AI ​​model and the AI ​​function, when the second device knows which AI functions are supported by the first device based on the indication of the first device, the second device can first infer which AI models are supported by the first device based on the association between the AI ​​model and the AI ​​function, and then further infer which AI functions each AI model supported by the first device is specifically used to implement.

[0130] However, it should be noted that in some embodiments, the aforementioned step of "the first device indicating to the second device the AI ​​function supported by the first device (i.e., the first device sending the aforementioned third information to the second device)" is subject to a prerequisite: "a one-to-one association between the AI ​​model and the AI ​​function." Specifically, when the AI ​​model and the AI ​​function are not associated one-to-one, for example, if AI functionality 1 is associated with AI model 1 and AI model 2 (i.e., both AI model 1 and AI model 2 can implement AI functionality 1), then if the first device supports either AI model 1 or AI model 2, the first device can support AI functionality 1. Based on this, when the first device indicates to the second device that the AI ​​function supported by the first device is AI functionality 1, the second device cannot determine whether the first device supports AI model 1, AI model 2, or both AI model 1 and AI model 2, resulting in the second device being unable to clearly understand the model on the first device. Based on this, the above-mentioned step of "sending at least one third information to the second device" needs to be performed under the premise that "the association relationship between the AI ​​model and the AI ​​function has been predefined and the association relationship between the AI ​​model and the AI ​​function is one-to-one". Only in this way can the purpose of "indicating to the second device the association relationship between the AI ​​model and the AI ​​function supported by the first device" be achieved.

[0131] For example, assuming that there is a one-to-one association relationship between AI models and AI functions, the association relationship is, for example: AI model 1 is associated with AI functionality 1 (i.e., AI model 1 can be used to implement AI functionality 1), AI model 2 is associated with AI functionality 2 (i.e., AI model 2 can be used to implement AI functionality 2), and AI model 3 is associated with AI functionality 3 (i.e., AI model 3 can be used to implement AI functionality 3). In this case, if the first device supports AI functionality 1 and AI functionality 2, and supports AI models 1 and AI model 2, the first device may send at least one third information to the second device to indicate that the AI ​​functions supported by the first device are AI functionality 1 and AI functionality 2. Furthermore, when the second device knows, based on the third information sent by the first device, that the AI ​​functions supported by the first device are AI functionality 1 and AI functionality 2, it can be determined based on the above-mentioned association between the AI ​​models and the AI ​​functions that: AI functionality 1 is uniquely implemented by AI model 1, and AI functionality 2 is uniquely implemented by AI model 2. Therefore, the second device can infer that the AI ​​models supported by the first device are: AI model 1 and AI model 2, and that AI model 1 is used to implement AI functionality 1, and AI model 2 is used to implement AI functionality 2, thereby achieving alignment between the second device's understanding of the AI ​​model on the first device and the actual situation of the AI ​​model of the first device.

[0132] Optionally, in some embodiments, the third information and / or fourth information may be sent by the first device to the second device via RRC information and / or MAC layer information.

[0133] In summary, in the communication method provided by the embodiments of the present disclosure, in response to the predefined association relationship between the AI ​​model and the AI ​​function, the first device will send at least one third information and / or at least one fourth information to the second device; the third information indicates the AI ​​function supported by the first device, and the fourth information indicates the AI ​​model supported by the first device. Wherein, under the premise that the association relationship between the AI ​​model and the AI ​​function has been predefined, the third information and / or the fourth information can reflect the association relationship between the AI ​​model supported by the first device and the AI ​​function supported by the first device. After the second device receives the third information and / or the fourth information sent by the first device, it can determine which AI functions each AI model supported by the first device is used to implement based on the third information and / or the fourth information, so that the second device's understanding of the AI ​​model on the first device can be aligned with the actual situation of the AI ​​model of the first device, unifying the understanding of the AI ​​model on the first device by the first and second devices, ensuring that the second device can subsequently successfully manage the AI ​​model on the first device, and improving the stability of AI model management.

[0134] FIG5 is a flow chart of a communication method provided by an embodiment of the present disclosure. The method is executed by a first device. As shown in FIG5 , the communication method may include the following steps:

[0135] Step 501: Send at least one fifth information to a second device.

[0136] Optionally, in some embodiments, the fifth information may indicate an AI model supported by the first device, and different fifth information may indicate different AI models supported by the first device. Optionally, in some embodiments, the first device may indicate the AI ​​model supported by the first device by including the name and / or ID of the AI ​​model supported by the first device in the fifth information. Optionally, the name or ID of the AI ​​model supported by the first device may be pre-set. For the relevant introduction of this part, please refer to the above embodiment.

[0137] Optionally, in some embodiments, the fifth information may further include at least one sixth information. Optionally, the sixth information included in the fifth information may be used to indicate: the AI ​​function associated with the AI ​​model indicated by the fifth information. In other words, the sixth information included in the fifth information may be used to indicate: the AI ​​function that can be implemented by the AI ​​model indicated by the fifth information, wherein different sixth information included in the fifth information is used to indicate different AI functions. Optionally, the first device may indicate the AI ​​function by including the name and / or ID of the AI ​​function in the sixth information. Optionally, the name or ID of the AI ​​function may be pre-set. For the relevant introduction to this part, please refer to the above embodiment.

[0138] For example, the format of the fifth information is exemplified below. In some embodiments, it is assumed that two AI functions (AI functionality) are defined for "AI-based spatial beam prediction", namely AI functionality 1 and AI functionality 2. The two AI functionality are respectively for different beam configurations, wherein AI functionality 1 corresponds to beam configuration 1, AI functionality 2 corresponds to beam configuration 2, and AI model m is defined to implement AI functionality 1; AI model n is defined to implement AI functionality 2. It can be known that: AI model m is associated with AI functionality 1; AI model n is associated with AI functionality 2. At this time, if the AI ​​models supported by the first device are: AI model m and AI model n, the format of the fifth information can be:

[0139] Support of AI model m

[0140] {linked Functionality Functionality 1}

[0141] Alternatively, the format of the fifth information may be:

[0142] Support of AI model n

[0143] {linked Functionality Functionality 2}

[0144] Optionally, it should be noted that, in some embodiments, the fifth information described above can essentially be understood as information obtained after the functionality identification information is included in the model identification information. For detailed descriptions of the functionality identification information and model identification, please refer to the description of the aforementioned embodiments.

[0145] Based on the above description, in some embodiments, the method for constructing the above-mentioned fifth information can be: at least one fifth information is constructed by adding the associated functionality identification information for each AI model indicated by the model identification information in the original model identification information. Optionally, when the first device constructs the fifth information in the above manner, the AI ​​functions and AI models supported by the first device and having an associated relationship are included in the same fifth information. Therefore, when the first device sends the fifth information to the second device, the second device can determine the association between the AI ​​functions supported by the first device and the AI ​​models supported by the first device based on the received fifth information (such as determining that the AI ​​functions and AI models included in the same fifth information have an associated relationship). This can align the second device's understanding of the AI ​​model on the first device with the actual situation of the AI ​​model on the first device, thereby unifying the understanding of the AI ​​model on the first device by the first and second devices, ensuring that the second device can subsequently successfully manage the AI ​​model on the first device, and improving the stability of AI model management.

[0146] Optionally, in some embodiments, the fifth information may be sent by the first device to the second device via RRC information and / or MAC layer information.

[0147] To sum up, in the communication method provided by the embodiments of the present disclosure, the first device will send at least one fifth information to the second device. The fifth information can reflect the association between the AI ​​model supported by the first device and the AI ​​function supported by the first device. After the second device receives the fifth information sent by the first device, it can determine, based on the fifth information, which AI functions each AI model supported by the first device is used to implement. This allows the second device's understanding of the AI ​​model on the first device to be aligned with the actual situation of the AI ​​model on the first device, unifying the first and second devices' understanding of the AI ​​model on the first device, ensuring that the second device can subsequently successfully manage the AI ​​model on the first device, and improving the stability of AI model management.

[0148] FIG6 is a flow chart of a communication method provided by an embodiment of the present disclosure. The method is executed by a first device. As shown in FIG6 , the communication method may include the following steps:

[0149] Step 601: Send at least one seventh information to a second device.

[0150] Optionally, in some embodiments, the seventh information may indicate an AI function supported by the first device, and different seventh information may indicate different AI functions supported by the first device. Optionally, in some embodiments, the first device may indicate the AI ​​function supported by the first device by including the name of the AI ​​function supported by the first device in the seventh information.

[0151] For example, assuming that the AI ​​functions supported by the first device are AI Functionality x and AI Functionality y, the seventh information may include Support of AI Functionality x; or, the seventh information may, for example, be: Support of AI Functionality y.

[0152] Optionally, in some embodiments, the seventh information may be the functionality identification information. Optionally, step 601 may be considered as a functionality identification process of the first device.

[0153] Optionally, in some embodiments, the first device may send the seventh information mentioned above to the second device via RRC information and / or MAC layer information.

[0154] Step 602: Receive identification information sent by the second device.

[0155] Optionally, in some embodiments, the identification information may include: an identifier assigned by the second device to at least one AI function supported by the first device.

[0156] Optionally, in some embodiments, when the second device receives the seventh information sent by the first device, it may first verify the seventh information (such as performing a cyclic redundancy check (CRC)). When the verification passes, the second device confirms that the reception is successful (or determines that the functionality identification process of the first device is successful). The second device can then assign identifiers to the AI ​​functions supported by the first device indicated by the seventh information to obtain identification information, and send the identification information to the first device.

[0157] For example, if the seventh information sent by the first device indicates AI Functionality x and AI Functionality y, the second device may assign an identifier "1" to AI Functionality x and an identifier "2" to AI Functionality y, and send identification information to the first device. The identification information may be, for example, AI functionality 1, AI functionality 2. At this time, based on the identification information, the first device can know that the identifier corresponding to AI Functionality x is AI functionality 1, and the identifier corresponding to AI Functionality y is AI functionality 2.

[0158] Step 603: Send at least one eighth information to the second device.

[0159] Optionally, in some embodiments, the eighth information may indicate an AI model supported by the first device, and different eighth information may indicate different AI models supported by the first device. Optionally, in some embodiments, the first device may indicate the AI ​​model supported by the first device by including the name and / or ID of the AI ​​model supported by the first device in the eighth information. Optionally, the name or ID of the AI ​​model supported by the first device may be pre-set. For the relevant introduction of this part, please refer to the above embodiment.

[0160] Optionally, in some embodiments, the eighth information may further include at least one identification information. Optionally, the at least one identification information included in the eighth information may be: an identification corresponding to at least one AI function associated with the AI ​​model indicated by the eighth information.

[0161] For example, assuming that the AI ​​models supported by the first device are AI model m and AI model n, where AI model m is associated with AI Functionality x (i.e., AI model m is used to implement AI Functionality x), and AI model n is associated with AI Functionality y (i.e., AI model n is used to implement AI Functionality y), then the format of the eighth information can be:

[0162] Support of AI model m

[0163] {Linked AI functionality#1

[0164] }

[0165] Alternatively, the format of the eighth information may be:

[0166] Support of AI model n

[0167] {Linked AI functionality#2

[0168] }

[0169] Optionally, in some embodiments, the eighth information may be sent by the first device to the second device via RRC information and / or MAC layer information.

[0170] To sum up, in the communication method provided by the embodiments of the present disclosure, the first device will send at least one eighth information to the second device, and the eighth information can reflect the association between the AI ​​model supported by the first device and the AI ​​function supported by the first device. After the second device receives the eighth information sent by the first device, it can determine, based on the eighth information, which AI functions each AI model supported by the first device is used to implement, so that the second device's understanding of the AI ​​model on the first device can be aligned with the actual situation of the AI ​​model of the first device, unifying the first and second devices' understanding of the AI ​​model on the first device, ensuring that the second device can subsequently successfully manage the AI ​​model on the first device, and improving the stability of AI model management.

[0171] FIG7 is a flow chart of a communication method provided by an embodiment of the present disclosure. The method is performed by a second device. As shown in FIG7 , the communication method may include the following steps:

[0172] Step 701: Determine model-related information of the first device based on an indication of the first device.

[0173] For a detailed description of step 701 , please refer to the above embodiment description.

[0174] In summary, in the communication method provided by the embodiment of the present disclosure, the first device indicates the model-related information of the first device to the second device; the model-related information includes at least one of the following: at least one AI model supported by the first device; the AI ​​functions respectively associated with the at least one AI model supported by the first device; at least one AI function supported by the first device; the AI ​​models respectively associated with the at least one AI function supported by the first device. It can be seen that the model-related information can reflect the association relationship between the AI ​​models supported by the first device and the AI ​​functions supported by the first device. Then, by sending the model-related information of the first device to the second device, the first device can determine which AI functions each AI model supported by the first device is used to implement based on the model-related information indicated by the first device, so that the second device's understanding of the AI ​​model on the first device can be aligned with the actual situation of the AI ​​model of the first device, unifying the understanding of the AI ​​model on the first device by the first and second devices, ensuring that the second device can successfully manage the AI ​​model on the first device in the future, and improving the stability of AI model management.

[0175] FIG8 is a flow chart of a communication method provided by an embodiment of the present disclosure. The method is performed by a second device. As shown in FIG8 , the communication method may include the following steps:

[0176] Step 801: Receive at least one first information sent by a first device.

[0177] For a detailed description of step 801 , please refer to the above embodiment description.

[0178] To sum up, in the communication method provided by the embodiments of the present disclosure, the first device will send at least one first information to the second device. The first information can reflect the association between the AI ​​model supported by the first device and the AI ​​function supported by the first device. After the second device receives the first information sent by the first device, it can determine, based on the first information, which AI functions each AI model supported by the first device is used to implement. In this way, the second device's understanding of the AI ​​model on the first device can be aligned with the actual situation of the AI ​​model of the first device, unifying the first and second devices' understanding of the AI ​​model on the first device, ensuring that the second device can subsequently successfully manage the AI ​​model on the first device, and improving the stability of AI model management.

[0179] FIG9 is a flow chart of a communication method provided by an embodiment of the present disclosure. The method is performed by a second device. As shown in FIG9 , the communication method may include the following steps:

[0180] Step 901: In response to a predefined association relationship between an AI model and an AI function, receive at least one third information and / or at least one fourth information sent by a first device.

[0181] For a detailed description of step 901 , please refer to the above embodiment description.

[0182] In summary, in the communication method provided by the embodiments of the present disclosure, in response to the predefined association relationship between the AI ​​model and the AI ​​function, the first device will send at least one third information and / or at least one fourth information to the second device; the third information indicates the AI ​​function supported by the first device, and the fourth information indicates the AI ​​model supported by the first device. Wherein, under the premise that the association relationship between the AI ​​model and the AI ​​function has been predefined, the third information and / or the fourth information can reflect the association relationship between the AI ​​model supported by the first device and the AI ​​function supported by the first device. After the second device receives the third information and / or the fourth information sent by the first device, it can determine which AI functions each AI model supported by the first device is used to implement based on the third information and / or the fourth information, so that the second device's understanding of the AI ​​model on the first device can be aligned with the actual situation of the AI ​​model of the first device, unifying the understanding of the AI ​​model on the first device by the first and second devices, ensuring that the second device can subsequently successfully manage the AI ​​model on the first device, and improving the stability of AI model management.

[0183] FIG10 is a flow chart of a communication method provided by an embodiment of the present disclosure. The method is performed by a second device. As shown in FIG10 , the communication method may include the following steps:

[0184] Step 1001: Receive at least one fifth information sent by a first device.

[0185] For a detailed description of step 1001 , please refer to the above embodiment description.

[0186] To sum up, in the communication method provided by the embodiments of the present disclosure, the first device will send at least one fifth information to the second device. The fifth information can reflect the association between the AI ​​model supported by the first device and the AI ​​function supported by the first device. After the second device receives the fifth information sent by the first device, it can determine, based on the fifth information, which AI functions each AI model supported by the first device is used to implement. This allows the second device's understanding of the AI ​​model on the first device to be aligned with the actual situation of the AI ​​model on the first device, unifying the first and second devices' understanding of the AI ​​model on the first device, ensuring that the second device can subsequently successfully manage the AI ​​model on the first device, and improving the stability of AI model management.

[0187] FIG11 is a flow chart of a communication method provided by an embodiment of the present disclosure. The method is performed by a second device. As shown in FIG11 , the communication method may include the following steps:

[0188] Step 1101: Receive at least one seventh information sent by a first device;

[0189] Step 1102: Send identification information to the first device;

[0190] Step 1103: Receive at least one eighth information sent by the first device.

[0191] For a detailed description of steps 1101 to 1103 , please refer to the above embodiment description.

[0192] To sum up, in the communication method provided by the embodiments of the present disclosure, the first device will send at least one eighth information to the second device, and the eighth information can reflect the association between the AI ​​model supported by the first device and the AI ​​function supported by the first device. After the second device receives the eighth information sent by the first device, it can determine, based on the eighth information, which AI functions each AI model supported by the first device is used to implement, so that the second device's understanding of the AI ​​model on the first device can be aligned with the actual situation of the AI ​​model of the first device, unifying the first and second devices' understanding of the AI ​​model on the first device, ensuring that the second device can subsequently successfully manage the AI ​​model on the first device, and improving the stability of AI model management.

[0193] FIG12 is a schematic diagram of the structure of a communication device provided by an embodiment of the present disclosure. As shown in FIG12 , the device may include:

[0194] A transceiver module, configured to indicate model-related information of the first device to a second device;

[0195] The model-related information includes at least one of the following:

[0196] at least one AI model supported by the first device;

[0197] an AI function respectively associated with at least one AI model supported by the first device;

[0198] at least one AI function supported by the first device;

[0199] an AI model associated with at least one AI function supported by the first device.

[0200] In summary, in the communication device provided in the embodiment of the present disclosure, the first device indicates the model-related information of the first device to the second device; the model-related information includes at least one of the following: at least one AI model supported by the first device; the AI ​​functions respectively associated with the at least one AI model supported by the first device; at least one AI function supported by the first device; the AI ​​models respectively associated with the at least one AI function supported by the first device. It can be seen that the model-related information can reflect the association relationship between the AI ​​models supported by the first device and the AI ​​functions supported by the first device. Then, by sending the model-related information of the first device to the second device, the first device can determine which AI functions each AI model supported by the first device is used to implement based on the model-related information indicated by the first device, so that the second device's understanding of the AI ​​model on the first device can be aligned with the actual situation of the AI ​​model of the first device, unifying the understanding of the AI ​​model on the first device by the first and second devices, ensuring that the second device can successfully manage the AI ​​model on the first device in the future, and improving the stability of AI model management.

[0201] Optionally, in one embodiment of the present disclosure, the transceiver module is further configured to:

[0202] Send at least one first information to the second device, where the first information indicates an AI function supported by the first device, and the first information also includes at least one second information, where the second information is used to indicate: an AI model associated with the AI ​​function indicated by the first information and supported by the first device.

[0203] Optionally, in an embodiment of the present disclosure, the second information included in different first information is the same or different.

[0204] Optionally, in one embodiment of the present disclosure, the transceiver module is further configured to:

[0205] In response to the association relationship between the AI ​​model and the AI ​​function being predefined, sending at least one third information and / or at least one fourth information to the second device;

[0206] The third information indicates the AI ​​function supported by the first device, and the fourth information indicates the AI ​​model supported by the first device.

[0207] Optionally, in one embodiment of the present disclosure, the transceiver module is further configured to:

[0208] In response to a one-to-one association relationship between the AI ​​model and the AI ​​function, at least one third information is sent to the second device.

[0209] Optionally, in one embodiment of the present disclosure, the transceiver module is further configured to:

[0210] Send at least one fifth information to the second device; the fifth information indicates the AI ​​model supported by the first device, and the fifth information also includes at least one sixth information, wherein the sixth information is used to indicate: the AI ​​function associated with the AI ​​model indicated by the fifth information.

[0211] Optionally, in one embodiment of the present disclosure, the transceiver module is further configured to:

[0212] Sending at least one seventh information to the second device, where the seventh information indicates an AI function supported by the first device;

[0213] receiving identification information sent by the second device, where the identification information includes: an identifier assigned by the second device to at least one AI function supported by the first device;

[0214] Send at least one eighth information to the second device, where the eighth information indicates the AI ​​model supported by the first device, and the eighth information also includes at least one identification information, where the at least one identification information is: an identification corresponding to at least one AI function associated with the AI ​​model indicated by the eighth information.

[0215] Optionally, in one embodiment of the present disclosure, the model-related information also includes: application scenarios of at least one AI model supported by the first device.

[0216] Optionally, in one embodiment of the present disclosure, the first device is a device on which an AI model is deployed or stored, and the second device is a device that is to manage the AI ​​model in the first device.

[0217] FIG13 is a schematic diagram of the structure of a communication device provided by an embodiment of the present disclosure. As shown in FIG13 , the device may include:

[0218] a processing module, configured to determine model-related information of the first device based on an indication of the first device;

[0219] The model-related information includes at least one of the following:

[0220] at least one AI model supported by the first device;

[0221] an AI function respectively associated with at least one AI model supported by the first device;

[0222] at least one AI function supported by the first device;

[0223] an AI model associated with at least one AI function supported by the first device.

[0224] In summary, in the communication device provided in the embodiment of the present disclosure, the first device indicates the model-related information of the first device to the second device; the model-related information includes at least one of the following: at least one AI model supported by the first device; the AI ​​functions respectively associated with the at least one AI model supported by the first device; at least one AI function supported by the first device; the AI ​​models respectively associated with the at least one AI function supported by the first device. It can be seen that the model-related information can reflect the association relationship between the AI ​​models supported by the first device and the AI ​​functions supported by the first device. Then, by sending the model-related information of the first device to the second device, the first device can determine which AI functions each AI model supported by the first device is used to implement based on the model-related information indicated by the first device, so that the second device's understanding of the AI ​​model on the first device can be aligned with the actual situation of the AI ​​model of the first device, unifying the understanding of the AI ​​model on the first device by the first and second devices, ensuring that the second device can successfully manage the AI ​​model on the first device in the future, and improving the stability of AI model management.

[0225] Optionally, in one embodiment of the present disclosure, the processing module is further configured to:

[0226] Receive at least one first information sent by the first device, where the first information indicates an AI function supported by the first device, and the first information also includes at least one second information, wherein the second information is used to indicate: an AI model associated with the AI ​​function indicated by the first information and supported by the first device.

[0227] Optionally, in an embodiment of the present disclosure, the second information included in different first information is the same or different.

[0228] Optionally, in one embodiment of the present disclosure, the processing module is further configured to:

[0229] In response to the association relationship between the AI ​​model and the AI ​​function being predefined, receiving at least one third information and / or at least one fourth information sent by the first device;

[0230] The third information indicates the AI ​​function supported by the first device, and the fourth information indicates the AI ​​model supported by the first device.

[0231] Optionally, in one embodiment of the present disclosure, the processing module is further configured to:

[0232] In response to a one-to-one association relationship between the AI ​​model and the AI ​​function, at least one third information sent by the first device is received.

[0233] Optionally, in one embodiment of the present disclosure, the processing module is further configured to:

[0234] Receive at least one fifth information sent by the first device; the fifth information indicates the AI ​​model supported by the first device, and the fifth information also includes at least one sixth information, wherein the sixth information is used to indicate: the AI ​​function associated with the AI ​​model indicated by the fifth information.

[0235] Optionally, in one embodiment of the present disclosure, the processing module is further configured to:

[0236] receiving at least one seventh information sent by the first device, where the seventh information indicates an AI function supported by the first device;

[0237] Sending identification information to the first device, where the identification information includes: an identifier assigned by the second device to at least one AI function supported by the first device;

[0238] Receive at least one eighth information sent by the first device, where the eighth information indicates an AI model supported by the first device, and the eighth information also includes at least one identification information, where the at least one identification information is: an identification corresponding to at least one AI function associated with the AI ​​model indicated by the eighth information.

[0239] Optionally, in one embodiment of the present disclosure, the model-related information also includes: application scenarios of at least one AI model supported by the first device.

[0240] Optionally, in one embodiment of the present disclosure, the first device is a device on which an AI model is deployed or stored, and the second device is a device that is to manage the AI ​​model in the first device.

[0241] The following is an example introduction to the communication method disclosed in the present invention:

[0242] Optionally, in AI-based deployment solutions, the model may be deployed on the terminal side. At the same time, the network side also needs to participate in the management of the AI ​​model, so the network side and the terminal side need to align the relevant information of the AI ​​model. Therefore, 3GPP defines the following process: functionality identification, that is, the terminal needs to report the AI ​​functions it supports.

[0243] In addition, in the 3GPP discussion, the following relationship is also defined

[0244] An AI / ML feature can contain one or more functionalities, each of which can be targeted at a specific application environment or scenario.

[0245] The AI / ML feature here can be an AI / ML use case, for example, the AI / ML feature can be CSI compression, or time domain CSI prediction, or AI-based spatial domain beam prediction, etc.

[0246] A functionality can contain one or more AI models.

[0247] Optionally, model identification was defined in the 3GPP discussion. The purpose of AI model identification is to unify the understanding of AI models between the network and the terminal. However, the specific process of model identification is not clear, and the relationship between model identification and functionality identification is also unclear.

[0248] Optionally, the present disclosure provides a method for mapping functionality and model and a method for model identification.

[0249] In some embodiments, (1) the functionality associated with the AI ​​model is determined. The functionality associated with the AI ​​model may be one or more, and AI model identification is performed based on a mapping relationship between the AI ​​model and the functionality.

[0250] In some embodiments, in response to the terminal needing to perform model identification, the terminal needs to perform functionality identification. The functionality identification reporting information includes the terminal's model identification information. For example, for AI-based spatial beam prediction, two functionalities are defined, and the two functionalities are respectively for different beam configurations or different reference signal configurations. Two AI models are also defined in the two functionalities, one AI model is used for high-speed scenarios, and the other AI model is used for low-speed scenarios. In this case, when the terminal reports the model functionality, it can report in the following manner:

[0251] Support of functionality 1

[0252] {support of AI model x;

[0253] Support of AI model y:

[0254] }

[0255] Support of functionality 2

[0256] {support of AI model m;

[0257] Support of AI model n:

[0258] }

[0259] In some embodiments, in response to an AI model being able to implement multiple functionalities, multiple functional identifications are also required during the AI ​​model identification process.

[0260] For example, AI model m can support both functionality 1 and functionality 2. Then the model identification method can be

[0261] Support of functionality 1

[0262] {support of AI model m;

[0263] }

[0264] Support of functionality 2

[0265] {support of AI model m;

[0266] }

[0267] In some embodiments, the relationship between functionality and AI model is predefined in advance, and in response to the terminal needing to perform model identification, AI model identification can be performed directly.

[0268] For example, if the relationship between AI model m and functionality 1 is predefined, and the relationship between AI model n and functionality 2 is predefined, then when the terminal reports AI model m or AI model n, the network will know that AI model m can implement function 1 and AI model n can implement functionality 2 through the predefined relationship. If an AI model can implement multiple functions, then a one-to-many mapping can be achieved when the mapping relationship is predefined.

[0269] In some embodiments, in response to a request for AI model identification by a terminal, the terminal directly performs model identification, where the model identification information includes information about the implemented AI functionality.

[0270] For example

[0271] Support of AI model m

[0272] {linked Functionality Functionality#1}

[0273] Support of AI model n

[0274] {linked Functionality Functionality 2}

[0275] If an AI model can be mapped to multiple AI functionality, then multiple linked functionality can be reported.

[0276] In some embodiments, in response to the terminal needing to perform AI model identification, the terminal needs to perform functionality identification, and then perform model identification after functionality identification is successful.

[0277] For example

[0278] -Terminal sends information

[0279] Support of Functionality x

[0280] Support of Functionality y

[0281] - The network confirms success and assigns corresponding IDs to each functionality: functionality#1, functionality#2

[0282] -The terminal performs model identification and reports the corresponding functionality

[0283] Support of AI model m

[0284] {Linked functionality#1

[0285] }

[0286] Support of AI model n

[0287] {Linked functionality#2

[0288] }

[0289] Optionally, when the terminal reports functionality 1 or functionality 2, it corresponds to configuration 1 or configuration 2. This actually proves that the terminal can only use AI work in configuration 1 or configuration 2. In addition to these configurations, the terminal does not support AI-based work.

[0290] In addition, the network side also knows that under configuration 1, the terminal uses functionality 1 to work, and under configuration 2, the terminal uses functionality 2 to work. In this case, the network can also manage the functionality according to the configuration information, such as activation and switching.

[0291] Optionally, the network can number or name AI models. For example, if a terminal reports that it supports AI model m and also reports that the AI ​​model is used in high-speed scenarios, and the terminal reports five models in sequence, the network can number these five models in sequence and inform the terminal of the network numbering.

[0292] Optionally, the indication of the corresponding functionality can be based on an ID or a name. Indication using only an ID or a name can be predefined. For example, the protocol predefines the configuration corresponding to functionality #1 and the specific function. The terminal then reports based on its support for the predefined content of the protocol. This method can be used in (2), (3), and (5). Another method is that the protocol does not predefine each functionality, and the terminal reports its support for the functionality. In this case, the terminal can name it itself or the network can name it. If the network is the one that names it, some preset rules are needed to synchronize the understanding of the functionality between the network and the terminal. For example, if the terminal reports N functionalities in sequence in the signaling, the network will assign N IDs or N names.

[0293] Please refer to Figure 14, which is a schematic diagram of the structure of a communication device 1400 provided in an embodiment of the present disclosure. Communication device 1400 can be a network device or a terminal device, or a chip, chip system, or processor that supports a network device in implementing the above-mentioned method. It can also be a chip, chip system, or processor that supports a terminal device in implementing the above-mentioned method. This device can be used to implement the method described in the above-mentioned method embodiment. For details, please refer to the description of the above-mentioned method embodiment.

[0294] The communication device 1400 may include one or more processors 1401. The processor 1401 may be a general-purpose processor or a dedicated processor. For example, it may be a baseband processor or a central processing unit. The baseband processor may be used to process communication protocols and communication data, and the central processing unit may be used to control the communication device (e.g., a base station, a baseband chip, a terminal device, a terminal device chip, a DU or CU, etc.), execute computer programs, and process computer program data.

[0295] Optionally, the communication device 1400 may further include one or more memories 1402, on which a computer program 1404 may be stored. The processor 1401 executes the computer program 1404 to cause the communication device 1400 to perform the method described in the above method embodiment. Optionally, the memory 1402 may also store data. The communication device 1400 and the memory 1402 may be provided separately or integrated together.

[0296] Optionally, the communication device 1400 may further include a transceiver 1405 and an antenna 1406. The transceiver 1405 may be referred to as a transceiver unit, a transceiver, or a transceiver circuit, etc., and is configured to implement transceiver functions. The transceiver 1405 may include a receiver and a transmitter. The receiver may be referred to as a receiver or a receiving circuit, etc., and is configured to implement a receiving function; the transmitter may be referred to as a transmitter or a transmitting circuit, etc., and is configured to implement a transmitting function.

[0297] Optionally, the communication device 1400 may further include one or more interface circuits 1406. The interface circuit 1406 is configured to receive code instructions and transmit the code instructions to the processor 1401. The processor 1401 executes the code instructions to enable the communication device 1400 to perform the method described in the above method embodiment.

[0298] In one implementation, processor 1401 may include a transceiver for implementing receiving and transmitting functions. For example, the transceiver may be a transceiver circuit, an interface, or an interface circuit. The transceiver circuit, interface, or interface circuit for implementing the receiving and transmitting functions may be separate or integrated. The transceiver circuit, interface, or interface circuit may be used for reading and writing code / data, or may be used for transmitting or delivering signals.

[0299] In one implementation, processor 1401 may store a computer program 1403. Computer program 1403, when executed on processor 1401, may cause communication device 1400 to perform the method described in the above method embodiment. Computer program 1403 may be embedded in processor 1401, in which case processor 1401 may be implemented by hardware.

[0300] In one implementation, the communication device 1400 may include a circuit that can implement the functions of sending, receiving, or communicating in the aforementioned method embodiments. The processor and transceiver described in the present disclosure can be implemented on an integrated circuit (IC), an analog IC, a radio frequency integrated circuit RFIC, a mixed signal IC, an application specific integrated circuit (ASIC), a printed circuit board (PCB), an electronic device, etc. The processor and transceiver can also be manufactured using various IC process technologies, such as complementary metal oxide semiconductor (CMOS), N-type metal oxide semiconductor (nMetal-oxide-semiconductor, NMOS), P-type metal oxide semiconductor (positive channel metal oxide semiconductor, PMOS), bipolar junction transistor (bipolar junction transistor, BJT), bipolar CMOS (BiCMOS), silicon germanium (SiGe), gallium arsenide (GaAs), etc.

[0301] The communication device described in the above embodiments may be a network device or a terminal device, but the scope of the communication device described in this disclosure is not limited thereto, and the structure of the communication device may not be limited to FIG14. The communication device may be an independent device or may be part of a larger device. For example, the communication device may be:

[0302] (1) An independent integrated circuit (IC), or chip, or chip system or subsystem;

[0303] (2) a collection of one or more ICs, optionally including a storage component for storing data and computer programs;

[0304] (3) ASIC, such as modem;

[0305] (4) Modules that can be embedded in other devices;

[0306] (5) Receivers, terminal devices, intelligent terminal devices, cellular phones, wireless devices, handheld devices, mobile units, vehicle-mounted devices, network devices, cloud devices, artificial intelligence devices, etc.;

[0307] (6)Others, etc.

[0308] For the case where the communication device can be a chip or a chip system, please refer to the schematic diagram of the chip structure shown in Figure 15. The chip shown in Figure 15 includes a processor 1501 and an interface 1502. Optionally, the number of processors 1501 can be one or more, and the number of interfaces 1502 can be multiple.

[0309] Optionally, the chip further includes a memory 1503, which is used to store necessary computer programs and data.

[0310] Those skilled in the art will also appreciate that the various illustrative logical blocks and steps listed in the embodiments of the present disclosure may be implemented by electronic hardware, computer software, or a combination of both. Whether such functionality is implemented by hardware or software depends on the specific application and the design requirements of the entire system. Those skilled in the art may use various methods to implement the described functionality for each specific application, but such implementation should not be construed as exceeding the scope of protection of the embodiments of the present disclosure.

[0311] The present disclosure also provides a readable storage medium having instructions stored thereon, which implement the functions of any of the above method embodiments when executed by a computer.

[0312] The present disclosure also provides a computer program product, which implements the functions of any of the above method embodiments when executed by a computer.

[0313] In the above embodiments, all or part of the embodiments can be implemented by software, hardware, firmware or any combination thereof. When implemented using software, all or part of the embodiments can be implemented in the form of a computer program product. The computer program product includes one or more computer programs. When the computer program is loaded and executed on a computer, all or part of the processes or functions described in the embodiments of the present disclosure are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer program can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer program can be transmitted from one website, computer, server or data center to another website, computer, server or data center via a wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) method. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that includes one or more available media integrated therein. The available medium may be a magnetic medium (eg, a floppy disk, a hard disk, a magnetic tape), an optical medium (eg, a high-density digital video disc (DVD)), or a semiconductor medium (eg, a solid state disk (SSD)).

[0314] Those skilled in the art will understand that the various numerical numbers such as first and second involved in the present disclosure are only for the convenience of description and are not used to limit the scope of the embodiments of the present disclosure, and also indicate the order of precedence.

[0315] The at least one in the present disclosure can also be described as one or more, and the multiple can be two, three, four or more, which is not limited in the present disclosure. In the embodiments of the present disclosure, for a technical feature, the technical features in the technical feature are distinguished by "first", "second", "third", "A", "B", "C" and "D", and there is no order of precedence or size between the technical features described by "first", "second", "third", "A", "B", "C" and "D".

[0316] The correspondences shown in the tables in the present disclosure can be configured or predefined. The values ​​of the signals in the tables are merely examples and can be configured to other values, which are not limited by the present disclosure. When configuring the correspondences between the configuration information and the parameters, it is not necessarily required to configure all the correspondences shown in the tables. For example, in the tables in the present disclosure, the correspondences shown in certain rows may not be configured. For another example, appropriate deformation adjustments may be made based on the above tables, such as splitting, merging, etc. The names of the parameters shown in the titles of the above tables may also adopt other names that can be understood by the communication device, and the values ​​or representations of the parameters may also adopt other values ​​or representations that can be understood by the communication device. When implementing the above tables, other data structures may also be used, such as arrays, queues, containers, stacks, linear lists, pointers, linked lists, trees, graphs, structures, classes, heaps, hash tables or hash tables, etc.

[0317] The predefined in the present disclosure may be understood as defined, predefined, stored, pre-stored, pre-negotiated, pre-configured, solidified, or pre-burned.

[0318] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this disclosure.

[0319] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0320] The above description is merely a specific embodiment of the present disclosure, but the scope of protection of the present disclosure is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this disclosure should be included in the scope of protection of the present disclosure. Therefore, the scope of protection of the present disclosure should be based on the scope of protection of the claims.

Claims

1. A communication method, characterized in that: The method is performed by a first device, and includes: indicating model-related information of the first device to a second device; The model-related information includes at least one of the following: At least one artificial intelligence (AI) model supported by the first device; an AI function respectively associated with at least one AI model supported by the first device; at least one AI function supported by the first device; An AI model associated with at least one AI function supported by the first device.

2. The method according to claim 1, characterized in that The indicating the model-related information of the first device to the second device includes: Send at least one first information to the second device, wherein the first information indicates an AI function supported by the first device, and the first information also includes at least one second information, wherein the second information is used to indicate: an AI model associated with the AI ​​function indicated by the first information and supported by the first device.

3. The method according to claim 2, characterized in that The second information included in different first information may be the same or different.

4. The method according to claim 1, characterized in that The indicating the model-related information of the first device to the second device includes: In response to the association relationship between the AI ​​model and the AI ​​function being predefined, sending at least one third information and / or at least one fourth information to the second device; Among them, the third information indicates the AI ​​function supported by the first device, and the fourth information indicates the AI ​​model supported by the first device.

5. The method according to claim 4, characterized in that The sending at least one third information to the second device includes: In response to a one-to-one association relationship between the AI ​​model and the AI ​​function, at least one third information is sent to the second device.

6. The method according to claim 1, characterized in that The indicating the model-related information of the first device to the second device includes: Send at least one fifth information to the second device; the fifth information indicates the AI ​​model supported by the first device, and the fifth information also includes at least one sixth information, wherein the sixth information is used to indicate: the AI ​​function associated with the AI ​​model indicated by the fifth information.

7. The method according to claim 1, characterized in that The indicating the model-related information of the first device to the second device includes: Sending at least one seventh information to the second device, where the seventh information indicates an AI function supported by the first device; receiving identification information sent by the second device, where the identification information includes: an identification assigned by the second device to at least one AI function supported by the first device; At least one eighth information is sent to the second device, wherein the eighth information indicates an AI model supported by the first device, and the eighth information also includes at least one identification information, wherein the at least one identification information is: an identification corresponding to at least one AI function associated with the AI ​​model indicated by the eighth information.

8. The method according to any one of claims 1 to 7, characterized in that: The model-related information also includes: an application scenario of at least one AI model supported by the first device.

9. The method according to any one of claims 1 to 7, characterized in that: The first device is a device on which an AI model is deployed or stored, and the second device is a device that is to manage the AI ​​model in the first device.

10. A communication method, characterized in that: The method is performed by a second device, and the method includes: determining model-related information of the first device based on the indication of the first device; The model-related information includes at least one of the following: at least one AI model supported by the first device; an AI function respectively associated with at least one AI model supported by the first device; at least one AI function supported by the first device; An AI model associated with at least one AI function supported by the first device.

11. The method according to claim 10, characterized in that The determining the model-related information of the first device based on the indication of the first device includes: Receive at least one first information sent by the first device, wherein the first information indicates an AI function supported by the first device, and the first information also includes at least one second information, wherein the second information is used to indicate: an AI model associated with the AI ​​function indicated by the first information and supported by the first device.

12. The method according to claim 11, characterized in that The second information included in different first information may be the same or different.

13. The method according to claim 10, characterized in that The determining the model-related information of the first device based on the indication of the first device includes: In response to the association relationship between the AI ​​model and the AI ​​function being predefined, receiving at least one third information and / or at least one fourth information sent by the first device; Among them, the third information indicates the AI ​​function supported by the first device, and the fourth information indicates the AI ​​model supported by the first device.

14. The method according to claim 13, characterized in that The receiving at least one third information sent by the first device includes: In response to a one-to-one association relationship between the AI ​​model and the AI ​​function, at least one third information sent by the first device is received.

15. The method according to claim 10, characterized in that The determining the model-related information of the first device based on the indication of the first device includes: Receive at least one fifth information sent by the first device; the fifth information indicates the AI ​​model supported by the first device, and the fifth information also includes at least one sixth information, wherein the sixth information is used to indicate: the AI ​​function associated with the AI ​​model indicated by the fifth information.

16. The method according to claim 10, characterized in that The determining the model-related information of the first device based on the indication of the first device includes: receiving at least one seventh information sent by the first device, where the seventh information indicates an AI function supported by the first device; Sending identification information to the first device, where the identification information includes: an identification assigned by the second device to at least one AI function supported by the first device; Receive at least one eighth information sent by the first device, wherein the eighth information indicates an AI model supported by the first device, and the eighth information also includes at least one identification information, wherein the at least one identification information is: an identification corresponding to at least one AI function associated with the AI ​​model indicated by the eighth information.

17. The method according to any one of claims 10 to 16, characterized in that: The model-related information also includes: an application scenario of at least one AI model supported by the first device.

18. The method according to any one of claims 10 to 16, characterized in that: The first device is a device on which an AI model is deployed or stored, and the second device is a device that is to manage the AI ​​model in the first device.

19. A communication device, characterized in that: include: A transceiver module, configured to indicate model-related information of the first device to a second device; The model-related information includes at least one of the following: at least one AI model supported by the first device; an AI function respectively associated with at least one AI model supported by the first device; at least one AI function supported by the first device; An AI model associated with at least one AI function supported by the first device.

20. A communication device, characterized in that: include: A processing module, configured to determine model-related information of the first device based on an indication of the first device; The model-related information includes at least one of the following: at least one AI model supported by the first device; an AI function respectively associated with at least one AI model supported by the first device; at least one AI function supported by the first device; An AI model associated with at least one AI function supported by the first device.

21. A communication device, characterized in that: The device comprises a processor and a memory, wherein a computer program is stored in the memory, and the processor executes the computer program stored in the memory so that the device performs the method according to any one of claims 1 to 9 and claims 10 to 18.

22. A communication device, characterized in that: include: processor and interface circuitry, wherein The interface circuit is used to obtain code instructions and transmit them to the processor; The processor is configured to execute the code instructions to perform the method according to any one of claims 1 to 9 and claims 10 to 18.

23. A computer-readable storage medium storing instructions, which, when executed, enable the method according to any one of claims 1 to 9 and claims 10 to 18 to be implemented.

Images