Artificial intelligence communication method and device and storage medium

Abstract

The invention relates to an artificial intelligence communication method and device and a storage medium. The artificial intelligence communication method comprises the following steps: determining processing time, wherein the processing time is time for switching an AI model corresponding to an AI function or model identifier; and switching the AI model corresponding to the AI function or the model identifier based on the processing time. According to the method and the device, the processing time is determined, so that the processing time of switching the AI model corresponding to the AI function or the model identifier is determined.

Description

Artificial intelligence communication method, device and storage medium Technical Field

[0001] The present disclosure relates to the field of communication technologies, and in particular to an artificial intelligence (AI) communication method, device, and storage medium. Background Art

[0002] In recent years, AI technology has achieved continuous breakthroughs in various fields. Among related technologies, AI has been introduced into wireless air interfaces to assist in improving wireless air interface transmission technology. Currently, AI technology is supported for communication processing within wireless air interfaces, including the training of AI models corresponding to model identifiers and the application of model inference.

[0003] Summary of the Invention

[0004] To overcome the problems existing in the related art, the present disclosure provides an AI communication method, device and storage medium.

[0005] According to a first aspect of an embodiment of the present disclosure, there is provided an AI method, which is executed by a terminal and includes:

[0006] Determine a processing time, where the processing time is the time for switching the AI ​​model corresponding to the AI ​​function or model identifier; and switch the AI ​​model corresponding to the AI ​​function or model identifier based on the processing time.

[0007] In one implementation, different AI functions or AI models corresponding to different model identifiers have the same processing time for switching.

[0008] In another embodiment, the processing time is predefined based on a protocol; or the processing time is based on a network device configuration.

[0009] In another embodiment, different AI functions or AI models corresponding to different model identifiers have different processing times for switching.

[0010] In another embodiment, the method includes: sending first information, where the first information is used to instruct the network device to determine a processing time for switching an AI function or an AI model corresponding to a model identifier.

[0011] In another embodiment, the first information includes the processing time for switching AI models corresponding to different AI functions or different model identifiers; and / or the first information includes the association relationship between switching AI models corresponding to different AI functions or different model identifiers; wherein, the processing time for switching between AI models corresponding to different AI functions or different model identifiers with an association relationship is different from the processing time for switching between AI models corresponding to different AI functions or different model identifiers without an association relationship.

[0012] In another embodiment, switching the AI ​​model corresponding to the AI ​​function or model identifier based on the processing time includes: determining the start time of AI communication of the AI ​​model corresponding to the switched AI function or model identifier based on the processing time.

[0013] In another embodiment, the method further includes: synchronizing the processing time with the network device; performing AI communication operations with the network device based on the AI ​​model corresponding to the switched AI function or model identifier, wherein the communication operation time is the time interval for the AI ​​communication operation determined based on the processing time.

[0014] In yet another embodiment, the method further includes: determining an interruption time based on the processing time, where the interruption time is a time during which the terminal is unable to perform AI communication.

[0015] In another embodiment, during the interruption time, the terminal communicates based on a non-AI mode; or the terminal discards unfinished AI operations of the AI ​​model corresponding to the AI ​​function or model identifier before switching.

[0016] In another embodiment, the method further includes: receiving a switching instruction, where the switching instruction is used to instruct the terminal to switch the AI ​​function or the AI ​​model corresponding to the model identifier.

[0017] In another embodiment, the method further includes: determining the AI ​​model corresponding to the switching AI function or model identifier based on preset rules.

[0018] In yet another embodiment, the preset rule includes a change in a radio resource control (RRC) parameter.

[0019] According to a second aspect of an embodiment of the present disclosure, an AI communication method is provided, which is executed by a network device. The method includes: determining a processing time, where the processing time is the time for a terminal to switch the AI ​​model corresponding to the AI ​​function or model identifier.

[0020] In one implementation, different AI functions or AI models corresponding to different model identifiers have the same processing time for switching.

[0021] In another embodiment, the processing time is predefined based on a protocol; or the processing time is based on a network device configuration.

[0022] In another embodiment, different AI functions or AI models corresponding to different model identifiers have different processing times for switching.

[0023] In another embodiment, the method includes: receiving first information, where the first information is used to instruct the network device to determine a processing time for switching an AI function or an AI model corresponding to a model identifier.

[0024] In another embodiment, the first information includes the processing time for switching AI models corresponding to different AI functions or different model identifiers; and / or the first information includes the association relationship between switching AI models corresponding to different AI functions or different model identifiers; wherein, the processing time for switching between AI models corresponding to different AI functions or different model identifiers with an association relationship is different from the processing time for switching between AI models corresponding to different AI functions or different model identifiers without an association relationship.

[0025] In another embodiment, the method further includes: determining, based on the processing time, a time for performing an AI communication operation based on the AI ​​model corresponding to the switched AI function or model identifier; during the communication operation time, performing an AI communication operation with the terminal based on the AI ​​model corresponding to the switched AI function or model identifier, and the communication operation time is the time for the AI ​​communication operation determined based on the processing time.

[0026] In yet another embodiment, the method further includes: determining an interruption time based on the processing time, where the interruption time is a time during which the terminal is unable to perform AI communication.

[0027] In another embodiment, the terminal being unable to perform AI communication includes: the terminal communicating based on a non-AI mode; or the terminal discarding an unfinished AI operation of the AI ​​model corresponding to the AI ​​function or model identifier before switching.

[0028] In yet another embodiment, the method further includes: sending a switching instruction, where the switching instruction is used to instruct the terminal to determine to switch the AI ​​function or the AI ​​model corresponding to the model identifier.

[0029] In another embodiment, the switching of the AI ​​model corresponding to the AI ​​function or model identifier is determined based on a preset rule.

[0030] In yet another embodiment, the preset rule includes a change in a radio resource control (RRC) parameter.

[0031] According to a third aspect of an embodiment of the present disclosure, there is provided an AI communication device, including:

[0032] A processing unit is used to determine a processing time, where the processing time is the time for switching the AI ​​model corresponding to the AI ​​function or model identifier; and based on the processing time, switch the AI ​​model corresponding to the AI ​​function or model identifier.

[0033] In one implementation, different AI functions or AI models corresponding to different model identifiers have the same processing time for switching.

[0034] In another embodiment, the processing time is predefined based on a protocol; or the processing time is based on a network device configuration.

[0035] In another embodiment, different AI functions or AI models corresponding to different model identifiers have different processing times for switching.

[0036] In another embodiment, the AI ​​communication device further includes a sending unit, wherein the sending unit is configured to send first information, where the first information is configured to instruct the network device to determine a processing time for switching the AI ​​function or the AI ​​model corresponding to the model identifier.

[0037] In another embodiment, the first information includes the processing time for switching AI models corresponding to different AI functions or different model identifiers; and / or the first information includes the association relationship between switching AI models corresponding to different AI functions or different model identifiers; wherein, the processing time for switching between AI models corresponding to different AI functions or different model identifiers with an association relationship is different from the processing time for switching between AI models corresponding to different AI functions or different model identifiers without an association relationship.

[0038] In another embodiment, the processing unit switches the AI ​​model corresponding to the AI ​​function or model identifier based on the processing time in the following manner:

[0039] Based on the processing time, a start time for AI communication by the AI ​​model corresponding to the switched AI function or model identifier is determined.

[0040] In another embodiment, the processing unit is also used to synchronize the processing time with the network device; during the communication operation time, the processing unit performs AI communication operations with the network device based on the AI ​​model corresponding to the switched AI function or model identifier, and the communication operation time is the time for AI communication operations determined based on the processing time.

[0041] In yet another embodiment, the processing unit is further configured to determine an interruption time based on the processing time, where the interruption time is a time during which the terminal is unable to perform AI communication.

[0042] In another embodiment, during the interruption time, the terminal communicates based on a non-AI mode; or the terminal discards unfinished AI operations of the AI ​​model corresponding to the AI ​​function or model identifier before switching.

[0043] In another embodiment, the AI ​​communication device further includes a receiving unit, wherein the receiving unit is configured to receive a switching instruction, wherein the switching instruction is configured to instruct the terminal to switch the AI ​​function or the AI ​​model corresponding to the model identifier.

[0044] In another embodiment, the processing unit is further configured to determine the AI ​​model corresponding to the switching AI function or model identifier based on a preset rule.

[0045] In yet another embodiment, the preset rule includes a change in a radio resource control (RRC) parameter.

[0046] According to a fourth aspect of an embodiment of the present disclosure, there is provided an AI communication apparatus, executed by a network device, comprising:

[0047] The processing unit is used to determine a processing time, where the processing time is the time it takes for the terminal to switch the AI ​​model corresponding to the AI ​​function or model identifier.

[0048] In one implementation, different AI functions or AI models corresponding to different model identifiers have the same processing time for switching.

[0049] In another embodiment, the processing time is predefined based on a protocol; or the processing time is based on a network device configuration.

[0050] In another embodiment, different AI functions or AI models corresponding to different model identifiers have different processing times for switching.

[0051] In another embodiment, the AI ​​communication device further includes a receiving unit, wherein the receiving unit is used to receive first information, where the first information is used to instruct the network device to determine a processing time for switching the AI ​​function or the AI ​​model corresponding to the model identifier.

[0052] In another embodiment, the first information includes the processing time for switching AI models corresponding to different AI functions or different model identifiers; and / or the first information includes the association relationship between switching AI models corresponding to different AI functions or different model identifiers; wherein, the processing time for switching between AI models corresponding to different AI functions or different model identifiers with an association relationship is different from the processing time for switching between AI models corresponding to different AI functions or different model identifiers without an association relationship.

[0053] In another embodiment, the processing unit is further used to determine, based on the processing time, a time for performing an AI communication operation based on the AI ​​model corresponding to the switched AI function or model identifier; and during the communication operation time, perform an AI communication operation with the terminal based on the AI ​​model corresponding to the switched AI function or model identifier, and the communication operation time is the time for the AI ​​communication operation determined based on the processing time.

[0054] In yet another embodiment, the processing unit is further configured to determine an interruption time based on the processing time, where the interruption time is a time during which the terminal is unable to perform AI communication.

[0055] In another embodiment, the terminal being unable to perform AI communication includes: the terminal communicating based on a non-AI mode; or the terminal discarding an unfinished AI operation of the AI ​​model corresponding to the AI ​​function or model identifier before switching.

[0056] In another embodiment, the AI ​​communication device further includes a sending unit, wherein the sending unit is configured to send a switching instruction, wherein the switching instruction is configured to instruct the terminal to determine the AI ​​model corresponding to the switching AI function or model identifier.

[0057] In another embodiment, the processing unit is further configured to determine the AI ​​model corresponding to the switching AI function or model identifier based on a preset rule.

[0058] In yet another embodiment, the preset rule includes a change in a radio resource control (RRC) parameter.

[0059] According to a fifth aspect of an embodiment of the present disclosure, there is provided an AI communication device, including:

[0060] a processor; a memory for storing instructions executable by the processor;

[0061] The processor is configured to execute the AI ​​communication method described in the first aspect or any one of the embodiments of the first aspect.

[0062] According to a sixth aspect of an embodiment of the present disclosure, there is provided an AI communication device, including:

[0063] a processor; a memory for storing instructions executable by the processor;

[0064] The processor is configured to execute the AI ​​communication method described in the second aspect or any one of the embodiments of the second aspect.

[0065] In a seventh aspect of the embodiments of the present disclosure, a storage medium is provided, in which instructions are stored. When the instructions in the storage medium are executed by a processor of a terminal, the terminal is enabled to execute the method described in the first aspect or any one embodiment of the first aspect.

[0066] In an eighth aspect of the embodiments of the present disclosure, a storage medium is provided, in which instructions are stored. When the instructions in the storage medium are executed by a processor of a terminal, the terminal is enabled to execute the method described in the first aspect or any one embodiment of the first aspect.

[0067] According to a ninth aspect of an embodiment of the present disclosure, an artificial intelligence communication system is provided, the system comprising: a terminal for executing the method described in the first aspect or any one of the embodiments of the first aspect; and a network device for executing the method described in the second aspect or any one of the embodiments of the second aspect.

[0068] The technical solutions provided by the embodiments of the present disclosure may have the following beneficial effects: determining the processing time for switching the AI ​​model corresponding to the AI ​​function or model identifier, thereby achieving the determination of the processing time for switching the AI ​​function or model identifier. Based on the processing time, the AI ​​model corresponding to the AI ​​function or model identifier is switched, thereby improving the communication performance of the AI ​​model switching based on the AI ​​function or model identifier.

[0069] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0070] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the present disclosure.

[0071] Fig. 1 is a schematic diagram showing a wireless communication system according to an exemplary embodiment.

[0072] Fig. 2a is a flow chart showing an AI communication method according to an exemplary embodiment.

[0073] Fig. 2b is a flowchart showing yet another AI communication method according to an exemplary embodiment.

[0074] Fig. 2c is a flow chart showing yet another AI communication method according to an exemplary embodiment.

[0075] Fig. 2d is a flowchart showing yet another AI communication method according to an exemplary embodiment.

[0076] Fig. 2e is a flowchart showing yet another AI communication method according to an exemplary embodiment.

[0077] Fig. 2f is a flowchart showing yet another AI communication method according to an exemplary embodiment.

[0078] Fig. 2g is a flowchart showing yet another AI communication method according to an exemplary embodiment.

[0079] Fig. 3a is a flowchart showing an AI communication method according to an exemplary embodiment.

[0080] Fig. 3b is a flowchart showing yet another AI communication method according to an exemplary embodiment.

[0081] FIG4 is a schematic diagram showing the architecture of an AI communication system according to an exemplary embodiment.

[0082] FIG5 a is a structural block diagram of an AI communication device according to an exemplary embodiment.

[0083] Fig. 5b is a structural block diagram of yet another AI communication device according to an exemplary embodiment.

[0084] Fig. 5c is a structural block diagram of yet another AI communication device according to an exemplary embodiment.

[0085] Fig. 5d is a structural block diagram of an AI communication device according to an exemplary embodiment.

[0086] Fig. 5e is a structural block diagram of yet another AI communication device according to an exemplary embodiment.

[0087] FIG5f is a structural block diagram of yet another AI communication device according to an exemplary embodiment.

[0088] Fig. 6 is a block diagram of a device for AI communication according to an exemplary embodiment.

[0089] Fig. 7 is a block diagram of a device for AI communication according to an exemplary embodiment. DETAILED DESCRIPTION

[0090] Exemplary embodiments are described in detail herein, with examples illustrated in the accompanying drawings. When the following description refers to the drawings, identical numerals in different drawings represent identical or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments are not intended to represent all embodiments consistent with the present disclosure.

[0091] The communication method of the embodiment of the present disclosure can be applied to the wireless communication system shown in Figure 1. Referring to Figure 1, the wireless communication system includes a network device and a terminal. The terminal is connected to the network device through wireless resources and performs data transmission.

[0092] It should be understood that the wireless communication system shown in Figure 1 is for illustrative purposes only, and the wireless communication system may also include other network devices, such as core network devices, wireless relay devices, and wireless backhaul devices, which are not shown in Figure 1. The embodiments of the present disclosure do not limit the number of network devices and terminals included in the wireless communication system.

[0093] It can be further understood that the wireless communication system of the embodiment of the present disclosure is a network that provides wireless communication functions. The wireless communication system can adopt different communication technologies, such as code division multiple access (CDMA), wideband code division multiple access (WCDMA), time division multiple access (TDMA), frequency division multiple access (FDMA), orthogonal frequency-division multiple access (OFDMA), single carrier frequency division multiple access (SC-FDMA), carrier sense multiple access / collision avoidance (Carrier Sense Multiple Access with CollisionAvoidance). According to factors such as the capacity, rate, and latency of different networks, the network can be divided into 2G (English: generation) network, 3G network, 4G network or future evolution network, such as 5G network, which can also be called New Radio (NR). For the convenience of description, the present disclosure sometimes refers to the wireless communication network as simply a network.

[0094] Furthermore, the network devices involved in the present disclosure may also be referred to as wireless access network devices. The wireless access network device may be: a base station, an evolved node B (base station), a home base station, an access point (AP) in a wireless fidelity (WIFI) system, a wireless relay node, a wireless backhaul node, a transmission point (TP) or a transmission and reception point (TRP), etc. It may also be a gNB in ​​an NR system, or it may also be a component or part of a base station. It should be understood that in the embodiments of the present disclosure, the specific technology and specific device form adopted by the network device are not limited. In the present disclosure, the network device can provide communication coverage for a specific geographical area and can communicate with terminals located in the coverage area (cell). In addition, when it is a vehicle-to-everything (V2X) communication system, the network device may also be a vehicle-mounted device.

[0095] Furthermore, the terminal involved in the present disclosure may also be referred to as a terminal device, user equipment (UE), mobile station (MS), mobile terminal (MT), etc., which is a device that provides voice and / or data connectivity to users. For example, the terminal can be a handheld device with wireless connection function, a vehicle-mounted device, etc. At present, some examples of terminals are: smart phones (Mobile Phones), customer premises equipment (Customer Premise Equipment, CPE), pocket computers (Pocket Personal Computers, PPCs), handheld computers, personal digital assistants (Personal Digital Assistants, PDAs), laptops, tablet computers, wearable devices, or vehicle-mounted devices, etc. In addition, when it is a vehicle-to-everything (V2X) communication system, the terminal device can also be a vehicle-mounted device. It should be understood that the embodiments of the present disclosure do not limit the specific technology and specific device form adopted by the terminal.

[0096] In recent years, artificial intelligence (AI) technology has made continuous breakthroughs in many fields. AI technology is gradually cross-penetrating into other disciplines, providing new directions and methods for the development of different disciplines.

[0097] In related technologies, the 3rd Generation Partnership Project (3GPP) has established a research project on artificial intelligence technology in wireless air interfaces. This project aims to study the introduction of AI technology in wireless air interfaces and explore how AI technology can assist in improving wireless air interface transmission technology.

[0098] In the research on AI communications, AI use cases may include: AI-based channel state information (CSI) enhancement, AI-based beam management, and AI-based positioning.

[0099] It's understandable that AI use cases can also be called AI features. These are communication scenarios where AI-based communication operations are performed to achieve a specific purpose. For example, AI can be used to predict channel information in the time domain or to manage beams in the air domain. An AI feature is typically defined in the protocol.

[0100] In the aforementioned AI use cases, multiple AI functions are defined for each AI use case. Different AI functions may be configured within a single AI use case. For example, assuming that the AI-based CSI enhancement use case includes two AI functions, AI function #1 may support the prediction of the optimal beam ID, and AI function #2 may support the prediction of the optimal beam and the corresponding beam measurement results.

[0101] For AI functions, they are implemented through corresponding AI models. During the communication processing, if the AI ​​function is to be switched, it may involve the switching of the AI ​​model (AI model), or it may not involve the switching of the AI ​​model. For example, the implementation of AI function 1# may be implemented through model A, and the implementation of AI function 2# may be implemented through model B. If the AI ​​function is to be switched from AI function 1# to AI function 2#, it is necessary to switch model A to model B accordingly. Furthermore, if AI function 1# is implemented through model C, and AI function 2# can also be implemented through model C, then there is no need to switch the corresponding model when switching the AI ​​function from AI function 1# to AI function 2#. When the AI ​​model switch occurs, the terminal needs to reload the AI ​​model from the storage. The process of loading the new model and completing the model switch will be accompanied by the interruption of the model processing. The time of the model processing interruption will be called the interruption time.

[0102] Based on this, the interruption time may vary depending on the mapping between different AI models and AI functions. Some interruption times may be equal to the processing time, while others may be longer. Furthermore, the number of AI models corresponding to each AI function may vary, which can also lead to different processing times when switching AI functions.

[0103] Regarding the processing time of AI model switching, there are also the following scenarios: When the AI ​​model is deployed on the terminal side, the terminal will register the model with the network device and obtain a model ID. The model ID can be set for both the logical model and the physical model.

[0104] It can be understood that the physical model is the AI ​​model actually used to implement AI functions, and the logical model is the AI ​​model that virtualizes the functions and conditions implemented by the physical model.

[0105] Therefore, when a network device instructs a logical model switch based on a model identifier, this may result in a switch between different physical models under the same model identifier, or it may not result in a physical model switch at all. In this case, the interruption time caused by the model switch will vary. Furthermore, the number of physical models associated with a model identifier will also vary, resulting in different model switch processing times.

[0106] In the related art, when switching the AI ​​function or model identifier corresponding to the AI ​​model, the processing time corresponding to the switching process is not clear, and thus the communication processing based on the AI ​​function switching or the model identifier corresponding to the AI ​​model switching will not be clear, affecting the communication performance.

[0107] Based on this, the present disclosure provides an AI communication method, which clarifies the processing time corresponding to the AI ​​function switching or the AI ​​model switching corresponding to the model identifier, and based on the processing time, switches the AI ​​function or switches the AI ​​model corresponding to the model identifier to improve communication performance.

[0108] It should be noted that, for the sake of convenience of description, the switching time used for switching AI functions or AI models in each embodiment of the present disclosure is described in terms of processing time.

[0109] It should be noted that the representation of the processing time involved in each embodiment of the present disclosure may include at least one of the following: absolute time, communication time unit and AI time unit.

[0110] Among them, absolute time includes: seconds, milliseconds, microseconds, etc.

[0111] Communication time units include: Orthogonal Frequency Division Multiplexing (OFDM) symbols, slots, subslots, and OFDM symbol sampling intervals.

[0112] The AI ​​time unit is used to describe the time unit of AI communication. It is understood that the AI ​​time unit is defined as the basic time unit used to measure AI processing tasks.

[0113] The processing time involved in the embodiments of the present disclosure can be represented based on at least one of the absolute time, communication time unit, and AI time unit involved above. It should be noted that in some special scenarios, the switching time between different AI functions or AI models may be zero.

[0114] The following describes the AI ​​communication method involved in the present disclosure.

[0115] FIG2a is a flow chart of an AI communication method according to an exemplary embodiment. As shown in FIG2a , the AI ​​communication method, executed by a terminal, includes the following steps:

[0116] In step S11, a processing time is determined, where the processing time is the time for performing AI function switching or AI model switching corresponding to the model identifier.

[0117] In step S12, based on the processing time, the AI ​​model corresponding to the AI ​​function or model identifier is switched.

[0118] In the embodiment of the present disclosure, the processing time for switching the AI ​​model corresponding to the AI ​​function or model identifier is determined, and the switching time corresponding to the AI ​​model switching corresponding to the AI ​​function or model identifier is clarified.

[0119] In the AI ​​communication method provided in the embodiments of the present disclosure, AI function switching can be understood as switching between different AI functions. AI model switching corresponding to a model identifier can be understood as switching between AI models corresponding to different model identifiers. Among them, the AI ​​models corresponding to different model identifiers can be understood as different AI models under the same model identifier, or as different AI models corresponding to different model identifiers.

[0120] In one implementation of the AI ​​communication method provided by the embodiment of the present disclosure, the processing time for switching AI models corresponding to different AI functions or different model identifiers is the same.

[0121] In one implementation of the disclosed embodiment, the terminal may determine that the processing time for switching different AI functions is the same, and determine the switching time of different AI functions to be the same processing time, so as to simplify the processing of switching different AI functions.

[0122] It is understandable that the processing time required to switch between different AI functions may objectively be different. In some scenarios, to simplify processing, the processing time of different AI functions can be defined as the same processing time. For example, when the difference in the processing time of different AI functions is less than a certain time threshold, the processing time of the different AI functions can be determined to be the same.

[0123] For example, the different AI functions to be switched include AI function #1, AI function #2, and AI function #3. In this embodiment of the present disclosure, the switching time for different AI functions is defined as the same time, T1. Therefore, the processing time for switching between AI function #3 and AI function #1 is T1. The processing time for switching between AI function #3 and AI function #2 is T1. The processing time for switching between AI function #2 and AI function #1 is T1.

[0124] In one implementation of the present disclosure, the same processing time for switching between different AI functions may be predefined by a protocol, or the same processing time for switching between different AI functions may be based on a network device configuration.

[0125] In one implementation of the disclosed embodiment, the terminal may determine that the processing time for switching the AI ​​models corresponding to different model identifiers is the same, and determine the switching time of the AI ​​models corresponding to different model identifiers to be the same processing time, so as to simplify the processing of switching the AI ​​models corresponding to different model identifiers.

[0126] Exemplarily, the AI ​​models corresponding to the different model identifiers to be switched include the physical model m1 corresponding to the model identifier M, the physical model n1 corresponding to the model identifier N, and the physical model l1 corresponding to the model identifier L (it can be understood that M, N and L are different, and the physical model m1, the physical model n1 and the physical model l1 can be the same or different). In the embodiment of the present disclosure, the time for the AI ​​models corresponding to different model identifiers is defined as the same time T2. Therefore, the processing time for switching between the physical model m1 corresponding to the model identifier M and the physical model n1 corresponding to the model identifier N is T2, the processing time for switching between the physical model n1 corresponding to the model identifier N and the physical model l1 corresponding to the model identifier L is T2, and the processing time for switching between the physical model m1 corresponding to the model identifier M and the physical model l1 corresponding to the model identifier L is T2.

[0127] In the AI ​​communication method provided in the embodiments of the present disclosure, the same processing time for switching AI models corresponding to different model identifiers may be predefined by the protocol. Alternatively, the same processing time for switching AI models corresponding to different model identifiers may be based on network device configuration.

[0128] In the AI ​​communication method provided in the embodiments of the present disclosure, for switching of different AI functions or switching of AI models corresponding to different model identifiers, the situation where the switching time is the same is clarified.

[0129] In the embodiment of the present disclosure, the same processing time is predefined based on a protocol or the same processing time is based on a network configuration.

[0130] In another embodiment of the AI ​​communication method provided by the present disclosure, different AI functions or AI models corresponding to different model identifiers have different processing times for switching to adapt to the switching processing of AI functions or AI models with different association relationships.

[0131] The association relationship can be determined by whether the same AI model is used. For example, if two AI functions use the same AI model, the two AI functions are determined to be associated. Alternatively, if the model identifiers corresponding to two logical AI models use the same physical AI model, the two logical AI models are determined to be associated.

[0132] The different AI functions to be switched may or may not have an association relationship. The terminal may determine that the processing time for switching different AI functions is different.

[0133] For example, switching is performed for different AI functions: AI function #1, AI function #2, and AI function #3. AI function #1 and AI function #2 use the same AI model and are associated. AI function #1 and AI function #3 use different AI models and are not associated. In this embodiment, different processing times are defined for switching between different AI functions. The processing time for switching between AI function #1 and AI function #2 is T3. The processing time for switching between AI function #1 and AI function #3 is T4, where T3 is not equal to T4.

[0134] The different AI models switched may or may not have an association relationship. In one implementation of the embodiment of the present disclosure, the terminal may determine that the processing time for switching the AI ​​models corresponding to different model identifiers is different.

[0135] Exemplarily, the AI ​​model switching corresponding to different model identifiers may include the model identifier switching causing a change in the physical model, that is, there is no association relationship between the AI ​​models before and after the switching. The AI ​​model switching corresponding to different model identifiers may include the model identifier switching not causing a change in the physical model, that is, there is an association relationship between the AI ​​models before and after the switching. For example, taking the model identifier M / model identifier N and the model identifier O as an example, the M identifier also corresponds to the physical model m1, the identifier N corresponds to the physical model n1, and the O corresponds to the physical model m1. Among them, the physical model used by the model identifier O is the same as that used by the model identifier M, and they have an association relationship. The physical models used by the model identifier M and the model identifier N are different, and they do not have an association relationship. In the embodiment of the present disclosure, the processing time for the AI ​​model switching corresponding to different model identifiers is defined to be different. The switching between the model identifier M and the model identifier O is T5, and the switching between the model identifier M and the model identifier N is T6. T5 is not equal to T6.

[0136] It can be understood that based on the description of the above embodiments, the situations corresponding to switching AI models corresponding to different AI functions or different model identifiers have been explained. Here, the above situations are similar and will not be described one by one.

[0137] In the AI ​​communication method provided in the embodiments of the present disclosure, for AI model switching corresponding to different AI functions or different model identifiers, different switching times are clarified.

[0138] In the AI ​​communication method provided by the embodiment of the present disclosure, the terminal reports the processing time of different AI function switching or the processing time of AI model switching corresponding to different model identifiers to the network device, so that the network device can determine the processing time of different AI function switching or the processing time of AI model switching corresponding to different model identifiers.

[0139] FIG2b is a flow chart of another AI communication method according to an exemplary embodiment. In one embodiment of the present disclosure, as shown in FIG2b, the method includes the following steps:

[0140] In step S21, first information is sent.

[0141] In an embodiment of the present disclosure, the first information is used to instruct the network device to determine the processing time for switching different AI functions or the processing time for switching AI models corresponding to different model identifiers.

[0142] In an embodiment of the present disclosure, the terminal sends a first message to the network device, which indicates the processing time of different AI functions or the processing time of switching AI models corresponding to different model identifiers through the first message, thereby enabling the network device to determine the processing time of switching different AI functions or the processing time of switching AI models corresponding to different model identifiers.

[0143] In one implementation of the AI ​​communication method of the embodiment of the present disclosure, the first information may explicitly indicate the processing time for switching the AI ​​models corresponding to different AI functions or different model identifiers, or may implicitly indicate the processing time for switching the AI ​​models corresponding to different AI functions or different model identifiers.

[0144] In one implementation of the AI ​​communication method provided in the embodiment of the present disclosure, the first information includes at least one of the following (1) and (2):

[0145] (1) The processing time required to switch between AI models corresponding to different AI functions or different model identifiers.

[0146] In the embodiment of the present disclosure, the processing time included in the first information may be predefined based on a protocol or configured based on a network device.

[0147] Exemplarily, when predefined based on a protocol, the protocol may predefine multiple optional values, such as 1 millisecond, 2 milliseconds, and 3 milliseconds, etc. The terminal may report based on the predefined optional values ​​according to a preset selection rule.

[0148] Exemplarily, the terminal may report the switching time T1 between AI function #1 and AI function #2, and the switching time T2 between AI function #1 and AI function #3.

[0149] (2) The association relationship between switching between AI models corresponding to different AI functions or different model identifiers.

[0150] Among them, the association relationship involved in the embodiment of the present disclosure is used to determine the processing time of switching different AI functions, or to determine the processing time of switching AI models corresponding to different model identifiers.

[0151] In the embodiments of the present disclosure, scenarios with associated relationships may include at least one of the following: multiple AI functions using the same AI model, or multiple logical models using the same physical model. Each logical model corresponds to a model identifier, and the logical model and logical identifier mentioned below can be used interchangeably.

[0152] For example, if Model A is used to implement Function 1#, Model B is used to implement Function 2#, and Model B is used to implement Function 3#, Model A and Model B are different. Based on this, we can conclude that Function 2# and Function 3# are different functions, but both Function 2# and Function 3# are implemented using Model B, thus confirming that Function 2# and Function 2# are associated. Furthermore, if Function 1# and Function 2# are different functions, and Function 1# is implemented using Model A, while Function 2# is implemented using Model B, then we can confirm that Function 1# and Function 2# are not associated.

[0153] It can be understood that logical model M1 corresponds to physical model m1, logical model M2 corresponds to physical model m2, and logical model M3 corresponds to physical model m2, where physical model m1 and physical model m2 are different. Based on this, it can be understood that logical model M2 and logical model M3 both use physical model m2, so logical model M2 and logical model M3 have an association relationship. However, logical model M1 uses physical model m1, which is different from logical model M2, so logical model M1 and logical model M2 have no association relationship.

[0154] In an embodiment of the present disclosure, after determining the association relationship for switching AI functions or AI models corresponding to different model identifiers, the terminal can report the association relationship to the network device, and the network device determines the processing time based on the obtained association relationship.

[0155] The processing time used for switching between different AI functions that have an associated relationship is different from the processing time used for switching between different AI functions that do not have an associated relationship.

[0156] The processing time for switching between AI models corresponding to different model identifiers with an associated relationship is different from the processing time for switching between AI models corresponding to different model identifiers without an associated relationship.

[0157] It is understandable that the terminal will pre-store the corresponding processing time mapping relationship between AI models corresponding to different functions or different model identifiers.

[0158] It is understandable that in some scenarios, the processing time corresponding to the switching of associated AI functions and the switching of associated model identifiers may be 0.

[0159] Exemplarily, the terminal and the network device pre-store different AI functions with associated relationships, and the AI ​​models corresponding to different model identifiers with associated relationships. The terminal can report which AI functions are associated based on whether there is an associated relationship between different AI functions. When switching is required, the terminal reports the AI ​​functions before and after the switching. In this way, after receiving the switching between the AI ​​functions reported by the terminal, the network device can determine whether the AI ​​functions before and after the switching are switching between AI functions with associated relationships or switching between AI functions without associated relationships. Then, based on the mapping relationship between the AI ​​functions with associated relationships and the switching time, and the mapping relationship between the AI ​​functions without associated relationships and the switching time, the processing time of the switching is determined.

[0160] In one example, since the models corresponding to the associated AI functions are the same, even if the AI ​​function is switched, the model used will not be switched, so the switching time can be 0.

[0161] In one example, unrelated AI functions correspond to different models, and switching of the AI ​​function results in switching of the used model, so the switching time is greater than 0.

[0162] In the embodiment of the present disclosure, the switching time when the AI ​​functions with associated relationships are switched is shorter than the switching time when the AI ​​functions without associated relationships are switched.

[0163] Figure 2c is a flow chart of another AI communication method according to an exemplary embodiment. In one implementation of the disclosed embodiment, as shown in Figure 2c, the terminal can enable the network device to determine the processing time for switching between different AI functions or the processing time for switching between AI models with different model identifiers in the following manner:

[0164] In step S31, the terminal reports the processing time of switching between different AI functions or the processing time of switching between AI models with different model identifiers.

[0165] In an embodiment of the present disclosure, the network device may determine the processing time for switching different AI functions or the processing time for switching AI models with different model identifiers based on the processing time reported by the terminal.

[0166] In the embodiment of the present disclosure, the network device can convert the processing time reported by the terminal to the time for communication processing between the terminal and the network device. For example, the time can be the time represented by the communication time unit in the communication system.

[0167] Exemplarily, the network device determines the representation of the processing time when switching the AI ​​function or AI model in the communication system based on the representation of the processing time reported by the terminal.

[0168] Exemplarily, the processing time determined by the network device may be expressed in communication time units. The processing time reported by the terminal may be expressed in absolute time, communication time units, or AI time units. For example, if the processing time reported by the terminal is 0.5 milliseconds, the corresponding processing time determined by the network device may be 1 OFDM symbol.

[0169] In an embodiment of the present disclosure, the terminal may determine the time for subsequent communication processing based on the determined processing time for switching between different AI functions or the processing time for switching between AI models with different model identifiers. For example, the time for the communication processing may be the start time of AI communication performed by the AI ​​model corresponding to the switched AI function or model identifier. For another example, the time for the communication processing may be the time for performing AI communication operations based on the AI ​​model corresponding to the switched AI function or model identifier.

[0170] FIG2 d is a flowchart of another AI communication method according to an exemplary embodiment. In one implementation of the embodiment of the present disclosure, as shown in FIG2 d , the terminal may determine the start time of AI communication for the AI ​​model corresponding to the switched AI function or model identifier in the following manner:

[0171] In step S41: based on the processing time, the start time of AI communication of the AI ​​model corresponding to the switched AI function or model identifier is determined.

[0172] In the embodiment of the present disclosure, the processing time may be the processing time reported by the terminal or the processing time determined by the network device.

[0173] For example, if the switching time between AI function #1 and AI function #2 is X time units, then based on X time units, the terminal can determine that AI function #2 will take effect after Z time units. Z is determined based on X, and Z is the start time. For example, in AI-based beam management, when switching from AI function #1 to AI function #2, where AI function #2 requires the terminal to send the predicted optimal beam ID and the measurement result of the optimal beam, the terminal will then feedback the optimal beam ID and the corresponding measurement result after Z time units at the earliest.

[0174] Figure 2e is a flow chart of another AI communication method according to an exemplary embodiment. In one implementation of the disclosed embodiment, as shown in Figure 2e, the terminal can enable the network device to determine the time for performing the AI ​​communication operation based on the AI ​​model corresponding to the switched AI function or model identifier in the following manner:

[0175] In step S51: synchronizing processing time with network equipment.

[0176] In step S52: during the communication operation time, an AI communication operation is performed with the network device based on the AI ​​model corresponding to the switched AI function or model identifier. The communication operation time is the time for the AI ​​communication operation determined based on the processing time.

[0177] Exemplarily, the time for performing an AI communication operation based on the AI ​​model corresponding to the switched AI function or model identifier may be the time at which the network device performs the AI ​​communication operation based on the AI ​​model corresponding to the switched AI function or model identifier. For example, the network device sends an instruction instructing the terminal to perform the AI ​​operation. In this case, the terminal and the network device synchronize the processing time for switching between different AI functions or the processing time for switching between AI models with different model identifiers, so that the network device determines the time for performing the AI ​​communication operation based on the AI ​​model corresponding to the switched AI function or model identifier.

[0178] For example, if the switching time between AI function #1 and AI function #2 is X time units, then based on X time units, the network can determine that it can send instructions to the terminal to perform the corresponding AI operation after Z time units. For example, in AI-based positioning, if switching from AI function #1 to AI function #2, the network can only send a positioning request based on AI function #2 after Z time units.

[0179] Figure 2f is a flow chart of another AI communication method according to an exemplary embodiment. In one embodiment of the AI ​​communication method provided by the present disclosure, as shown in Figure 2f, the terminal can determine the interruption time in the following manner:

[0180] In step S61: based on the processing time, an interruption time is determined, wherein the interruption time is used to indicate the time when the terminal cannot perform AI communication.

[0181] In the embodiment of the present disclosure, the interruption time may be greater than the processing time, or may be equal to the processing time.

[0182] In one implementation of the embodiment of the present disclosure, during the interruption time, the terminal can perform the following operations: communicate in a non-AI mode; or the terminal discards the unfinished AI operation of the AI ​​model corresponding to the AI ​​function or model identifier before switching.

[0183] Exemplarily, communication operations are performed based on a Non-AI method during the interruption time.

[0184] It is understandable that the terminal selects the non-AI mode for communication based on preset rules.

[0185] Figure 2g is a flow chart of another AI communication method according to an exemplary embodiment. In one implementation of the AI ​​communication method provided by the embodiment of the present disclosure, as shown in Figure 2g, the terminal can determine the processing time through the following steps, including:

[0186] In step S71: it is determined that the AI ​​function needs to be switched or the AI ​​model corresponding to the model identifier needs to be switched.

[0187] In step S72 , based on determining that the AI ​​function needs to be switched or determining that the AI ​​model corresponding to the model identifier needs to be switched, a processing time is determined.

[0188] In an embodiment of the present disclosure, the terminal may determine the processing time when determining that the AI ​​function needs to be switched or determining that the AI ​​model corresponding to the model identifier needs to be switched.

[0189] In one implementation of the embodiment of the present disclosure, the AI ​​model corresponding to the switching AI function or model identifier is determined based on a preset rule.

[0190] In one implementation of the embodiment of the present disclosure, the preset rule includes a change in a Radio Resource Control (RRC) parameter.

[0191] For example, AI function #1 supports running when the RRC parameter is configured as X, and AI function #2 supports running when the RRC parameter is configured as Y. When the network device reconfigures the RRC parameter from X to Y, the AI ​​function running on the terminal side also switches from function #1 to function #2.

[0192] It should be noted that those skilled in the art will appreciate that the various implementation methods / embodiments involved in the embodiments of the present disclosure can be used in conjunction with the aforementioned embodiments or can be used independently. Whether used alone or in conjunction with the aforementioned embodiments, the implementation principles are similar. In the implementation of the present disclosure, some embodiments are described in terms of implementation methods used together. Of course, those skilled in the art will appreciate that such examples are not limitations on the embodiments of the present disclosure.

[0193] Based on the same concept, the embodiment of the present disclosure also provides an AI communication method.

[0194] FIG3a is a flow chart of an AI communication method according to an exemplary embodiment. As shown in FIG3a , the AI ​​communication method is executed by a network device. The AI ​​communication method includes the following steps:

[0195] In step S81, a processing time is determined, where the processing time is the time it takes for the terminal to switch the AI ​​model corresponding to the AI ​​function or model identifier.

[0196] In the AI ​​communication method provided in the embodiments of the present disclosure, AI function switching can be understood as switching between different AI functions. AI model switching corresponding to a model identifier can be understood as switching between AI models corresponding to different model identifiers. Among them, the AI ​​models corresponding to different model identifiers can be understood as different AI models under the same model identifier, or as different AI models corresponding to different model identifiers.

[0197] In the embodiments of the present disclosure, the scenarios in which the network device switches between different AI functions or AI models corresponding to different model identifiers are similar. Therefore, for scenarios in which the processing time for switching between different AI functions or AI models corresponding to different model identifiers is the same, please refer to the relevant description in the embodiments of the terminal device above, and no further details will be given here. In one implementation of the embodiments of the present disclosure, the processing time for switching between different AI functions or AI models corresponding to different model identifiers is the same.

[0198] In one embodiment of the present disclosure, the same processing time for switching between different AI functions may be predefined by a protocol. Alternatively, the same processing time for switching between different AI functions may be based on network device configuration. In one embodiment of the present disclosure, different AI functions or AI models corresponding to different model identifiers may have different processing times for switching.

[0199] FIG3b is a flow chart of another AI communication method according to an exemplary embodiment. In one embodiment of the present disclosure, as shown in FIG3b, the method includes the following steps:

[0200] In step S91, first information is received.

[0201] In an embodiment of the present disclosure, the first information is used to instruct the network device to determine the processing time for switching different AI functions or the processing time for switching AI models corresponding to different model identifiers.

[0202] In one implementation of an embodiment of the present disclosure, the first information may explicitly indicate the processing time for switching AI models corresponding to different AI functions or different model identifiers, or may implicitly indicate the processing time for switching AI models corresponding to different AI functions or different model identifiers.

[0203] In one implementation of the AI ​​communication method provided in the embodiments of the present disclosure, the first information includes processing time for switching between different AI functions or AI models corresponding to different model identifiers; and / or the first information includes an association relationship between switching between different AI functions or AI models corresponding to different model identifiers;

[0204] Among them, the processing time for switching between AI models corresponding to different AI functions or different model identifiers with associated relationships is different from the processing time for switching between AI models corresponding to different AI functions or different model identifiers without associated relationships.

[0205] It is understandable that the network device will pre-store the corresponding processing time mapping relationship between AI models corresponding to different functions or different model identifiers. Taking function switching as an example, when performing function switching, the terminal reports the AI ​​functions before and after the switch. When the network device receives the AI ​​functions before and after the switch reported by the terminal, it can determine the corresponding situation of the AI ​​function switch based on the mapping relationship (switching between AI functions with associated relationships or switching between AI functions without associated relationships), thereby determining the processing time.

[0206] It can be understood that for the switching of AI functions with associated relationships or the switching of model identifiers with associated relationships, since the switching process is not accompanied by the switching of AI models, the processing time of the switching of AI functions with associated relationships is less than the processing time of the switching of AI functions without associated relationships; the processing time of the switching of model identifiers with associated relationships is less than the processing time of the switching of AI functions without associated relationships.

[0207] It is understandable that in some scenarios, the processing time corresponding to the switching of associated AI functions and the switching of associated model identifiers may be 0.

[0208] In the embodiment of the present disclosure, the definition and description of the association relationship are similar to the definition and description of the association relationship in the terminal device. Therefore, the relevant description can refer to the description in the embodiment of the above-mentioned terminal device, and will not be repeated here.

[0209] In one implementation of the embodiments of the present disclosure, the method further includes: determining, based on the processing time, a time for performing an AI communication operation based on the AI ​​model corresponding to the switched AI function or model identifier; and performing an AI communication operation with the terminal based on the AI ​​model corresponding to the switched AI function or model identifier during the communication operation time. The communication operation time is the time for the AI ​​communication operation determined based on the processing time.

[0210] In the embodiment of the present disclosure, the processing time may be the processing time reported by the terminal or the processing time determined by the network device.

[0211] In one implementation of the embodiment of the present disclosure, the method further includes: determining an interruption time based on the processing time, where the interruption time is used to indicate a time when the terminal cannot perform AI communication.

[0212] In one implementation of the embodiments of the present disclosure, the terminal being unable to perform AI communication includes: the terminal communicating based on a non-AI mode; or the terminal discarding an uncompleted AI operation of the AI ​​model corresponding to the AI ​​function or model identifier before switching.

[0213] In one implementation of the embodiment of the present disclosure, the method further includes: sending a switching instruction, where the switching instruction is used to instruct the terminal to determine the AI ​​model corresponding to the switching AI function or model identifier.

[0214] In one implementation of the embodiments of the present disclosure, the switching of the AI ​​model corresponding to the AI ​​function or model identifier is determined based on a preset rule.

[0215] In one implementation of the embodiment of the present disclosure, the preset rule includes a change in RRC parameters.

[0216] It can be understood that the implementation process of the AI ​​communication method executed by the network device in the embodiment of the present disclosure is similar to that of the AI ​​communication method executed by the terminal device. The similarities will not be repeated here. Please refer to the implementation process of the AI ​​communication method executed by the terminal device mentioned above.

[0217] Based on the same concept, embodiments of the present disclosure also provide an AI communication system. The AI ​​communication system includes a terminal device and a network device. The terminal device and the network device interact to implement an AI communication method.

[0218] Figure 4 is a schematic diagram of a method interaction of an AI communication system shown in an exemplary embodiment of the present disclosure. As shown in Figure 4, the embodiment of the present disclosure relates to an AI communication system, and the above method includes:

[0219] Step S101: Determine processing time.

[0220] In one embodiment, the processing time is the time for switching the AI ​​model corresponding to the AI ​​function or model identifier.

[0221] In one implementation, different AI functions or AI models corresponding to different model identifiers have the same processing time for switching.

[0222] In one embodiment, the processing time is predefined based on a protocol; or the processing time is based on a network device configuration.

[0223] In one implementation, different AI functions or AI models corresponding to different model identifiers have different processing times for switching.

[0224] Step S102: Send the first information.

[0225] In one embodiment, the first information is the processing time for the network device to determine the AI ​​model corresponding to the switching AI function or model identifier.

[0226] In one embodiment, the first information may explicitly indicate the processing time for switching the AI ​​models corresponding to different AI functions or different model identifiers, or may implicitly indicate the processing time for switching the AI ​​models corresponding to different AI functions or different model identifiers.

[0227] Step S103: Determine the processing time.

[0228] In one implementation, based on the processing time reported by the terminal, the processing time for switching between different AI functions or the processing time for switching between AI models with different model identifiers is determined.

[0229] In one implementation, the network device may convert the processing time reported by the terminal to convert the processing time reported by the terminal into the time for communication processing between the terminal and the network device.

[0230] In one implementation, the processing time is the time it takes for the terminal to switch the AI ​​model corresponding to the AI ​​function or model identifier.

[0231] In one implementation, different AI functions or AI models corresponding to different model identifiers have the same processing time for switching.

[0232] In one embodiment, the processing time is predefined based on a protocol; or the processing time is based on a network device configuration.

[0233] In one implementation, different AI functions or AI models corresponding to different model identifiers have different processing times for switching.

[0234] Step S104: Send an instruction to instruct the terminal to perform the AI ​​operation time.

[0235] In one embodiment, the network device sends an instruction to instruct the terminal when to perform the AI ​​operation.

[0236] Step S105: Synchronize processing time.

[0237] In one embodiment, the terminal and the network device synchronize the processing time of switching different AI functions or the processing time of switching AI models with different model identifiers, so that the network device determines the time for performing AI communication operations based on the AI ​​model corresponding to the switched AI function or model identifier.

[0238] The positioning measurement method involved in the embodiments of the present disclosure may include at least one of steps S101 to S105. For example, step S101 can be implemented as an independent embodiment, step S103 can be implemented as an independent embodiment, step S101+step S102 can be implemented as an independent embodiment, and step S101+step S102+step S103 can be implemented as an independent embodiment, but are not limited thereto. In some embodiments, step S102 and step S103 can be exchanged in order or executed simultaneously, and step S101 and step S104 can be exchanged in order or executed simultaneously. In some embodiments, step S101, step S104, and step S105 are optional, and one or more of these steps can be omitted or replaced in different embodiments.

[0239] In the embodiments of the present disclosure, the implementation process involved in the AI ​​communication method executed by the network device is the same as or similar to the implementation process of the AI ​​communication method executed by the terminal. Based on this, for the processing process of network device related information, please refer to the relevant embodiments of the terminal mentioned above, and the embodiments of the present disclosure will not be repeated here.

[0240] The AI ​​communication method provided in the embodiments of the present disclosure is applicable to the implementation process of interaction between a terminal and a network device in a communication system.

[0241] Based on the same concept, an embodiment of the present disclosure provides a communication system, which includes a terminal and a network device that executes the above-mentioned AI communication method.

[0242] In the embodiments of the present disclosure, in the interaction scenario between the terminal and the network device, the relevant information processing process of the network device in the interaction scenario is the same or similar to that of the terminal in the interaction scenario. Based on this, the relevant information processing process of the network device in the interaction scenario can be referred to the relevant embodiments of the terminal above, and the embodiments of the present disclosure will not be repeated here.

[0243] Based on the same concept, an embodiment of the present disclosure also provides an AI communication device.

[0244] FIG5a is a structural block diagram of an AI communication device according to an exemplary embodiment, wherein the AI ​​communication device is executed by a terminal.

[0245] As shown in Figure 5a, an embodiment of the present disclosure provides an AI communication device, including: a processing unit 500, used to determine a processing time, where the processing time is the time for switching the AI ​​model corresponding to the AI ​​function or model identifier; based on the processing time, switching the AI ​​model corresponding to the AI ​​function or model identifier.

[0246] In one implementation, different AI functions or AI models corresponding to different model identifiers have the same processing time for switching.

[0247] In one embodiment, the processing time is predefined based on a protocol; or the processing time is based on a network device configuration.

[0248] In one implementation, different AI functions or AI models corresponding to different model identifiers have different processing times for switching.

[0249] Figure 5b is a block diagram of another AI communication device according to an exemplary embodiment. In one embodiment, as shown in Figure 5b, the AI ​​communication device further includes a sending unit 501, wherein the sending unit 501 is configured to send first information, where the first information is configured to instruct the network device to determine a processing time for switching the AI ​​function or AI model corresponding to the model identifier.

[0250] In one embodiment, the first information includes the processing time for switching between AI models corresponding to different AI functions or different model identifiers; and / or the first information includes the association relationship between the switching between AI models corresponding to different AI functions or different model identifiers; wherein, the processing time for switching between AI models corresponding to different AI functions or different model identifiers with an association relationship is different from the processing time for switching between AI models corresponding to different AI functions or different model identifiers without an association relationship.

[0251] In one embodiment, the processing unit 500 switches the AI ​​model corresponding to the AI ​​function or model identifier based on the processing time in the following manner: based on the processing time, determining the start time of AI communication of the AI ​​model corresponding to the switched AI function or model identifier.

[0252] In one embodiment, the processing unit 500 is also used to synchronize processing time with the network device; during the communication operation time, AI communication operations are performed with the network device based on the AI ​​model corresponding to the switched AI function or model identifier, and the communication operation time is the time for AI communication operations determined based on the processing time.

[0253] In one embodiment, the processing unit 500 is further configured to determine an interruption time based on the processing time, where the interruption time is a time during which the terminal cannot perform AI communication.

[0254] In one implementation, during the interruption time, the terminal communicates based on a non-AI mode; or the terminal discards an unfinished AI operation of the AI ​​model corresponding to the AI ​​function or model identifier before switching.

[0255] Figure 5c is a block diagram of another AI communication device according to an exemplary embodiment. In one embodiment, the AI ​​communication device shown in Figure 5c further includes a receiving unit, wherein the receiving unit 502 is further configured to receive a switching instruction, the switching instruction being configured to instruct the terminal to switch the AI ​​function or AI model corresponding to the model identifier.

[0256] In one embodiment, the processing unit 500 is further configured to determine the AI ​​model corresponding to the switching AI function or model identifier based on a preset rule.

[0257] In one implementation, the preset rule includes a change in an RRC parameter.

[0258] Based on the same concept, an embodiment of the present disclosure also provides an AI communication device.

[0259] FIG5 d is a structural block diagram of an AI communication device according to an exemplary embodiment, wherein the AI ​​communication device is executed by a network device.

[0260] As shown in FIG5d , an embodiment of the present disclosure provides an AI communication device, including: a processing unit 503, configured to determine a processing time, where the processing time is the time for a terminal to switch an AI model corresponding to an AI function or model identifier.

[0261] In one implementation, different AI functions or AI models corresponding to different model identifiers have the same processing time for switching.

[0262] In one embodiment, the processing time is predefined based on a protocol; or the processing time is based on a network device configuration.

[0263] In one implementation, different AI functions or AI models corresponding to different model identifiers have different processing times for switching.

[0264] Figure 5e is a block diagram of another AI communication device according to an exemplary embodiment. In one embodiment, the AI ​​communication device further includes a receiving unit, wherein the receiving unit 504 is configured to receive first information, the first information being configured to instruct the network device to determine a processing time for switching the AI ​​function or AI model corresponding to the model identifier.

[0265] In one embodiment, the first information includes the processing time for switching between AI models corresponding to different AI functions or different model identifiers; and / or the first information includes the association relationship between the switching between AI models corresponding to different AI functions or different model identifiers; wherein, the processing time for switching between AI models corresponding to different AI functions or different model identifiers with an association relationship is different from the processing time for switching between AI models corresponding to different AI functions or different model identifiers without an association relationship.

[0266] In one embodiment, the processing unit 503 is further used to determine, based on the processing time, a time for performing an AI communication operation based on the AI ​​model corresponding to the switched AI function or model identifier; and during the communication operation time, perform an AI communication operation with the terminal based on the AI ​​model corresponding to the switched AI function or model identifier, wherein the communication operation time is the time for the AI ​​communication operation determined based on the processing time.

[0267] In one implementation, the processing unit 503 is further configured to determine an interruption time based on the processing time, where the interruption time is used to indicate a time during which the terminal is unable to perform AI communication.

[0268] In one implementation, the terminal being unable to perform AI communication includes: the terminal communicating based on a non-AI mode; or the terminal discarding an uncompleted AI operation of the AI ​​model corresponding to the AI ​​function or model identifier before switching.

[0269] Figure 5f is a block diagram of another AI communication device according to an exemplary embodiment. In one embodiment, as shown in Figure 5f, the AI ​​communication device further includes a sending unit 505, which is configured to send a switching instruction, wherein the switching instruction is configured to instruct the terminal to determine whether to switch the AI ​​function or the AI ​​model corresponding to the model identifier.

[0270] In one embodiment, the processing unit is further configured to: determine the AI ​​model corresponding to the switching AI function or model identifier based on a preset rule;

[0271] .

[0272] In one embodiment, the preset rule includes a change in a radio resource control (RRC) parameter. FIG6 is a block diagram of a communication apparatus 600 according to an exemplary embodiment. For example, apparatus 600 may be a mobile phone, a computer, a digital broadcast terminal, a messaging device, a game console, a tablet device, a medical device, a fitness device, a personal digital assistant, or the like.

[0273] 6 , apparatus 600 may include one or more of the following components: a processing component 602 , a memory 604 , a power component 606 , a multimedia component 608 , an audio component 610 , an input / output (I / O) interface 612 , a sensor component 614 , and a communication component 616 .

[0274] The processing component 602 generally controls the overall operation of the device 600, such as operations associated with display, phone calls, data communications, camera operation, and recording operations. The processing component 602 may include one or more processors 620 to execute instructions to perform all or part of the steps of the above-described method. In addition, the processing component 602 may include one or more modules to facilitate interaction between the processing component 602 and other components. For example, the processing component 602 may include a multimedia module to facilitate interaction between the multimedia component 608 and the processing component 602.

[0275] The memory 604 is configured to store various types of data to support the operations of the device 600. Examples of such data include instructions for any application or method operating on the device 600, contact data, phone book data, messages, pictures, videos, etc. The memory 604 can be implemented by any type of volatile or non-volatile storage device, or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk, or optical disk.

[0276] The power component 606 provides power to the various components of the device 600. The power component 606 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power to the device 600.

[0277] The multimedia component 608 includes a screen that provides an output interface between the device 600 and the user. In some embodiments, the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen can be implemented as a touch screen to receive input signals from the user. The touch panel includes one or more touch sensors to sense touches, slides, and gestures on the touch panel. The touch sensor can not only sense the boundaries of the touch or slide action, but also detect the duration and pressure associated with the touch or slide operation. In some embodiments, the multimedia component 608 includes a front camera and / or a rear camera. When the device 600 is in an operating mode, such as a shooting mode or a video mode, the front camera and / or the rear camera can receive external multimedia data. Each front camera and rear camera can be a fixed optical lens system or have focal length and optical zoom capabilities.

[0278] The audio component 610 is configured to output and / or input audio signals. For example, the audio component 610 includes a microphone (MIC), which is configured to receive external audio signals when the device 600 is in an operating mode, such as a call mode, a recording mode, and a voice recognition mode. The received audio signal can be further stored in the memory 604 or transmitted via the communication component 616. In some embodiments, the audio component 610 also includes a speaker for outputting audio signals.

[0279] I / O interface 612 provides an interface between processing component 602 and peripheral interface modules, such as a keyboard, click wheel, buttons, etc. These buttons may include but are not limited to: a home button, volume buttons, a start button, and a lock button.

[0280] The sensor assembly 614 includes one or more sensors for providing various aspects of the status assessment of the device 600. For example, the sensor assembly 614 can detect the open / closed state of the device 600, the relative positioning of components, such as the display and keypad of the device 600. The sensor assembly 614 can also detect changes in the position of the device 600 or a component of the device 600, the presence or absence of user contact with the device 600, the orientation or acceleration / deceleration of the device 600, and temperature changes of the device 600. The sensor assembly 614 may include a proximity sensor configured to detect the presence of nearby objects without any physical contact. The sensor assembly 614 may also include an optical sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor assembly 614 may also include an accelerometer, a gyroscope, a magnetic sensor, a pressure sensor, or a temperature sensor.

[0281] The communication component 616 is configured to facilitate wired or wireless communication between the device 600 and other devices. The device 600 can access a wireless network based on a communication standard, such as WiFi, 2G or 3G, or a combination thereof. In an exemplary embodiment, the communication component 616 receives a broadcast signal or broadcast-related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 616 also includes a near field communication (NFC) module to facilitate short-range communication. For example, the NFC module can be implemented based on radio frequency identification (RFID) technology, infrared data association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology and other technologies.

[0282] In an exemplary embodiment, the apparatus 600 may be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the above-described method.

[0283] In an exemplary embodiment, a non-transitory computer-readable storage medium including instructions is also provided, such as a memory 604 including instructions, which can be executed by the processor 620 of the apparatus 600 to perform the above method. For example, the non-transitory computer-readable storage medium can be a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, etc.

[0284] FIG7 is a block diagram illustrating an apparatus 700 for communication, according to an exemplary embodiment. For example, apparatus 700 may be provided as a network device. Referring to FIG7 , apparatus 700 includes a processing component 722, which further includes one or more processors, and memory resources represented by memory 732 for storing instructions, such as applications, executable by processing component 722. The applications stored in memory 732 may include one or more modules, each corresponding to a set of instructions. Furthermore, processing component 722 is configured to execute the instructions to perform the aforementioned method.

[0285] The device 700 may also include a power supply component 726 configured to perform power management of the device 700, a wired or wireless network interface 750 configured to connect the device 700 to a network, and an input / output (I / O) interface 758. The device 700 may operate based on an operating system stored in the memory 732, such as Windows Server™, Mac OS X™, Unix™, Linux™, FreeBSD™, or the like.

[0286] In an exemplary embodiment, a non-transitory computer-readable storage medium including instructions is also provided, such as a memory 732 including instructions, which can be executed by the processing component 722 of the apparatus 700 to perform the above method. For example, the non-transitory computer-readable storage medium can be a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, etc.

[0287] The present disclosure provides an artificial intelligence communication method, device, and storage medium. In some embodiments, the terms "communication method," "information processing method," and "communication method" are interchangeable; the terms "communication device," "information processing device," and "information processing system" are interchangeable; and the terms "information processing system," "communication system," and "communication system" are interchangeable.

[0288] The embodiments of the present disclosure are not exhaustive and are merely illustrative of some embodiments, and are not intended to be a specific limitation on the scope of protection of the present disclosure. In the absence of contradiction, each step in a certain embodiment can be implemented as an independent embodiment, and the steps can be arbitrarily combined. For example, a solution after removing some steps in a certain embodiment can also be implemented as an independent embodiment, and the order of the steps in a certain embodiment can be arbitrarily exchanged. In addition, the optional implementation methods in a certain embodiment can be arbitrarily combined; in addition, the embodiments can be arbitrarily combined. For example, some or all steps of different embodiments can be arbitrarily combined, and a certain embodiment can be arbitrarily combined with the optional implementation methods of other embodiments.

[0289] In the various embodiments of the present disclosure, unless otherwise specified or logically conflicting, the terms and / or descriptions between the various embodiments are consistent and can be referenced from each other. The technical features of different embodiments can be combined to form new embodiments based on their inherent logical relationships. The terms used in the embodiments of the present disclosure are only for the purpose of describing specific embodiments and are not intended to limit the present disclosure.

[0290] It is further understood that in the present disclosure, "plurality" refers to two or more than two, and other quantifiers are similar. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. The character " / " generally indicates that the related objects before and after are in an "or" relationship. The singular forms "a", "the" and "the" are also intended to include the plural forms, unless the context clearly indicates otherwise.

[0291] It is further understood that the meanings of words such as "in response to" and "if" involved in this disclosure depend on the context and the actual usage scenario. For example, the word "in response to" used herein can be interpreted as "at..." or "when..." or "if".

[0292] It will be further understood that the terms "first," "second," and the like are used to describe various types of information, but such information should not be limited to these terms. These terms are used solely to distinguish information of the same type from one another and do not indicate a particular order or level of importance. In fact, the terms "first," "second," and the like are fully interchangeable. For example, first information could be referred to as second information, and similarly, second information could be referred to as first information without departing from the scope of this disclosure.

[0293] It is further understood that although operations are described in a particular order in the drawings in the embodiments of the present disclosure, this should not be construed as requiring that the operations be performed in the particular order shown or in a serial order, or that all of the operations shown be performed to obtain the desired results. In certain circumstances, multitasking and parallel processing may be advantageous.

[0294] Those skilled in the art will readily appreciate other embodiments of the present disclosure after considering the specification and practicing the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the present disclosure that follow the general principles of the present disclosure and include common knowledge or customary techniques in the art not disclosed herein.

[0295] It should be understood that the present disclosure is not limited to the exact structures described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the scope of the appended claims.

Claims

1. An artificial intelligence (AI) communication method, characterized in that: Executed by a terminal, the method includes: Determine a processing time, where the processing time is the time for performing an AI model switch corresponding to the AI ​​function or model identifier; Based on the processing time, the AI ​​model corresponding to the AI ​​function or model identifier is switched.

2. The method according to claim 1, characterized in that: The processing time for switching AI models corresponding to different AI functions or different model identifiers is the same.

3. The method according to claim 2, characterized in that The processing time is predefined based on a protocol; or the processing time is based on a network device configuration.

4. The method according to claim 1, characterized in that: The processing time for switching AI models corresponding to different AI functions or different model identifiers is different.

5. The method according to claim 4, characterized in that The method comprises: Sending first information, wherein the first information is used to instruct the network device to determine the processing time of the AI ​​model corresponding to the switching AI function or model identifier.

6. The method according to claim 5, characterized in that The first information includes processing time for switching AI models corresponding to different AI functions or different model identifiers; and / or The first information includes an association relationship between switching of AI models corresponding to different AI functions or different model identifiers; Among them, the processing time for switching between AI models corresponding to different AI functions or different model identifiers with associated relationships is different from the processing time for switching between AI models corresponding to different AI functions or different model identifiers without associated relationships.

7. The method according to any one of claims 1 to 6, characterized in that: The switching of the AI ​​model corresponding to the AI ​​function or model identifier based on the processing time includes: Based on the processing time, a start time for AI communication of the AI ​​model corresponding to the switched AI function or model identifier is determined.

8. The method according to any one of claims 1 to 6, characterized in that The method further comprises: synchronizing the processing time with a network device; During the communication operation time, AI communication operation is performed with the network device based on the AI ​​model corresponding to the switched AI function or model identifier, and the communication operation time is the time for the AI ​​communication operation determined based on the processing time.

9. The method according to any one of claims 1 to 8, characterized in that The method further comprises: Based on the processing time, an interruption time is determined, where the interruption time is a time during which the terminal cannot perform AI communication.

10. The method according to claim 9, characterized in that During the interruption time, the terminal communicates based on the non-AI mode; or the terminal discards the unfinished AI operation of the AI ​​model corresponding to the AI ​​function or model identifier before switching.

11. The method according to any one of claims 1 to 10, characterized in that The method further comprises: A switching instruction is received, where the switching instruction is used to instruct the terminal to switch the AI ​​function or the AI ​​model corresponding to the model identifier.

12. The method according to any one of claims 1 to 10, characterized in that The method further comprises: Determine the AI ​​model corresponding to the switching AI function or model identifier based on preset rules.

13. The method according to claim 12, characterized in that The preset rule includes a change in a radio resource control (RRC) parameter.

14. An artificial intelligence (AI) communication method, characterized in that: Executed by a network device, the method includes: Determine a processing time, where the processing time is the time it takes for the terminal to switch the AI ​​model corresponding to the AI ​​function or model identifier.

15. The method according to claim 14, characterized in that The processing time for switching AI models corresponding to different AI functions or different model identifiers is the same.

16. The method according to claim 15, characterized in that The processing time is predefined based on a protocol; or the processing time is based on a network device configuration.

17. The method according to claim 14, characterized in that The processing time for switching AI models corresponding to different AI functions or different model identifiers is different.

18. The method according to claim 17, characterized in that The method comprises: Receive first information, where the first information is used to instruct the network device to determine a processing time for switching an AI model corresponding to an AI function or model identifier.

19. The method according to claim 18, characterized in that The first information includes processing time for switching AI models corresponding to different AI functions or different model identifiers; and / or The first information includes an association relationship between switching of AI models corresponding to different AI functions or different model identifiers; Among them, the processing time for switching between AI models corresponding to different AI functions or different model identifiers with associated relationships is different from the processing time for switching between AI models corresponding to different AI functions or different model identifiers without associated relationships.

20. The method according to any one of claims 14 to 19, characterized in that The method further comprises: Based on the processing time, determine to perform AI based on the AI ​​model corresponding to the switched AI function or model identifier. the timing of the communication operation; During the communication operation time, AI communication operation is performed with the terminal based on the AI ​​model corresponding to the switched AI function or model identifier, and the communication operation time is the time for AI communication operation determined based on the processing time.

21. The method according to any one of claims 14 to 20, characterized in that The method further comprises: Based on the processing time, an interruption time is determined, where the interruption time is used to indicate a time when the terminal cannot perform AI communication.

22. The method according to claim 21, characterized in that The terminal cannot perform AI communication including: The terminal communicates based on the non-AI mode; or the terminal discards the unfinished AI operation of the AI ​​model corresponding to the AI ​​function or model identifier before switching.

23. The method according to any one of claims 14 to 22, characterized in that The method further comprises: Send a switching instruction, where the switching instruction is used to instruct the terminal to determine the AI ​​model corresponding to the switching AI function or model identifier.

24. The method according to any one of claims 14 to 23, characterized in that The switching of the AI ​​model corresponding to the AI ​​function or model identifier is determined based on preset rules.

25. The method according to claim 24, characterized in that The preset rule includes a change in a radio resource control (RRC) parameter.

26. An artificial intelligence (AI) communication device, characterized in that: Executed by a terminal, the device includes: A processing unit is used to determine a processing time, where the processing time is the time for switching the AI ​​model corresponding to the AI ​​function or model identifier; based on the processing time, switching the AI ​​model corresponding to the AI ​​function or model identifier.

27. An artificial intelligence (AI) communication device, characterized in that: Executed by a network device, the apparatus comprises: The processing unit is used to determine the processing time, where the processing time is the time for the terminal to switch the AI ​​model corresponding to the AI ​​function or model identifier.

28. An artificial intelligence (AI) communication device, characterized in that: include: processor; a memory for storing processor-executable instructions; The processor is configured to execute the method as described in any one of claims 1-13 or 14-25.

29. A storage medium, characterized in that: The storage medium stores instructions, and when the instructions in the storage medium are executed by the processor of the terminal, the terminal is enabled to execute the method described in any one of claims 1 to 13; or, when the instructions in the storage medium are executed by the processor of the network device, the network device is enabled to execute the method described in any one of claims 14 to 25.

Images