Information interaction method and related device

Abstract

The present disclosure provides an information interaction method and related equipment, and relates to the technical field of communication. The information interaction method provided by the present disclosure comprises that a terminal receives first information sent by a network device, and the first information is used to determine at least one of the following: a function and / or a model, a state of the function and / or the model. The terminal receives the first information sent by the network device, thereby obtaining specific parameters and data used for model training on the network side, ensuring that the parameters and data used by the terminal are consistent with those used when the network side is trained, and improving network performance.

Description

Technical Field

[0001] This disclosure relates to the field of communication technology, and in particular to an information interaction method, apparatus, electronic device, computer-readable storage medium, and computer program product. Background Technology

[0002] In the field of communication technology, AI / machine learning models for terminal applications are typically trained on the network side. However, the terminal is unaware of the specific parameters and data used during network-side training. Therefore, when applying these models on the terminal side, it cannot be guaranteed that the parameters and data used are consistent with those used during network-side training. This inconsistency may lead to mismatches between terminal application functions or models, thereby affecting network performance and causing performance degradation.

[0003] It should be noted that the information disclosed in the background section above is only used to enhance the understanding of the background of this disclosure, and therefore may include information that does not constitute prior art known to those skilled in the art. Summary of the Invention

[0004] This disclosure provides an information interaction method and related equipment, which at least to some extent overcomes the problem of network performance degradation caused by the mismatch between the artificial intelligence model / machine learning model of the terminal application.

[0005] Other features and advantages of this disclosure will become apparent from the following detailed description, or may be learned in part from practice of this disclosure.

[0006] According to one aspect of this disclosure, an information interaction method is provided, applied to a terminal, comprising: receiving first information sent by a network device, the first information being used to determine at least one of the following: a function and / or a model, and a state of the function and / or the model.

[0007] According to another aspect of this disclosure, an information interaction method is also provided, applied to a network device, the method comprising: sending first information to a terminal for determining at least one of the following: a function and / or a model, and a state of the function and / or the model.

[0008] According to another aspect of this disclosure, an information interaction method is also provided, applied to a terminal, the method comprising: sending fifteenth information to a network device, the fifteenth information being used to determine at least one of the following: function and / or model, and state of function and / or model.

[0009] According to another aspect of this disclosure, an information interaction method is also provided, applied to a network device, the method comprising: receiving fifteenth information sent by a terminal, the fifteenth information being used to determine at least one of the following: a function and / or a model, and a state of the function and / or the model.

[0010] According to another aspect of this disclosure, an information interaction device is also provided, applied to a terminal, comprising: a first receiving module, configured to receive first information sent by a network device, the first information being used to determine at least one of the following: function and / or model, and the state of function and / or model.

[0011] According to another aspect of this disclosure, an information interaction device is also provided, applied to a network device, comprising: a first sending module, configured to send first information to a terminal, the first information being configured to determine at least one of the following: a function and / or a model, and a state of the function and / or the model.

[0012] According to another aspect of this disclosure, an information interaction device is also provided, applied to a terminal, comprising: a second sending module for sending fifteenth information to a network device, the fifteenth information being used to determine at least one of the following: function and / or model, and the state of function and / or model.

[0013] According to another aspect of this disclosure, an information interaction device is also provided, applied to a network device, comprising: a second receiving module for receiving fifteenth information sent by a terminal, the fifteenth information being used to determine at least one of the following: function and / or model, and the state of function and / or model.

[0014] According to another aspect of this disclosure, an electronic device is also provided, comprising: a processor; and a memory for storing executable instructions of the processor; wherein the processor is configured to perform the information interaction method described in any of the preceding claims by executing the executable instructions.

[0015] According to another aspect of this disclosure, a computer-readable storage medium is also provided, on which a computer program is stored, which, when executed by a processor, implements the information interaction method described in any of the preceding claims.

[0016] According to another aspect of this disclosure, a computer program product is also provided, comprising: a computer program or instructions that, when executed by a processor, implement the information interaction method of any one of the above.

[0017] The information interaction method provided in the embodiments of this disclosure involves a terminal receiving first information sent by a network device. This first information is used to determine at least one of the following: a function and / or a model, and the state of the function and / or the model. By receiving the first information sent by the network device, the terminal obtains specific parameters and data used by the network side for model training, ensuring that the parameters and data used by the terminal are consistent with those used by the network side during training, thereby improving network performance.

[0018] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure. Attached Figure Description

[0019] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure. It is obvious that the drawings described below are merely some embodiments of this disclosure, and those skilled in the art can obtain other drawings based on these drawings without any inventive effort.

[0020] Figure 1 This diagram illustrates an information interaction system structure according to an embodiment of the present disclosure;

[0021] Figure 2 This diagram illustrates a flowchart of an information interaction method according to an embodiment of the present disclosure.

[0022] Figure 3 This diagram illustrates a flowchart of an information interaction method according to another embodiment of the present disclosure;

[0023] Figure 4 This diagram illustrates a flowchart of an information interaction method in yet another embodiment of the present disclosure.

[0024] Figure 5 This diagram illustrates a flowchart of an information interaction method in yet another embodiment of the present disclosure;

[0025] Figure 6 This diagram illustrates a flowchart of an information interaction method in yet another embodiment of the present disclosure;

[0026] Figure 7 This diagram illustrates a flowchart of an information interaction method in yet another embodiment of the present disclosure;

[0027] Figure 8 This diagram illustrates a signaling diagram of an information interaction method according to an embodiment of the present disclosure;

[0028] Figure 9 A signaling diagram of an information interaction method according to another embodiment of this disclosure is shown;

[0029] Figure 10 This diagram illustrates an information interaction device according to an embodiment of the present disclosure;

[0030] Figure 11 A schematic diagram of an information interaction device is shown in another embodiment of this disclosure;

[0031] Figure 12 This diagram illustrates an information interaction device in yet another embodiment of the present disclosure.

[0032] Figure 13 This diagram illustrates an information interaction device in yet another embodiment of the present disclosure;

[0033] Figure 14 A structural block diagram of an electronic device according to an embodiment of the present disclosure is shown. Detailed Implementation

[0034] Exemplary embodiments will now be described more fully with reference to the accompanying drawings. However, these exemplary embodiments can be implemented in many forms and should not be construed as limited to the examples set forth herein; rather, they are provided so that this disclosure will be more comprehensive and complete, and will fully convey the concept of the exemplary embodiments to those skilled in the art. The described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.

[0035] Furthermore, the accompanying drawings are merely illustrative of this disclosure and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and therefore repeated descriptions of them will be omitted. Some block diagrams shown in the drawings are functional entities and do not necessarily correspond to physically or logically independent entities. These functional entities may be implemented in software, in one or more hardware modules or integrated circuits, or in different network and / or processor devices and / or microcontroller devices.

[0036] To facilitate understanding, before introducing the embodiments of this disclosure, the following explanations are provided for several terms involved in the embodiments of this disclosure:

[0037] Artificial intelligence (AI) is a technology that simulates human intelligence processes, including abilities such as learning, reasoning, problem-solving, perception, and language understanding. In the field of communications, AI is mainly applied to data analysis, network optimization, and resource allocation to improve system efficiency and performance.

[0038] Machine learning (ML) is a subfield of artificial intelligence that uses algorithms and statistical models to enable computer systems to learn and optimize from empirical data without explicit programming. It is widely used in data analysis, pattern recognition, and automated control. In communication networks, ML can be used for intelligent scheduling, fault detection, and traffic prediction.

[0039] The OSI model (Open Systems Interconnection Model) is a standard network protocol model used to understand and describe communication processes in computer networks.

[0040] Layer 1 (L1) is the physical layer in the OSI model, responsible for transmitting raw bit streams (such as electrical or optical signals) through the communication medium. It defines the physical interfaces between hardware devices, signal encoding, modulation methods, etc., and is the foundation of network communication.

[0041] Channel State Information (CSI) is a parameter used in a network to describe the quality and characteristics of communication links. Through CSI, the network can understand the channel's frequency response, delay, noise, and other characteristics, thereby enabling signal scheduling, interference management, and other optimization strategies.

[0042] Life Cycle Management (LCM) is the management activity carried out throughout the entire life cycle of a product or service, including the stages of design, development, production, deployment, operation, and decommissioning.

[0043] The network side (NW-side) refers to the infrastructure, equipment, servers, and other components of a communication network. In a communication system, the network side is responsible for managing and coordinating all communication operations within the network, such as the management and control of devices like base stations, routers, and switches.

[0044] The UE-side (User Equipment-side) is the terminal device, such as a mobile phone or laptop, which interacts with the communication network.

[0045] RS (Reference Signal) is a known signal used for signal measurement and synchronization in a communication system.

[0046] RSRP (Reference Signal Receive Power) refers to the power value of the reference signal received by the terminal device.

[0047] like Figure 1 As shown, the system architecture includes terminal 101, network 102, and network device 103.

[0048] Network 102 is a medium used to provide a communication link between terminal 101 and network device 103, and can be a wired network or a wireless network.

[0049] Optionally, the aforementioned wireless or wired networks use standard communication technologies and / or protocols. The network is typically the Internet, but can also be any network, including but not limited to Local Area Networks (LANs), Metropolitan Area Networks (MANs), Wide Area Networks (WANs), mobile, wired or wireless networks, private networks, or any combination of virtual private networks. In some embodiments, technologies and / or formats including Hyper Text Markup Language (HTML), Extensible Markup Language (XML), etc., are used to represent data exchanged over the network. Furthermore, conventional encryption technologies such as Secure Socket Layer (SSL), Transport Layer Security (TLS), Virtual Private Networks (VPNs), and Internet Protocol Security (IPSec) can be used to encrypt all or some links. In other embodiments, custom and / or dedicated data communication technologies can be used to replace or supplement the aforementioned data communication technologies.

[0050] Optionally, the terminal in this embodiment may also be referred to as UE (User Equipment). In specific implementation, the terminal may be a mobile phone, tablet computer, laptop computer, personal digital assistant (PDA), mobile internet device (MID), wearable device, or vehicle-mounted device, etc. It should be noted that the specific type of terminal device is not limited in the embodiments of the present invention.

[0051] Network equipment, also known as network-side equipment, can be a base station, relay, or access point. A base station can be a 5G or later version base station (e.g., 5G NR NB), or a base station in other communication systems (e.g., eNB base station). It should be noted that the specific type of network equipment is not limited in this disclosure.

[0052] For example, the terminal receives first information sent by the network device, the first information being used to determine at least one of the following: a function and / or model, and the state of the function and / or model. For example, the first information includes at least one of a first identifier, a second identifier, a third identifier, and a fourth identifier; the first identifier includes an identifier for an artificial intelligence function and / or a machine learning function; the second identifier includes an identifier for an artificial intelligence model and / or a machine learning model; the third identifier includes an identifier related to network-side configuration; and the fourth identifier includes a dataset identifier.

[0053] Those skilled in the art will know that Figure 1 The number of terminals, networks, and network devices shown is merely illustrative; any number of terminals, networks, and network devices can be included as needed. This disclosure does not limit the number of such devices.

[0054] This disclosure provides an information exchange method applicable to mobile communications. For example, this disclosure can be applied to beam management, spectrum sharing, network slicing, user positioning, and network optimization. The embodiments of this disclosure are not limited in this regard. The following description uses a beam management scenario as an example, assuming the network device is a base station and the terminal is a user equipment.

[0055] Beam management involves selecting, maintaining, and optimizing directional beams between base stations and user equipment (UEs) to ensure reliable and high-quality communication. Its ultimate goal is to establish and maintain suitable beam pairs. For example, this involves selecting a suitable transmit beam on the base station side and a suitable receive beam on the UE side. Once the initial beams are established, the suitability of the beam selection on both the base station and UE sides needs to be periodically reassessed to ensure consistently high reliability and quality communication.

[0056] For downlink transmitter beam adjustment, the user equipment (UE) assesses the current beam quality by measuring the reference signal and reports the measurement results to the base station. The base station then uses this data to determine whether the current transmit beam needs adjustment. For downlink receiver beam adjustment, the UE adjusts its receive beam based on the measurement results.

[0057] However, current beam management remains quite complex. The increase in the number of beams and users has significantly increased the overhead of beam measurement and reporting. Furthermore, there is a certain delay in beam quality reporting and indication, and beam failure detection and recovery require optimization. For these challenging beam management problems that are difficult to model, leveraging artificial intelligence technologies can be considered to improve performance.

[0058] AI-based beam management is one application of artificial intelligence and / or machine learning in wireless air interfaces, primarily encompassing two application scenarios: spatial beam prediction and temporal beam prediction. In the spatial beam prediction scheme, the AI / ML model uses the measured beam quality of SetB (reference beam set) as input to predict the Top-1 / N beams and their quality measurements (e.g., L1-RSRP) in Set A (target beam set). In the temporal beam prediction scheme, the AI / ML model uses historical measurements of the beam quality of SetB as input to predict the Top-1 / N beams and their quality measurements (e.g., L1-RSRP) in Set A at future times. It's important to note that Top-1 / N refers to selecting the optimal beam or the top N beams from multiple beams. In AI / ML beam prediction, the system predicts the best beam in Set A based on the current beam set (e.g., Set B).

[0059] By using AI-based spatial and temporal beam prediction, measurement delay can be significantly reduced, signaling overhead can be lowered, and the performance of MIMO (Multiple Input Multiple Output) systems can be improved.

[0060] The inventors discovered that in current network architectures, when AI / ML functions and / or models are trained on the network side and applied on the terminal side, the terminal cannot know the training parameters and data used by the network-side model. Therefore, when applied on the terminal side, it may not be possible to ensure that the model parameters and data used by the application are consistent with those on the network side, thus affecting the model's performance and accuracy.

[0061] Furthermore, the management of AI / ML functions and / or models mainly includes the selection, activation / deactivation, switching, and rollback of functions or models, which are typically controlled by the network side. However, the network side is unaware of which AI / ML functions and / or models the terminal supports, nor can it determine which functions or models are suitable for the terminal, thus hindering effective control over how the terminal performs model management. Simultaneously, the performance of AI / ML functions and / or models is often closely related to terminal-side conditions (such as scenario, configuration, and mobility), while the base station cannot directly know the specific conditions of the terminal and cannot accurately determine whether the terminal meets the application requirements of the model, leading to difficulties in AI / ML function / model management.

[0062] Therefore, further research and discussion are needed on whether terminals should send auxiliary information about their status to the network to help the network better manage the use and adaptation of AI / ML functions and / or models. This information includes, but is not limited to, the terminal's operating conditions, supported models, and usage scenarios.

[0063] Under the above system architecture, this disclosure provides an information exchange method that can be executed by any electronic device with computing capabilities.

[0064] In some embodiments, the information interaction method provided in this disclosure can be executed by a terminal in the above-described system architecture; in other embodiments, the information interaction method provided in this disclosure can be executed by a network device in the above-described system architecture; in still other embodiments, the information interaction method provided in this disclosure can be implemented by the terminal and the network device in the above-described system architecture through interaction.

[0065] Figure 2 A flowchart of an information exchange method according to an embodiment of this disclosure is shown, such as Figure 2 As shown, applied to a terminal, the information interaction method provided in this embodiment includes the following S202.

[0066] S202, receiving first information sent by a network device, the first information being used to determine at least one of the following: function and / or model, and the state of function and / or model.

[0067] In this embodiment of the disclosure, the first information is used to indicate information related to the network device. For example, the first information may be network-side auxiliary information / network-side conditions. Exemplarily, the content of the network-side auxiliary information / network-side conditions may include information such as network conditions, available bandwidth, network topology, and how to transmit this information to the terminal side for terminal use. As another example, the first information includes at least one of a first identifier, a second identifier, a third identifier, and a fourth identifier; the first identifier includes an identifier for artificial intelligence functions and / or machine learning functions; the second identifier includes an identifier for an artificial intelligence model and / or a machine learning model; the third identifier includes an identifier related to network-side configuration; and the fourth identifier includes a dataset identifier.

[0068] For example, the features and / or models may include identifiers of the features and / or models.

[0069] For example, the state of a function includes an applicable state and / or an active state; the state of a model includes an applicable state and / or an active state, where the applicable state includes: applicable or inapplicable, and the active state includes active or inactive.

[0070] In this embodiment of the disclosure, the artificial intelligence function may include at least one artificial intelligence model, and similarly, the machine learning function may include at least one machine learning model.

[0071] A machine learning model identifier refers to a label or code used to uniquely identify and distinguish different machine learning models. It can be a unique name, version number, ID (unique identifier), feature descriptor, or other information used to identify a specific machine learning model and its associated features, configuration, or training parameters.

[0072] An AI model identifier refers to a label or code used to uniquely identify and distinguish different AI models. It can be a unique name, version number, ID, feature descriptor, or other information used to identify a specific AI model and its related features, configuration, or training parameters.

[0073] The labeling of machine learning functions refers to the marking of different functions, features, or variables in a machine learning model.

[0074] The identification of artificial intelligence functions refers to the clear marking of different functions or features in an AI system.

[0075] The network-side configuration-related identifier (Associated ID) represents a set of configuration information. That is, each function / model may use different configurations for training and inference, distinguished by the network-side configuration-related identifier. For example, the network-side configuration-related identifier can be the association ID between an AI / ML function / model and a scenario / configuration. The scenario / configuration can include: deployment scenario (e.g., Uma (urban macro base station scenario), Umi (urban micro base station scenario)), distribution of indoor / outdoor user equipment, carrier frequency (e.g., 2GHz), antenna array dimensions and number of ports, user equipment hardware capabilities (e.g., battery), user equipment speed and rotation, user equipment performance requirements for the model, and user equipment speed.

[0076] Dataset identifiers refer to the labels or codes on network devices that relate to artificial intelligence models and / or machine learning models, as well as artificial intelligence functions and / or machine learning functions, such as the ID of a model training dataset.

[0077] In this embodiment of the disclosure, the terminal receives first information sent by the network device. The first information includes at least one of a first identifier, a second identifier, a third identifier, and a fourth identifier. For example, the first information includes a first identifier, a second identifier, a third identifier, and a fourth identifier. For example, the first information includes a first identifier, a second identifier, and a third identifier.

[0078] In this embodiment of the present disclosure, the terminal receives first information sent by the network device. Based on the first information, it can obtain information from the network side about the specific parameters and data used for model training, thereby determining the artificial intelligence functions and / or machine learning functions, artificial intelligence models and / or machine learning models that can be applied on the terminal. This ensures that the parameters and data used by the terminal are consistent with those used by the network side during training, improves the performance and accuracy of the model and / or functions, and thus enhances network performance.

[0079] The present disclosure will be further illustrated below by means of several exemplary embodiments.

[0080] In one exemplary embodiment, an information interaction method provided in this disclosure may further include: reporting second information to a network device, the second information including capabilities related to artificial intelligence and / or machine learning supported by the terminal.

[0081] In this embodiment of the disclosure, the network device learns about the artificial intelligence and / or machine learning capabilities supported by the terminal through second information. The second information includes the artificial intelligence and / or machine learning capabilities supported by the terminal. For example, the artificial intelligence and / or machine learning capabilities include at least one of supported artificial intelligence functions and supported machine learning functions; and / or, the artificial intelligence and / or machine learning capabilities include at least one of supported artificial intelligence models and supported machine learning models.

[0082] It should be noted that the second piece of information can be a User Equipment Capability (UE) report. Taking the base station as an example, the terminal receives a UE capability query request from the base station; it then sends a UE capability report to the base station. The UE capability report carries a list of AI / ML functions and / or models supported by the terminal. This list may include identifiers of the AI / ML functions and / or machine learning functions, identifiers of the AI / ML models and / or machine learning models, the association ID between the function / model and the scenario / configuration (e.g., an identifier related to network-side configuration), and dataset identifiers.

[0083] It should be noted that when a periodic CSI configuration consistent with the UE's reporting capabilities is provided, the UE will automatically activate the applicable AI / ML functions after reporting the applicable functions. When a semi-persistent CSI and / or non-periodic CSI configuration is provided, the activation of the applicable AI / ML functions follows the traditional CSI framework after reporting the applicable AI / ML functions. That is, semi-persistent reporting can be activated through MAC (Medium Access Control), CE (Control Element), and DCI (Downlink Control Information), while non-periodic CSI reporting can be activated through DCI.

[0084] When an activated AI / ML function becomes unusable, the UE will not automatically deactivate it. Upon receiving an indication from the UE that the function has become unusable, the network should deactivate or release the activated function.

[0085] This embodiment of the disclosure reports the second information to the network device, which facilitates the network device to obtain the capabilities related to artificial intelligence and / or machine learning supported by the terminal. This can further ensure that the parameters and data used by the terminal are consistent with those used during network training, thereby improving network performance.

[0086] In another exemplary embodiment, the information interaction method provided in this disclosure may further include: reporting fourth information to a network device; the fourth information includes at least one of the following: an identifier of an applicable artificial intelligence function and / or machine learning function; an identifier of an applicable artificial intelligence model and / or machine learning model.

[0087] The identifiers for applicable AI and / or machine learning capabilities are used to identify applicable AI and / or machine learning capabilities. The identifiers for applicable AI and / or machine learning models are used to identify applicable AI and / or machine learning models.

[0088] For example, the fourth information includes the identifiers of the applicable artificial intelligence functions and machine learning functions. The fourth information is 0001, 0002, which indicates that the first artificial intelligence function can be applied on the terminal and the second machine learning function can be applied.

[0089] In this embodiment of the disclosure, by sending the fourth information to the network device, the network device can obtain the artificial intelligence functions and / or machine learning functions that the terminal can apply, and / or the applicable artificial intelligence models and / or machine learning models. This facilitates the network device in determining the applicable artificial intelligence functions and / or machine learning functions, and / or the applicable artificial intelligence models and / or machine learning models, thereby better configuring the terminal's models and / or functions, ensuring that the model parameters and data used by the terminal application are consistent with those on the network side, and improving network performance.

[0090] In addition to reporting information about the applicable models or functions of the terminal to the network device in the form of fourth information, it can also be reported to the network device in the form of fifth information. An information interaction method provided in this disclosure embodiment may further include: reporting fifth information to the network device, the fifth information indicating whether artificial intelligence and / or machine learning functions are applicable, and the fifth information including at least one of the following: applicability indication information of artificial intelligence functions and / or machine learning functions; applicability indication information of artificial intelligence models and / or machine learning models.

[0091] The specific form of the fifth information is not limited in this embodiment. For example, the fifth information can be represented in tabular form as applicable information. For instance, the fifth information includes the identifier of an applicable machine learning model, as shown in Table 1 below.

[0092] Table 1. Identification of Applicable Machine Learning Models

[0093] Model type logo Supervised learning 0 Recurrent Neural Networks 1 … … Transfer learning 1 semi-supervised learning 1

[0094] In Table 1 above, "0" represents that it cannot be applied, and "1" represents that it can be applied.

[0095] Both the fourth and fifth pieces of information can be determined through the following two examples.

[0096] In one embodiment, the terminal determines at least one of the following based on first information and terminal-related capabilities (such as terminal-side auxiliary information / terminal-side conditions, the fifteenth information below): an identifier of an applicable artificial intelligence function and / or machine learning function, an identifier of an applicable artificial intelligence model and / or machine learning model, an applicability indication information of the artificial intelligence function and / or machine learning function, and an identifier of an applicable artificial intelligence model and / or machine learning model.

[0097] In another embodiment, the information interaction method provided in this disclosure may further include: receiving third information sent by a network device, wherein the third information is information for measuring communication quality.

[0098] The terminal determines, based on first information, terminal-related capabilities, and third information, at least one of the following: an identifier of an applicable artificial intelligence function and / or machine learning function, an identifier of an applicable artificial intelligence model and / or machine learning model, applicability indication information of the artificial intelligence function and / or machine learning function, and an identifier of an applicable artificial intelligence model and / or machine learning model.

[0099] In this embodiment of the disclosure, the specific type of information used to measure communication quality is not limited. For example, the third information may include one or more of the following: a speed threshold, a reference signal received power threshold, and a signal-to-interference-plus-noise ratio threshold.

[0100] It should be noted that third-party information is crucial for the terminal to determine the applicable artificial intelligence functions and / or machine learning functions, as well as the applicable artificial intelligence models and / or machine learning models. Functions and / or models determined based on third-party information have higher performance and accuracy.

[0101] In this embodiment of the present disclosure, the terminal can determine the fourth information and / or the fifth information based on the first information and the fifteenth information. The terminal can also determine the fourth information and / or the fifth information based on the first information, the third information, and the fifteenth information, and send the fourth information and / or the fifth information to the network device. This facilitates the network device to obtain the artificial intelligence functions and / or machine learning functions that the terminal can apply, and / or the applicable artificial intelligence models and / or machine learning models. This makes it easier for the network device to select applicable artificial intelligence functions and / or machine learning functions, and / or the applicable artificial intelligence models and / or machine learning models, thereby better configuring the terminal's models and / or functions, ensuring that the model parameters and data used by the terminal application are consistent with those on the network side, and improving network performance.

[0102] As the terminal system is updated and the model / function changes, it is necessary to dynamically adjust the model / function. The following are several exemplary embodiments illustrating how to handle this situation.

[0103] In one exemplary embodiment, the information interaction method provided in this disclosure may further include: reporting sixth information to a network device, the sixth information indicating whether an artificial intelligence function and / or machine learning function has been updated; the sixth information including an identifier of the updated artificial intelligence function and / or machine learning function; or / and reporting seventh information to the network device, the seventh information indicating whether an artificial intelligence model and / or machine learning model has been updated; the seventh information including an identifier of the updated artificial intelligence model and / or machine learning model.

[0104] The terminal in this embodiment can report the sixth and / or seventh information in a timely manner, thereby enabling the network device to dynamically adjust based on the information reported by the terminal, select applicable models and / or functions, and thus better configure the terminal's models and / or functions, ensuring that the model parameters and data used by the terminal application are consistent with those on the network side, thereby improving network performance.

[0105] In another exemplary embodiment, the information interaction method provided in this disclosure may further include: reporting eighth information to a network device, the eighth information indicating whether the applicability of artificial intelligence functions and / or machine learning functions has been updated; the eighth information includes an identifier of the updated applicable artificial intelligence functions and / or machine learning functions; or / and reporting ninth information to the network device, the ninth information indicating whether the applicability of artificial intelligence models and / or machine learning models has been updated; the ninth information includes an identifier of the updated applicable artificial intelligence models and / or machine learning models.

[0106] In this embodiment of the disclosure, when the applicability of the artificial intelligence function and / or machine learning function, or / and the artificial intelligence model and / or machine learning model is updated, its corresponding identifier is also updated.

[0107] The terminal in this embodiment can promptly report the eighth and / or ninth information, thereby enabling the network device to dynamically adjust based on the information reported by the terminal, select applicable models and / or functions, and thus better configure the terminal's models and / or functions, ensuring that the model parameters and data used by the terminal application are consistent with those on the network side, thereby improving network performance.

[0108] In yet another exemplary embodiment, the information interaction method provided in this disclosure may further include: reporting tenth information to a network device, the tenth information indicating whether the applicability indication information of the artificial intelligence function and / or machine learning function has been updated; the tenth information including updated applicability indication information of the artificial intelligence function and / or machine learning function; or / and reporting eleventh information to the network device, the eleventh information indicating whether the applicability indication information of the artificial intelligence model and / or machine learning model has been updated; the eleventh information including updated applicability indication information of the artificial intelligence model and / or machine learning model.

[0109] It should be noted that the applicability indication information in the embodiments of this disclosure changes according to changes in the applicability of the function and / or model.

[0110] The terminal in this embodiment can promptly report the tenth and / or eleventh information, thereby enabling the network device to dynamically adjust based on the information reported by the terminal, select applicable models and / or functions, and thus better configure the terminal's models and / or functions, ensuring that the model parameters and data used by the terminal application are consistent with those on the network side, thereby improving network performance.

[0111] It should be noted that when selecting applicable models and / or functions for network devices, the internal state of the terminal devices also needs to be considered in order to further improve network performance, as illustrated in the following examples.

[0112] In one embodiment, the information interaction method provided in this disclosure may further include: reporting a twelfth piece of information to a network device, wherein the twelfth piece of information is information related to the terminal.

[0113] Regarding the specific type of terminal-related information in the twelfth piece of information, this disclosure does not provide specific limitations. For example, the twelfth piece of information may include, but is not limited to, battery status, cache status, and storage status. As another example, the twelfth piece of information may include the terminal's hardware conditions, which may include, but are not limited to, CPU (Central Processing Unit) usage, GPU (Graphics Processing Unit) usage, sensor status, peripheral connection status, and hardware malfunctions.

[0114] For example, when the terminal device's battery level is less than 20%, selecting a low-power model for configuration or not configuring a model can improve the terminal's battery life, stability, and user experience, prevent rapid battery depletion, and ensure that the terminal can continue to work normally with limited power.

[0115] When selecting models and / or functions, the network device in this embodiment considers the internal state of the terminal, which can accurately determine whether the terminal meets the application requirements of the model and / or function, thus facilitating the network device's management of the model and / or function on the terminal.

[0116] In yet another exemplary embodiment, the information interaction method provided in this disclosure may further include: reporting thirteenth information to a network device, wherein the thirteenth information is updated information related to the terminal.

[0117] The terminal in this embodiment can report the thirteenth information in a timely manner, so that the network device can dynamically adjust according to the information reported by the terminal, select the applicable model and / or function, and thus better configure the terminal's model and / or function, ensuring that the model parameters and data used by the terminal application are consistent with those on the network side, thereby improving network performance.

[0118] After the network device completes the selection of the model and / or function, it sends the fourteenth message to the terminal. Exemplarily, an information interaction method provided in this disclosure embodiment may further include: receiving the fourteenth message sent by the network device, the fourteenth message being used to instruct the terminal to perform at least one of selection, activation, deactivation, switching, and rollback.

[0119] In this embodiment of the disclosure, activation refers to enabling AI / ML functions / models; deactivation refers to disabling AI / ML functions / models; switching refers to deactivating old AI / ML functions / models and activating new AI / ML functions / models; if no applicable model is available, then an AI / ML function / model rollback is performed (i.e., rollback to a non-AI method); selection refers to selecting AI / ML functions / models.

[0120] This disclosure provides a network-side and terminal-side information interaction method for terminal-side model management in beam management scenarios. Through the interaction of network-side and terminal-side information, the base station or terminal can determine whether AI / ML functions / models are available. The base station can control the management of AI / ML functions / models, including the selection, activation, deactivation, switching, and rollback of AI / ML functions. That is, it selects and applies appropriate AI / ML functions / models from the available AI / ML functions / models to ensure that AI / ML functions / models can run efficiently and stably on the terminal side, thereby avoiding poor network performance caused by the terminal applying mismatched functions / models.

[0121] This disclosure enables more precise management of AI / ML functions / models through effective information interaction between the terminal and network sides, improving the collaborative efficiency of the terminal and network, and thus enhancing the performance and user experience of AI / ML functions.

[0122] Based on the same inventive concept, this disclosure also provides an information interaction method, as described in the following embodiments. Since the principle by which this method solves the problem is similar to that of the above-described method embodiments, the implementation of this method embodiment can refer to the implementation of the above-described method embodiments, and repeated details will not be elaborated further.

[0123] Figure 3 A flowchart of an information interaction method according to another embodiment of this disclosure is shown, such as Figure 3 As shown, when applied to network devices, an information exchange method may include S302.

[0124] S302, send first information to the terminal, the first information being used to determine at least one of the following: function and / or model, and the status of function and / or model.

[0125] For example, the features and / or models may include identifiers of the features and / or models.

[0126] For example, the state of a function includes an applicable state and / or an active state; the state of a model includes an applicable state and / or an active state, where the applicable state includes: applicable or inapplicable, and the active state includes active or inactive.

[0127] For example, the first information includes at least one of a first identifier, a second identifier, a third identifier, and a fourth identifier; the first identifier includes an identifier for artificial intelligence functions and / or machine learning functions; the second identifier includes an identifier for artificial intelligence models and / or machine learning models; the third identifier includes an identifier related to network-side configuration; and the fourth identifier includes a dataset identifier.

[0128] In this embodiment of the network device, the first information sent to the terminal enables the terminal to obtain information from the network side regarding the specific parameters and data used for model training. This information allows the terminal to determine the artificial intelligence and / or machine learning functions, artificial intelligence models, and / or machine learning models that can be applied on the terminal. This ensures that the parameters and data used by the terminal are consistent with those used during network training, thereby improving the performance and accuracy of the model and / or functions, and ultimately enhancing network performance.

[0129] The present disclosure will be further illustrated below by means of several exemplary embodiments.

[0130] In one exemplary embodiment, such as Figure 4 As shown, the information exchange method provided in this disclosure may further include S402 to S406.

[0131] S402, Receive information reported by the terminal, the information reported by the terminal includes one or more of the following: fourth information, fifth information, sixth information, seventh information, eighth information, ninth information, tenth information, eleventh information, twelfth information and thirteenth information.

[0132] The fourth piece of information includes at least one of the following: an identifier of the applicable artificial intelligence and / or machine learning functions; an identifier of the applicable artificial intelligence and / or machine learning models.

[0133] The fifth piece of information is used to indicate whether artificial intelligence and / or machine learning functions are applicable, and the fifth piece of information includes at least one of the following: information indicating the applicability of artificial intelligence functions and / or machine learning functions; information indicating the applicability of artificial intelligence models and / or machine learning models.

[0134] The sixth piece of information includes the identifiers of updated artificial intelligence and / or machine learning functions; the seventh piece of information includes the identifiers of updated artificial intelligence and / or machine learning models; the eighth piece of information includes the identifiers of updated applicable artificial intelligence and / or machine learning functions; the ninth piece of information includes the identifiers of updated applicable artificial intelligence and / or machine learning models; the tenth piece of information includes updated indications of the applicability of artificial intelligence and / or machine learning functions; the eleventh piece of information includes updated indications of the applicability of artificial intelligence and / or machine learning models; the twelfth piece of information is terminal-related information; and the thirteenth piece of information is updated terminal-related information.

[0135] In one embodiment, the fourth, fifth, sixth, seventh, eighth, ninth, tenth, eleventh, twelfth, and thirteenth pieces of information all carry timestamps. The network device selects the most recent information based on the timestamp to determine the fourteenth information. It should be noted that this disclosure can also delete information with a longer storage time based on the timestamp to save memory.

[0136] S404, determine the fourteenth information based on the information reported by the terminal and the first information, the fourteenth information is used to instruct the terminal to perform at least one of selection, activation, deactivation, switching and rollback.

[0137] In one embodiment, the network device determines the fourteenth information based on the first information and the fourth information. That is, it determines the model and / or function corresponding to the model and / or function that can be applied on the network side and the terminal side based on the first information and the fourth information, thereby controlling the management of the model and / or function on the terminal side, and sending the fourteenth information to the terminal for management.

[0138] In another embodiment, the network device determines the fourteenth information based on the first, fifth, and twelfth information. This embodiment of the present disclosure considers the internal state of the terminal when determining the fourteenth information, thereby accurately determining whether the terminal meets the application requirements of the model and / or function, facilitating the network device's management of the model and / or function on the terminal.

[0139] S406, send the fourteenth message to the terminal.

[0140] This embodiment of the disclosure determines the fourteenth information by receiving information reported by the terminal and the first information, ensuring that the parameters and data used by the terminal are consistent with those used during network training, thereby improving network performance.

[0141] In another exemplary embodiment, the information interaction method provided in this disclosure may further include: receiving second information reported by a terminal, the second information including capabilities related to artificial intelligence and / or machine learning supported by the terminal.

[0142] Capabilities related to artificial intelligence and / or machine learning include: at least one of supported artificial intelligence functions and supported machine learning functions; and / or, capabilities related to artificial intelligence and / or machine learning include: at least one of supported artificial intelligence models and supported machine learning models.

[0143] In yet another exemplary embodiment, the information interaction method provided in this disclosure may further include: sending third information to a terminal, wherein the third information is information for measuring communication quality. The third information includes one or more of a speed threshold, a reference signal received power threshold, and a signal-to-interference-plus-noise ratio threshold.

[0144] Based on the same inventive concept, this disclosure also provides an information interaction method, as described in the following embodiments. Since the principle by which this method solves the problem is similar to that of the above-described method embodiments, the implementation of this method embodiment can refer to the implementation of the above-described method embodiments, and repeated details will not be elaborated further.

[0145] Figure 5 A flowchart of an information exchange method according to another embodiment of this disclosure is shown, such as Figure 5 As shown, when applied to a terminal, the information interaction method provided in this embodiment may include the following S502.

[0146] S502, send the fifteenth information to the network device, the fifteenth information being used to determine at least one of the following: function and / or model, and the status of function and / or model.

[0147] The fifteenth piece of information is used to indicate terminal-related information. For example, the fifteenth piece of information can be terminal-side auxiliary information / terminal-side conditions. For instance, the content of the terminal-side auxiliary information / terminal-side conditions may include information such as the terminal's hardware resources, operating environment, supported AI / ML models, and how to transmit this information to the network side so that the network device can make corresponding decisions based on the specific situation of the terminal. As another example, the fifteenth piece of information includes at least one of the fifth, sixth, seventh, and eighth identifiers; the fifth identifier includes an identifier for artificial intelligence functions and / or machine learning functions; the sixth identifier includes an identifier for artificial intelligence models and / or machine learning models; the seventh identifier includes an identifier related to network-side configuration; and the eighth identifier includes a dataset identifier.

[0148] For example, the features and / or models may include identifiers of the features and / or models.

[0149] For example, the state of a function includes an applicable state and / or an active state; the state of a model includes an applicable state and / or an active state, where the applicable state includes: applicable or inapplicable, and the active state includes active or inactive.

[0150] In this embodiment of the present disclosure, the terminal sends a fifteenth piece of information to the network device, so that the network device can obtain information about the specific parameters and data used by the terminal for model training based on the fifteenth piece of information. This allows the network device to determine the artificial intelligence functions and / or machine learning functions, artificial intelligence models and / or machine learning models that can be applied on the network device, thereby ensuring that the parameters and data used by the terminal are consistent with those used by the network device during training, improving the performance and accuracy of the model and / or functions, and thus enhancing network performance.

[0151] In one embodiment, the information interaction method provided in this disclosure may further include: reporting second information to a network device, the second information including capabilities related to artificial intelligence and / or machine learning supported by the terminal.

[0152] In one embodiment, the capabilities related to artificial intelligence and / or machine learning include at least one of supported artificial intelligence functions and supported machine learning functions; and / or, the capabilities related to artificial intelligence and / or machine learning include at least one of supported artificial intelligence models and supported machine learning models.

[0153] In one embodiment, the information interaction method provided in this disclosure may further include: reporting sixth information to a network device, the sixth information indicating whether the artificial intelligence function and / or machine learning function has been updated; the sixth information including an identifier of the updated artificial intelligence function and / or machine learning function; or / and reporting seventh information to the network device, the seventh information indicating whether the artificial intelligence model and / or machine learning model has been updated; the seventh information including an identifier of the updated artificial intelligence model and / or machine learning model.

[0154] In one embodiment, the information interaction method provided in this disclosure may further include: reporting eighth information to a network device, the eighth information indicating whether the applicability of artificial intelligence functions and / or machine learning functions has been updated; the eighth information includes an identifier of the updated applicable artificial intelligence functions and / or machine learning functions; or / and reporting ninth information to the network device, the ninth information indicating whether the applicability of artificial intelligence models and / or machine learning models has been updated; the ninth information includes an identifier of the updated applicable artificial intelligence models and / or machine learning models.

[0155] In one embodiment, the information interaction method provided in this disclosure may further include: reporting tenth information to a network device, the tenth information indicating whether the applicability indication information of the artificial intelligence function and / or machine learning function has been updated; the tenth information includes updated applicability indication information of the artificial intelligence function and / or machine learning function; or / and reporting eleventh information to the network device, the eleventh information indicating whether the applicability indication information of the artificial intelligence model and / or machine learning model has been updated; the eleventh information includes updated applicability indication information of the artificial intelligence model and / or machine learning model.

[0156] In one embodiment, the information interaction method provided in this disclosure may further include: reporting a twelfth piece of information to a network device, wherein the twelfth piece of information is information related to the terminal.

[0157] In one embodiment, the information interaction method provided in this disclosure may further include: reporting thirteenth information to a network device, wherein the thirteenth information is updated information related to the terminal.

[0158] In one embodiment, the information interaction method provided in this disclosure may further include: receiving fourteenth information sent by a network device, the fourteenth information being used to instruct the terminal to perform at least one of selection, activation, deactivation, switching, and rollback.

[0159] Based on the same inventive concept, this disclosure also provides an information interaction method, as described in the following embodiments. Since the principle by which this method solves the problem is similar to that of the above-described method embodiments, the implementation of this method embodiment can refer to the implementation of the above-described method embodiments, and repeated details will not be elaborated further.

[0160] Figure 6 This diagram illustrates a flowchart of an information interaction method according to an embodiment of the present disclosure, such as... Figure 6 As shown, when applied to network devices, an information exchange method may include S602.

[0161] S602, receiving the fifteenth information sent by the terminal, the fifteenth information being used to determine at least one of the following: function and / or model, and the status of function and / or model.

[0162] For example, the fifteenth information includes at least one of the fifth identifier, the sixth identifier, the seventh identifier, and the eighth identifier; the fifth identifier includes an identifier for artificial intelligence functions and / or machine learning functions; the sixth identifier includes an identifier for artificial intelligence models and / or machine learning models; the seventh identifier includes an identifier related to network-side configuration; and the eighth identifier includes a dataset identifier.

[0163] For example, the features and / or models may include identifiers of the features and / or models.

[0164] For example, the state of a function includes an applicable state and / or an active state; the state of a model includes an applicable state and / or an active state, where the applicable state includes: applicable or inapplicable, and the active state includes active or inactive.

[0165] According to the embodiments of this disclosure, the network device receives the fifteenth information sent by the terminal. Based on the fifteenth information, the network device can obtain information about the specific parameters and data used by the terminal for model training, thereby determining the artificial intelligence functions and / or machine learning functions, artificial intelligence models and / or machine learning models that can be applied on the network device. This ensures that the parameters and data used by the terminal are consistent with those used during network training, improves the performance and accuracy of the model and / or functions, and thus enhances network performance.

[0166] In one embodiment, such as Figure 7 As shown, the information interaction method provided in this disclosure may further include the following steps S702 to S708.

[0167] S702, Obtain first information, the first information including at least one of a first identifier, a second identifier, a third identifier, and a fourth identifier.

[0168] The first identifier includes identifiers for artificial intelligence functions and / or machine learning functions; the second identifier includes identifiers for artificial intelligence models and / or machine learning models; the third identifier includes identifiers related to network-side configuration; and the fourth identifier includes dataset identifiers.

[0169] S704, based on the first information and the fifteenth information, determine the fourth information and / or the fifth information.

[0170] The fourth piece of information includes at least one of the following: an identifier of the applicable artificial intelligence and / or machine learning functions; an identifier of the applicable artificial intelligence and / or machine learning models.

[0171] The fifth piece of information is used to indicate whether artificial intelligence and / or machine learning functions are applicable, and the fifth piece of information includes at least one of the following: information indicating the applicability of artificial intelligence functions and / or machine learning functions; information indicating the applicability of artificial intelligence models and / or machine learning models.

[0172] S706, based on the fourth and / or fifth information, determine the fourteenth information, which is used to instruct the terminal to perform at least one of selection, activation, deactivation, switching, and rollback.

[0173] S708 sends the fourteenth message to the terminal.

[0174] This embodiment determines the fourteenth information by using the fifteenth information and the first information, ensuring that the parameters and data used by the terminal are consistent with those used during network training, thereby improving network performance.

[0175] In one embodiment, the information interaction method provided in this disclosure may further include: receiving information reported by a terminal, wherein the information reported by the terminal includes one or more of the sixth, seventh, eighth, ninth, tenth, eleventh, twelfth and thirteenth information; and determining the fourteenth information based on the information reported by the terminal and the first information.

[0176] The information includes: the sixth information includes the identifier of the updated artificial intelligence function and / or machine learning function; the seventh information includes the identifier of the updated artificial intelligence model and / or machine learning model; the eighth information includes the identifier of the updated applicable artificial intelligence function and / or machine learning function; the ninth information includes the identifier of the updated applicable artificial intelligence model and / or machine learning model; the tenth information includes the applicability indication information of the updated artificial intelligence function and / or machine learning function; the eleventh information includes the applicability indication information of the updated artificial intelligence model and / or machine learning model; the twelfth information is terminal-related information; and the thirteenth information is updated terminal-related information.

[0177] The following two specific examples illustrate how to effectively exchange auxiliary information between the network side and the terminal side to support the management of AI / ML functions / models.

[0178] In one embodiment, the network device is a base station, such as... Figure 8 As shown, the information interaction method provided in this disclosure includes the following steps S801 to S810.

[0179] S801, User Equipment Capability Query / Report. For example, in response to a user equipment capability query request sent by the base station, a user equipment capability report (e.g., second information) is sent to the base station.

[0180] S802, the base station sends first information to the terminal. The first information is used to determine at least one of the following: a function and / or model, and the state of the function and / or model. For example, the first information includes at least one of a first identifier, a second identifier, a third identifier, and a fourth identifier; the first identifier includes an identifier for an artificial intelligence function and / or a machine learning function; the second identifier includes an identifier for an artificial intelligence model and / or a machine learning model; the third identifier includes an identifier related to network-side configuration; and the fourth identifier includes a dataset identifier. In other words, the base station sends network-side auxiliary information / network-side conditions (function / model ID, etc.) to the terminal.

[0181] S803, the terminal determines whether each AL / ML function / model is an applicable function / model based on the first and fifteenth information, and obtains the fourth and / or fifth information. In other words, the terminal determines the applicable AI / ML functions / models based on network-side auxiliary information / network-side conditions and terminal-side auxiliary information / terminal-side conditions.

[0182] S804, the terminal sends fourth and / or fifth information to the base station.

[0183] S805, the base station determines the fourteenth information based on the fourth and / or fifth information and the first information. In other words, the base station controls the management of AI / ML functions / models based on network-side auxiliary information / network-side conditions and terminal-side auxiliary information / terminal-side conditions, including the selection, (de)activation, switching, and rollback of AI / ML functions (i.e., selecting and applying appropriate AI / ML functions / models from available options) to avoid poor network performance caused by applying mismatched functions / models.

[0184] S806, the base station sends the fourteenth message to the terminal.

[0185] S807, the terminal determines whether the terminal-side auxiliary information / terminal-side conditions have been updated, and whether the applicability status of the AI / ML function / model has been updated. That is, the terminal determines whether the fourth and / or fifth and twelfth pieces of information have been updated, and whether one or more of the sixth, seventh, eighth, ninth, tenth, eleventh, and thirteenth pieces of information have been updated. Among these, the sixth, seventh, eighth, ninth, tenth, eleventh, and thirteenth pieces of information are used to represent the updated identifier.

[0186] S808, the terminal sends an updated identifier to the base station. The updated identifier includes one or more of the sixth, seventh, eighth, ninth, tenth, eleventh, and thirteenth information.

[0187] S809, the base station determines the fourteenth information based on the updated identifier and the first information.

[0188] S810, the base station sends the fourteenth message to the terminal.

[0189] In another embodiment, the network device is a base station, such as... Figure 9 As shown, the information interaction method provided in this disclosure includes the following steps S901 to S909.

[0190] S901, User Equipment Capability Query / Report. For example, in response to a user equipment capability query request sent by the base station, a user equipment capability report (e.g., second information) is sent to the base station.

[0191] S902, the terminal sends fifteenth information to the base station. The fifteenth information, for example, is used to determine at least one of the following: a function and / or model, and the status of the function and / or model. The fifteenth information includes at least one of a fifth identifier, a sixth identifier, a seventh identifier, and an eighth identifier; the fifth identifier includes an identifier for an artificial intelligence function and / or a machine learning function; the sixth identifier includes an identifier for an artificial intelligence model and / or a machine learning model; the seventh identifier includes an identifier related to network-side configuration; and the eighth identifier includes a dataset identifier. In other words, the terminal sends terminal-side auxiliary information / terminal-side conditions (scenario / configuration / mobility, etc.) to the base station.

[0192] S903, the base station determines whether each AI / ML function / model is an applicable function / model based on the first and fifteenth information, thus obtaining the fourth and / or fifth information. In other words, the base station determines whether each AI / ML function / model is an applicable function / model based on network-side auxiliary information / network-side conditions and terminal-side auxiliary information / terminal-side conditions.

[0193] S904, the base station determines the fourteenth information based on the fourth and / or fifth information. In other words, the base station controls the management of AI / ML functions / models based on network-side auxiliary information / network-side conditions and terminal-side auxiliary information / terminal-side conditions, including the selection, (de)activation, switching, and fallback of AI / ML functions (i.e., selecting and applying appropriate AI / ML functions / models from available options) to avoid poor network performance caused by applying mismatched functions / models.

[0194] S905, the base station sends the fourteenth message to the terminal.

[0195] S906, the terminal determines whether the terminal-side auxiliary information / terminal-side conditions have been updated, and whether the applicability status of the AI / ML function / model has been updated. That is, the terminal determines whether the fourth and / or fifth and twelfth pieces of information have been updated, and whether one or more of the sixth, seventh, eighth, ninth, tenth, eleventh, and thirteenth pieces of information have been updated. Among these, the sixth, seventh, eighth, ninth, tenth, eleventh, and thirteenth pieces of information are used to represent the updated identifier.

[0196] S907, the terminal sends an updated identifier to the base station. The updated identifier includes one or more of the sixth, seventh, eighth, ninth, tenth, eleventh, and thirteenth pieces of information.

[0197] S908, the base station determines the fourteenth information based on the updated identifier and the first information.

[0198] S909, the base station sends the fourteenth message to the terminal.

[0199] In summary, this disclosure defines the specific content of network-side auxiliary information / network-side conditions and terminal-side auxiliary information / terminal-side conditions. The terminal can report terminal-side auxiliary information / terminal-side conditions (the fifteenth piece of information) to the base station, and the base station sends network-side auxiliary information / network-side conditions (the first piece of information) to the terminal. Using this information, the base station or the terminal can determine whether AI / ML functions / models are available. Using this information, the base station can control the management of AI / ML functions / models, including the selection, de-activation, switching, and rollback of AI / ML functions (i.e., selecting and applying appropriate AI / ML functions / models from the available options). This disclosure can prevent poor network performance caused by the terminal applying mismatched functions / models.

[0200] In addition, this disclosure also provides a method for updating terminal-side auxiliary information / terminal-side conditions, which allows the base station or terminal to determine whether AI / ML functions / models are available and whether the availability status of AI / ML functions / models has been updated.

[0201] Based on the same inventive concept, this disclosure also provides an information interaction device, as described in the following embodiments. Since the principle by which this device embodiment solves the problem is similar to that of the above-described method embodiments, the implementation of this device embodiment can refer to the implementation of the above-described method embodiments, and repeated details will not be elaborated further.

[0202] Figure 10 This diagram illustrates an information interaction device according to an embodiment of the present disclosure, such as... Figure 10 As shown, the device is applied to a terminal and includes: a first receiving module 1001.

[0203] The first receiving module 1001 can be used to receive first information sent by the network device, the first information being used to determine at least one of the following: function and / or model, and the state of function and / or model.

[0204] In one embodiment, the first information includes at least one of a first identifier, a second identifier, a third identifier, and a fourth identifier; the first identifier includes an identifier for artificial intelligence functions and / or machine learning functions; the second identifier includes an identifier for artificial intelligence models and / or machine learning models; the third identifier includes an identifier related to network-side configuration; and the fourth identifier includes a dataset identifier.

[0205] In one embodiment, the information interaction device further includes a first reporting module 1002, which is used to report second information to the network device, the second information including the terminal's capabilities related to artificial intelligence and / or machine learning.

[0206] In one embodiment, the capabilities related to artificial intelligence and / or machine learning include at least one of supported artificial intelligence functions and supported machine learning functions; and / or, the capabilities related to artificial intelligence and / or machine learning include at least one of supported artificial intelligence models and supported machine learning models.

[0207] In one embodiment, the first receiving module 1001 can also be used to receive third information sent by the network device, the third information being information for measuring communication quality.

[0208] In one embodiment, the first reporting module 1002 may also be used to report fourth information to the network device; the fourth information includes at least one of the following: an identifier of the applicable artificial intelligence function and / or machine learning function; an identifier of the applicable artificial intelligence model and / or machine learning model.

[0209] In one embodiment, the first reporting module 1002 may also be used to report fifth information to the network device. The fifth information is used to indicate whether artificial intelligence and / or machine learning functions are applicable. The fifth information includes at least one of the following: information indicating the applicability of artificial intelligence functions and / or machine learning functions; information indicating the applicability of artificial intelligence models and / or machine learning models.

[0210] In one embodiment, the first reporting module 1002 may also be used to report sixth information to the network device, the sixth information being used to indicate whether the artificial intelligence function and / or machine learning function has been updated; the sixth information includes the identifier of the updated artificial intelligence function and / or machine learning function; or / and, to report seventh information to the network device, the seventh information being used to indicate whether the artificial intelligence model and / or machine learning model has been updated; the seventh information includes the identifier of the updated artificial intelligence model and / or machine learning model.

[0211] In one embodiment, the first reporting module 1002 may also be used to report eighth information to the network device, the eighth information being used to indicate whether the applicability of the artificial intelligence function and / or machine learning function has been updated; the eighth information includes the identifier of the updated applicable artificial intelligence function and / or machine learning function; or / and, to report ninth information to the network device, the ninth information being used to indicate whether the applicability of the artificial intelligence model and / or machine learning model has been updated; the ninth information includes the identifier of the updated applicable artificial intelligence model and / or machine learning model.

[0212] In one embodiment, the first reporting module 1002 may also be used to report tenth information to the network device, the tenth information being used to indicate whether the applicability indication information of the artificial intelligence function and / or machine learning function has been updated; the tenth information includes updated applicability indication information of the artificial intelligence function and / or machine learning function; or / and, to report eleventh information to the network device, the eleventh information being used to indicate whether the applicability indication information of the artificial intelligence model and / or machine learning model has been updated; the eleventh information includes updated applicability indication information of the artificial intelligence model and / or machine learning model.

[0213] In one embodiment, the first reporting module 1002 can also be used to report twelfth information to the network device, the twelfth information being information related to the terminal.

[0214] In one embodiment, the first reporting module 1002 can also be used to report thirteenth information to the network device, the thirteenth information being updated terminal-related information.

[0215] In one embodiment, the first receiving module 1001 can also be used to receive fourteenth information sent by the network device, the fourteenth information being used to instruct the terminal to perform at least one of selection, activation, deactivation, switching, and rollback.

[0216] Figure 11 This diagram illustrates an information interaction device according to an embodiment of the present disclosure, such as... Figure 11 As shown, the device is applied to a network device and includes: a first transmitting module 1101.

[0217] The first sending module 1101 can be used to send first information to the terminal, the first information being used to determine at least one of the following: function and / or model, and the state of function and / or model.

[0218] In one embodiment, the information interaction device further includes a first determining module 1102, which is configured to receive information reported by the terminal, the information reported by the terminal including one or more of the following: fourth information, fifth information, sixth information, seventh information, eighth information, ninth information, tenth information, eleventh information, twelfth information, and thirteenth information; determine fourteenth information based on the information reported by the terminal and the first information, the fourteenth information being used to instruct the terminal to perform at least one of selection, activation, deactivation, switching, and rollback; and send the fourteenth information to the terminal; wherein the fourth information includes at least one of the following: an identifier of the applicable artificial intelligence function and / or machine learning function; and an identifier of the applicable artificial intelligence function and / or machine learning function. The fifth information is used to indicate whether the artificial intelligence and / or machine learning functions are applicable, and includes at least one of the following: information indicating the applicability of the artificial intelligence and / or machine learning functions; information indicating the applicability of the artificial intelligence and / or machine learning models; wherein the first information includes at least one of a first identifier, a second identifier, a third identifier, and a fourth identifier; the first identifier includes an identifier of the artificial intelligence and / or machine learning functions; the second identifier includes an identifier of the artificial intelligence and / or machine learning models; the third identifier includes an identifier related to network-side configuration; and the fourth identifier includes a dataset identifier.

[0219] The information includes: the sixth information includes the identifier of the updated artificial intelligence function and / or machine learning function; the seventh information includes the identifier of the updated artificial intelligence model and / or machine learning model; the eighth information includes the identifier of the updated applicable artificial intelligence function and / or machine learning function; the ninth information includes the identifier of the updated applicable artificial intelligence model and / or machine learning model; the tenth information includes the applicability indication information of the updated artificial intelligence function and / or machine learning function; the eleventh information includes the applicability indication information of the updated artificial intelligence model and / or machine learning model; the twelfth information is terminal-related information; and the thirteenth information is updated terminal-related information.

[0220] Figure 12 This diagram illustrates an information interaction device according to an embodiment of the present disclosure, such as... Figure 12 As shown, the device is applied to a terminal and includes: a second transmitting module 1201.

[0221] The second sending module 1201 can be used to send a fifteenth message to the network device, the fifteenth message being used to determine at least one of the following: function and / or model, and the status of function and / or model.

[0222] In one embodiment, the fifteenth information includes at least one of the fifth identifier, the sixth identifier, the seventh identifier, and the eighth identifier; the fifth identifier includes an identifier for artificial intelligence functions and / or machine learning functions; the sixth identifier includes an identifier for artificial intelligence models and / or machine learning models; the seventh identifier includes an identifier related to network-side configuration; and the eighth identifier includes a dataset identifier.

[0223] In one embodiment, the information interaction device further includes a second reporting module 1202, which can be used to report second information to the network device, the second information including the terminal's capabilities related to artificial intelligence and / or machine learning.

[0224] In one embodiment, the capabilities related to artificial intelligence and / or machine learning include at least one of supported artificial intelligence functions and supported machine learning functions; and / or, the capabilities related to artificial intelligence and / or machine learning include at least one of supported artificial intelligence models and supported machine learning models.

[0225] In one embodiment, the second reporting module 1202 may also be used to report sixth information to the network device, the sixth information indicating whether the artificial intelligence function and / or machine learning function has been updated; the sixth information includes the identifier of the updated artificial intelligence function and / or machine learning function; or / and, report seventh information to the network device, the seventh information indicating whether the artificial intelligence model and / or machine learning model has been updated; the seventh information includes the identifier of the updated artificial intelligence model and / or machine learning model.

[0226] In one embodiment, the second reporting module 1202 can also be used to report eighth information to the network device, the eighth information indicating whether the applicability of the artificial intelligence function and / or machine learning function has been updated; the eighth information includes the identifier of the updated applicable artificial intelligence function and / or machine learning function; or / and, report ninth information to the network device, the ninth information indicating whether the applicability of the artificial intelligence model and / or machine learning model has been updated; the ninth information includes the identifier of the updated applicable artificial intelligence model and / or machine learning model.

[0227] In one embodiment, the second reporting module 1202 can also be used to report tenth information to the network device, the tenth information being used to indicate whether the applicability indication information of the artificial intelligence function and / or machine learning function has been updated; the tenth information includes updated applicability indication information of the artificial intelligence function and / or machine learning function; or / and, to report eleventh information to the network device, the eleventh information being used to indicate whether the applicability indication information of the artificial intelligence model and / or machine learning model has been updated; the eleventh information includes updated applicability indication information of the artificial intelligence model and / or machine learning model.

[0228] In one embodiment, the second reporting module 1202 can also be used to report twelfth information to the network device, the twelfth information being information related to the terminal.

[0229] In one embodiment, the second reporting module 1202 can also be used to report thirteenth information to the network device, the thirteenth information being updated terminal-related information.

[0230] In one embodiment, the information interaction device further includes a third receiving module 1203, which is used to receive fourteenth information sent by the network device. The fourteenth information is used to instruct the terminal to perform at least one of selection, activation, deactivation, switching, and rollback.

[0231] Figure 13 This diagram illustrates an information interaction device according to an embodiment of the present disclosure, such as... Figure 13 As shown, the device is applied to a network device and includes a second receiving module 1301. The second receiving module 1301 can be used to receive fifteenth information sent by a terminal, the fifteenth information being used to determine at least one of the following: function and / or model, and the state of function and / or model.

[0232] In one embodiment, the information interaction device further includes a second determining module 1302, which is configured to acquire first information, the first information including at least one of a first identifier, a second identifier, a third identifier, and a fourth identifier; determine fourth information and / or fifth information based on the first information and the fifteenth information; determine fourteenth information based on the fourth information and / or the fifth information, the fourteenth information being used to instruct the terminal to perform at least one of selection, activation, deactivation, switching, and rollback; and send the fourteenth information to the terminal; wherein the fourth information includes at least one of the following: an identifier of an applicable artificial intelligence function and / or machine learning function; an identifier of an applicable artificial intelligence model and / or machine learning model; wherein the fifth information is used to indicate whether the artificial intelligence and / or machine learning function is... The fifth information includes at least one of the following: information indicating the applicability of artificial intelligence functions and / or machine learning functions; information indicating the applicability of artificial intelligence models and / or machine learning models; a first identifier including an identifier of artificial intelligence functions and / or machine learning functions; a second identifier including an identifier of artificial intelligence models and / or machine learning models; a third identifier including an identifier related to network-side configuration; and a fourth identifier including a dataset identifier. The fifteenth information includes at least one of the fifth, sixth, seventh, and eighth identifiers; the fifth identifier including an identifier of artificial intelligence functions and / or machine learning functions; the sixth identifier including an identifier of artificial intelligence models and / or machine learning models; the seventh identifier including an identifier related to network-side configuration; and the eighth identifier including a dataset identifier.

[0233] In one embodiment, the second receiving module 1301 can also be used to receive information reported by the terminal, which includes one or more of the following: sixth information, seventh information, eighth information, ninth information, tenth information, eleventh information, twelfth information, and thirteenth information; and to determine the fourteenth information based on the information reported by the terminal and the first information; wherein, the sixth information includes an identifier of an updated artificial intelligence function and / or machine learning function; the seventh information includes an identifier of an updated artificial intelligence model and / or machine learning model; the eighth information includes an identifier of an updated applicable artificial intelligence function and / or machine learning function; the ninth information includes an identifier of an updated applicable artificial intelligence model and / or machine learning model; the tenth information includes an indication of the applicability of the updated artificial intelligence function and / or machine learning function; the eleventh information includes an indication of the applicability of the updated artificial intelligence model and / or machine learning model; the twelfth information is terminal-related information; and the thirteenth information is updated terminal-related information.

[0234] Those skilled in the art will understand that various aspects of this disclosure can be implemented in the following forms: a completely hardware implementation, a completely software implementation (including firmware, microcode, etc.), or a combination of hardware and software implementations, which can be collectively referred to herein as a "circuit", "module" or "system".

[0235] Based on the same inventive concept, this disclosure also provides an electronic device, which includes: a processor; and a memory for storing executable instructions of the processor; wherein the processor is configured to execute the information interaction method described above by executing the executable instructions. Since the principle by which this electronic device solves the problem is similar to that of the above method embodiments, the implementation of this electronic device embodiment can refer to the implementation of the above method embodiments, and repeated details will not be described again.

[0236] The following reference Figure 14 To describe an electronic device 1400 according to such an embodiment of the present disclosure. Figure 14 The electronic device 1400 shown is merely an example and should not be construed as limiting the functionality and scope of use of the embodiments disclosed herein.

[0237] like Figure 14 As shown, the electronic device 1400 is manifested in the form of a general-purpose computing device. The components of the electronic device 1400 may include, but are not limited to: at least one processing unit 1410, at least one storage unit 1420, and a bus 1430 connecting different system components (including storage unit 1420 and processing unit 1410).

[0238] The storage unit stores program code that can be executed by the processing unit 1410, causing the processing unit 1410 to perform the steps described in the "Exemplary Methods" section above according to various exemplary embodiments of this disclosure.

[0239] Storage unit 1420 may include readable media in the form of volatile storage units, such as random access memory (RAM) 14201 and / or cache memory 14202, and may further include read-only memory (ROM) 14203.

[0240] Storage unit 1420 may also include a program / utility 14204 having a set (at least one) of program modules 14205, such program modules 14205 including but not limited to: operating system, one or more application programs, other program modules and program data, each or some combination of these examples may include an implementation of a network environment.

[0241] Bus 1430 can represent one or more of several types of bus structures, including a memory cell bus or memory cell controller, a peripheral bus, a graphics acceleration port, a processing unit, or a local bus using any of the various bus structures.

[0242] Electronic device 1400 can also communicate with one or more external devices 1440 (e.g., keyboard, pointing device, Bluetooth device, etc.), and with one or more devices that enable a user to interact with electronic device 1400, and / or with any device that enables electronic device 1400 to communicate with one or more other computing devices (e.g., router, modem, etc.). This communication can be performed via input / output (I / O) interface 1450. Furthermore, electronic device 1400 can also communicate with one or more networks (e.g., local area network (LAN), wide area network (WAN), and / or public networks, such as the Internet) via network adapter 1460. As shown, network adapter 1460 communicates with other modules of electronic device 1400 via bus 1430. It should be understood that, although not shown in the figures, other hardware and / or software modules can be used in conjunction with electronic device 1400, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0243] From the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein can be implemented by software or by combining software with necessary hardware. Therefore, the technical solutions according to the embodiments of this disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (such as a CD-ROM, USB flash drive, external hard drive, etc.) or on a network, including several instructions to cause a computing device (such as a personal computer, server, terminal device, or network device, etc.) to execute the methods according to the embodiments of this disclosure.

[0244] Based on the same inventive concept, this disclosure also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements any of the above-described information interaction methods. Since the principle by which this computer-readable storage medium embodiment solves the problem is similar to that of the above-described method embodiments, the implementation of this computer-readable storage medium embodiment can refer to the implementation of the above-described method embodiments, and repeated details will not be elaborated further.

[0245] More specific examples of computer-readable storage media in this disclosure may include, but are not limited to: electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0246] In this disclosure, a computer-readable storage medium may include a data signal propagated in baseband or as part of a carrier wave, carrying readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A readable signal medium may also be any readable medium other than a readable storage medium, capable of transmitting, propagating, or transmitting a program for use by or in connection with an instruction execution system, apparatus, or device.

[0247] Optionally, the program code contained on the computer-readable storage medium may be transmitted using any suitable medium, including but not limited to wireless, wired, optical fiber, RF, etc., or any suitable combination thereof.

[0248] In practical implementation, program code for performing the operations of this disclosure can be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java and C++, and conventional procedural programming languages ​​such as C or similar languages. The program code can execute entirely on the user's computing device, partially on the user's device, as a standalone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server. In cases involving remote computing devices, the remote computing device can be connected to the user's computing device via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0249] Based on the same inventive concept, this disclosure also provides a computer program product, including a computer program or instructions, which, when executed by a processor, implements any one of the information interaction methods described in the above method embodiments. Since the principle by which this computer program product embodiment solves the problem is similar to that of the above method embodiments, the implementation of this computer program product embodiment can refer to the implementation of the above method embodiments, and repeated details will not be elaborated further.

[0250] It should be noted that although several modules or units for the device used to perform actions have been mentioned in the detailed description above, this division is not mandatory. In fact, according to embodiments of this disclosure, the features and functions of two or more modules or units described above can be embodied in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided and embodied by multiple modules or units.

[0251] Furthermore, although the steps of the method in this disclosure are described in a specific order in the accompanying drawings, this does not require or imply that the steps must be performed in that specific order, or that all the steps shown must be performed to achieve the desired result. Additional or alternative steps may be omitted, multiple steps may be combined into one step, and / or a step may be broken down into multiple steps.

[0252] Other embodiments of this disclosure will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This disclosure is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of this disclosure are indicated by the appended claims.

Claims

1. An information exchange method, characterized in that, Applied to terminals, including: Receive first information sent by a network device, the first information being used to determine at least one of the following: function and / or model, and the status of function and / or model.

2. The method according to claim 1, characterized in that, The functions and / or models include identifiers of the functions and / or models.

3. The method according to claim 1, characterized in that, The state of the function includes the function's applicable state and / or active state; the state of the model includes the model's applicable state and / or active state, the applicable state including: applicable or inapplicable, and the active state including active or inactive.

4. The method according to claim 1, characterized in that, The first information includes at least one of a first identifier, a second identifier, a third identifier, and a fourth identifier: The first identifier includes identifiers for artificial intelligence functions and / or machine learning functions; The second identifier includes the identifier of the artificial intelligence model and / or machine learning model; The third identifier includes identifiers related to network-side configuration; The fourth identifier includes the dataset identifier.

5. The method according to claim 1, characterized in that, The method further includes: The second information is reported to the network device, the second information including the capabilities related to artificial intelligence and / or machine learning supported by the terminal.

6. The method according to claim 5, characterized in that, The capabilities related to artificial intelligence and / or machine learning include at least one of supported artificial intelligence functions and supported machine learning functions; and / or, the capabilities related to artificial intelligence and / or machine learning include at least one of supported artificial intelligence models and supported machine learning models.

7. The method according to claim 1, characterized in that, The method further includes: Receive third information sent by the network device, wherein the third information is information for measuring communication quality.

8. The method according to claim 1, characterized in that, The method further includes: Report the fourth information to the network device; The fourth information includes at least one of the following: Identification of applicable artificial intelligence and / or machine learning capabilities; Identification of applicable artificial intelligence models and / or machine learning models.

9. The method according to claim 1, characterized in that, The method further includes: Report fifth information to the network device, the fifth information being used to indicate whether artificial intelligence and / or machine learning functions are applicable, the fifth information including at least one of the following: Information indicating the applicability of artificial intelligence and / or machine learning capabilities; Information indicating the applicability of artificial intelligence models and / or machine learning models.

10. The method according to claim 1, characterized in that, The method further includes: The network device is reported a sixth piece of information, which indicates whether the artificial intelligence function and / or machine learning function has been updated; the sixth piece of information includes an identifier of the updated artificial intelligence function and / or machine learning function; or / and, The network device reports a seventh piece of information, which indicates whether the artificial intelligence model and / or machine learning model has been updated; the seventh piece of information includes the identifier of the updated artificial intelligence model and / or machine learning model.

11. The method according to claim 8, characterized in that, The method further includes: The network device reports an eighth piece of information, which indicates whether the applicability of the artificial intelligence function and / or machine learning function has been updated; the eighth piece of information includes an identifier of the updated applicable artificial intelligence function and / or machine learning function; or / and, The network device reports a ninth piece of information, which indicates whether the applicability of the artificial intelligence model and / or machine learning model has been updated; the ninth piece of information includes an identifier of the updated applicable artificial intelligence model and / or machine learning model.

12. The method according to claim 9, characterized in that, The method further includes: The network device reports a tenth piece of information, which indicates whether the applicability indication information of the artificial intelligence function and / or machine learning function has been updated; the tenth piece of information includes updated applicability indication information of the artificial intelligence function and / or machine learning function; or / and, The network device reports eleventh information, which is used to indicate whether the applicability indication information of the artificial intelligence model and / or machine learning model has been updated; the eleventh information includes the updated applicability indication information of the artificial intelligence model and / or machine learning model.

13. The method according to claim 1, characterized in that, The method further includes: The twelfth piece of information is reported to the network device, and the twelfth piece of information is information related to the terminal.

14. The method according to claim 11, characterized in that, The method further includes: The network device is reported a thirteenth piece of information, which is updated information related to the terminal.

15. The method according to claim 1, characterized in that, The method further includes: The terminal receives a fourteenth message sent by the network device, the fourteenth message being used to instruct the terminal to perform at least one of selection, activation, deactivation, switching, and rollback.

16. An information exchange method, characterized in that, Applied to network devices, the method includes: Send first information to the terminal, the first information being used to determine at least one of the following: function and / or model, and the status of function and / or model.

17. The method according to claim 16, characterized in that, The method further includes: The terminal receives information reported by the terminal, which includes one or more of the following information: fourth, fifth, sixth, seventh, eighth, ninth, tenth, eleventh, twelfth and thirteenth information. The fourteenth information is determined based on the information reported by the terminal and the first information. The fourteenth information is used to instruct the terminal to perform at least one of selection, activation, deactivation, switching, and rollback. Send the fourteenth message to the terminal; The first information includes at least one of a first identifier, a second identifier, a third identifier, and a fourth identifier: the first identifier includes an identifier for artificial intelligence functions and / or machine learning functions; the second identifier includes an identifier for artificial intelligence models and / or machine learning models; the third identifier includes an identifier related to network-side configuration; and the fourth identifier includes a dataset identifier. The fourth information includes at least one of the following: Identification of the applicable artificial intelligence and / or machine learning functions; Identifiers of the applicable artificial intelligence models and / or machine learning models; The fifth piece of information is used to indicate whether the artificial intelligence and / or machine learning functions are applicable, and the fifth piece of information includes at least one of the following: Information indicating the applicability of the artificial intelligence and / or machine learning functions; Applicability indication information of the artificial intelligence model and / or machine learning model; The sixth piece of information includes updated identifiers of the artificial intelligence function and / or machine learning function; the seventh piece of information includes updated identifiers of the artificial intelligence model and / or machine learning model; the eighth piece of information includes updated identifiers of applicable artificial intelligence function and / or machine learning function; the ninth piece of information includes updated identifiers of applicable artificial intelligence model and / or machine learning model; the tenth piece of information includes updated applicability indication information of the artificial intelligence function and / or machine learning function; the eleventh piece of information includes updated applicability indication information of the artificial intelligence model and / or machine learning model; the twelfth piece of information is information related to the terminal; and the thirteenth piece of information is updated information related to the terminal.

18. An information exchange method, characterized in that, Applied to a terminal, the method includes: Send a fifteenth message to the network device, the fifteenth message being used to determine at least one of the following: function and / or model, and the status of function and / or model.

19. The method according to claim 18, characterized in that, The functions and / or models include identifiers of the functions and / or models.

20. The method according to claim 18, characterized in that, The state of the function includes the function's applicable state and / or active state; the state of the model includes the model's applicable state and / or active state, the applicable state including: applicable or inapplicable, and the active state including active or inactive.

21. The method according to claim 18, characterized in that, The fifteenth piece of information includes at least one of the fifth identifier, the sixth identifier, the seventh identifier, and the eighth identifier; The fifth identifier includes identifiers for artificial intelligence functions and / or machine learning functions; The sixth identifier includes the identifier of the artificial intelligence model and / or machine learning model; The seventh identifier includes identifiers related to network-side configuration; The eighth identifier includes the dataset identifier.

22. The method according to claim 18, characterized in that, The method further includes: The second information is reported to the network device, the second information including the capabilities related to artificial intelligence and / or machine learning supported by the terminal.

23. The method according to claim 22, characterized in that, The capabilities related to artificial intelligence and / or machine learning include at least one of supported artificial intelligence functions and supported machine learning functions; and / or, the capabilities related to artificial intelligence and / or machine learning include at least one of supported artificial intelligence models and supported machine learning models.

24. The method according to claim 18, characterized in that, The method further includes: The network device is reported a sixth piece of information, which indicates whether the artificial intelligence function and / or machine learning function has been updated; the sixth piece of information includes an identifier of the updated artificial intelligence function and / or machine learning function; or / and, The network device reports a seventh piece of information, which indicates whether the artificial intelligence model and / or machine learning model has been updated; the seventh piece of information includes the identifier of the updated artificial intelligence model and / or machine learning model.

25. The method according to claim 18, characterized in that, The method further includes: The network device reports an eighth piece of information, which indicates whether the applicability of the artificial intelligence and / or machine learning functions has been updated; the eighth piece of information includes an identifier of the updated applicable artificial intelligence and / or machine learning functions; or / and, The network device reports a ninth piece of information, which indicates whether the applicability of the artificial intelligence model and / or machine learning model has been updated; the ninth piece of information includes an identifier of the updated applicable artificial intelligence model and / or machine learning model.

26. The method according to claim 18, characterized in that, The method further includes: The network device reports a tenth piece of information, which indicates whether the applicability indication information for the artificial intelligence function and / or machine learning function has been updated; the tenth piece of information includes updated applicability indication information for the artificial intelligence function and / or machine learning function; or / and, The network device reports eleventh information, which indicates whether the applicability indication information of the artificial intelligence model and / or machine learning model has been updated; the eleventh information includes the updated applicability indication information of the artificial intelligence model and / or machine learning model.

27. The method according to claim 18, characterized in that, The method further includes: The twelfth piece of information is reported to the network device, and the twelfth piece of information is information related to the terminal.

28. The method according to claim 27, characterized in that, The method further includes: The network device is reported a thirteenth piece of information, which is updated information related to the terminal.

29. The method according to claim 18, characterized in that, The method further includes: The terminal receives a fourteenth message sent by the network device, the fourteenth message being used to instruct the terminal to perform at least one of selection, activation, deactivation, switching, and rollback.

30. An information exchange method, characterized in that, Applied to network devices, the method includes: The receiving terminal sends a fifteenth piece of information, which is used to determine at least one of the following: function and / or model, and the status of function and / or model.

31. The method according to claim 30, characterized in that, The method further includes: Obtain first information, wherein the first information includes at least one of a first identifier, a second identifier, a third identifier, and a fourth identifier; Based on the first information and the fifteenth information, determine the fourth information and / or the fifth information; Based on the fourth information and / or the fifth information, a fourteenth information is determined, the fourteenth information being used to instruct the terminal to perform at least one of selection, activation, deactivation, switching, and rollback; Send the fourteenth message to the terminal; The fifteenth piece of information includes at least one of the fifth identifier, the sixth identifier, the seventh identifier, and the eighth identifier; The fifth identifier includes identifiers for artificial intelligence functions and / or machine learning functions; The sixth identifier includes the identifier of the artificial intelligence model and / or machine learning model; The seventh identifier includes identifiers related to network-side configuration; The eighth identifier includes the dataset identifier; The fourth information includes at least one of the following: Identification of the applicable artificial intelligence and / or machine learning functions; Identifiers of the applicable artificial intelligence models and / or machine learning models; The fifth piece of information is used to indicate whether the artificial intelligence and / or machine learning functions are applicable, and the fifth piece of information includes at least one of the following: Information indicating the applicability of the artificial intelligence and / or machine learning functions; Applicability indication information of the artificial intelligence model and / or machine learning model; The first identifier includes identifiers for artificial intelligence functions and / or machine learning functions; The second identifier includes the identifier of the artificial intelligence model and / or machine learning model; The third identifier includes identifiers related to network-side configuration; The fourth identifier includes the dataset identifier.

32. The method according to claim 31, characterized in that, The method further includes: The terminal receives information reported by the terminal, which includes one or more of the following information: sixth, seventh, eighth, ninth, tenth, eleventh, twelfth and thirteenth information. The fourteenth piece of information is determined based on the information reported by the terminal and the first piece of information; The sixth piece of information includes updated identifiers of the artificial intelligence function and / or machine learning function; the seventh piece of information includes updated identifiers of the artificial intelligence model and / or machine learning model; the eighth piece of information includes updated identifiers of applicable artificial intelligence function and / or machine learning function; the ninth piece of information includes updated identifiers of applicable artificial intelligence model and / or machine learning model; the tenth piece of information includes updated applicability indication information of the artificial intelligence function and / or machine learning function; the eleventh piece of information includes updated applicability indication information of the artificial intelligence model and / or machine learning model; the twelfth piece of information is information related to the terminal; and the thirteenth piece of information is updated information related to the terminal.

33. An information interaction device, characterized in that, Applied to terminals, including: The first receiving module is configured to receive first information sent by the network device, the first information being used to determine at least one of the following: function and / or model, and the state of function and / or model.

34. An information interaction device, characterized in that, Applied to network devices, including: A first sending module is configured to send first information to a terminal, the first information being used to determine at least one of the following: function and / or model, and the state of function and / or model.

35. An information interaction device, characterized in that, Applied to terminals, including: The second sending module is used to send fifteenth information to the network device, the fifteenth information being used to determine at least one of the following: function and / or model, and the state of function and / or model.

36. An information interaction device, characterized in that, Applied to network devices, including: The second receiving module is used to receive the fifteenth information sent by the terminal, the fifteenth information being used to determine at least one of the following: function and / or model, and the state of function and / or model.

37. An electronic device, characterized in that, include: processor; as well as Memory for storing the executable instructions of the processor; The processor is configured to execute the information interaction method according to any one of claims 1-32 by executing the executable instructions.

38. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the information interaction method according to any one of claims 1-32.

39. A computer program product comprising computer instructions stored in a computer-readable storage medium, wherein the computer instructions, when executed by a processor, implement the operation instructions of the information interaction method according to any one of claims 1-32.

Images