Communication method and device and storage medium

Abstract

The invention relates to a communication method and device and a storage medium. The communication method comprises the following steps: determining a processing duration corresponding to a first operation related to artificial intelligence AI model processing; according to the method and the device, the processing duration corresponding to the first operation related to AI model processing is determined, so that the terminal and the network equipment can be ensured to perform time alignment based on the processing duration. Therefore, the network equipment or the terminal calls the AI model deployed on the opposite terminal for corresponding processing after the processing duration, and the operation efficiency of the AI model is improved.

Description

Communication method, device and storage medium Technical Field

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

[0002] The widespread adoption of 5G technology is bringing profound changes to every aspect of our lives. According to the International Telecommunication Union (ITU), 5G will permeate every aspect of future society, building a comprehensive, user-centric information ecosystem. 5G technology can support advanced services like mobile virtual reality, massive IoT devices, meet the demanding requirements of connected vehicles and industrial control, and provide a superior user experience in high-speed rail environments. As a representative of new infrastructure, 5G will be central to building the future information society.

[0003] In recent years, artificial intelligence (AI) technology has achieved continuous breakthroughs in numerous fields. The continued development of fields such as intelligent voice and computer vision has not only brought a rich variety of applications to smart terminals, but has also found widespread application in education, transportation, home furnishings, healthcare, retail, security, and other fields. While bringing convenience to people's lives, it is also promoting industrial upgrading across various industries.

[0004] Summary of the Invention

[0005] To overcome the problems existing in the related art, the present disclosure provides a communication method, device and storage medium.

[0006] According to a first aspect of an embodiment of the present disclosure, a communication method is provided, which is executed by a terminal and includes: determining a processing time corresponding to a first operation related to AI model processing.

[0007] In some embodiments, the first operation includes at least one of the following: an operation for activating the AI ​​model; an operation for switching the AI ​​model; and an operation for shutting down the AI ​​model.

[0008] In some implementations, the first operations are different, and the processing durations corresponding to the first operations are different.

[0009] In some embodiments, the processing duration corresponding to the operation for activating the AI ​​model is greater than or equal to the processing duration corresponding to the operation for switching the AI ​​model; and / or, the processing duration corresponding to the operation for deactivating the AI ​​model is less than or equal to the processing duration corresponding to the operation for switching the AI ​​model.

[0010] In some implementations, the deployment method of the AI ​​model is different, and the processing time corresponding to the first operation is different.

[0011] In some embodiments, the AI ​​model is deployed on a terminal or a network device, and the processing time corresponding to the first operation is the first processing time; and, the AI ​​model is deployed on a terminal and a network device, and the processing time corresponding to the first operation is the second processing time; the processing times corresponding to the first operation are different, including: the first processing time is less than or equal to the second processing time.

[0012] In some implementations, the processing time corresponding to the first operation varies depending on the application scenario of the AI ​​model.

[0013] In some embodiments, the AI ​​models occupy different storage spaces, and the processing time corresponding to the first operation is different; or, the AI ​​models have different complexities, and the processing time corresponding to the first operation is different.

[0014] In some implementations, the capabilities corresponding to the terminals are different, and the processing durations corresponding to the first operations are different.

[0015] In some implementations, the method further includes: sending first information, where the first information is used to indicate a capability corresponding to the terminal and / or a processing duration corresponding to a first operation supported by the capability.

[0016] In some implementations, the terminal operation states corresponding to the terminals are different, and the processing durations corresponding to the first operations are different.

[0017] In some embodiments, the method further includes: sending second information, where the second information is used to indicate a terminal operating state corresponding to the terminal and / or a processing duration corresponding to a first operation supported by the terminal operating state.

[0018] In some embodiments, the method further includes: determining third information, where the third information is used to indicate an AI model deployed on a terminal and / or network device, and / or to indicate an application scenario of the AI ​​model.

[0019] In some embodiments, the method further includes: executing a second operation based on the processing time corresponding to the first operation, wherein the second operation is used to instruct the terminal to use an AI model method or a non-AI model method to process data, and the AI ​​model corresponding to the AI ​​model method is the AI ​​model after the terminal executes the first operation.

[0020] In some embodiments, the method also includes: receiving fourth information based on the processing time corresponding to the first operation, the fourth information is used to indicate the second operation, wherein the second operation is used to instruct the terminal to use an AI model method or a non-AI model method to process data, and the AI ​​model corresponding to the AI ​​model method is the AI ​​model after the terminal executes the first operation.

[0021] According to a second aspect of an embodiment of the present disclosure, a communication method is provided, which is executed by a network device and includes: determining a processing time corresponding to a first operation related to AI model processing.

[0022] In some embodiments, the first operation includes at least one of the following: an operation for activating the AI ​​model; an operation for switching the AI ​​model; and an operation for shutting down the AI ​​model.

[0023] In some implementations, the first operations are different, and the processing durations corresponding to the first operations are different.

[0024] In some embodiments, the processing duration corresponding to the operation for activating the AI ​​model is greater than or equal to the processing duration corresponding to the operation for switching the AI ​​model; and / or, the processing duration corresponding to the operation for deactivating the AI ​​model is less than or equal to the processing duration corresponding to the operation for switching the AI ​​model.

[0025] In some implementations, the deployment method of the AI ​​model is different, and the processing time corresponding to the first operation is different.

[0026] In some embodiments, the AI ​​model is deployed on a terminal or a network device, and the processing time corresponding to the first operation is the first processing time; and, the AI ​​model is deployed on a terminal and a network device, and the processing time corresponding to the first operation is the second processing time; the processing times corresponding to the first operation are different, including: the first processing time is less than or equal to the second processing time.

[0027] In some implementations, the processing time corresponding to the first operation varies depending on the application scenario of the AI ​​model.

[0028] In some embodiments, the AI ​​models occupy different storage spaces, and the processing time corresponding to the first operation is different; or, the AI ​​models have different complexities, and the processing time corresponding to the first operation is different.

[0029] In some implementations, the capabilities corresponding to the terminals are different, and the processing durations corresponding to the first operations are different.

[0030] In some embodiments, the method further includes: receiving first information, where the first information is used to indicate a capability corresponding to the terminal and / or a processing duration corresponding to a first operation supported by the capability.

[0031] In some implementations, the terminal operation states corresponding to the terminals are different, and the processing durations corresponding to the first operations are different.

[0032] In some embodiments, the method further includes: receiving second information, where the second information is used to indicate a terminal operating state corresponding to the terminal and / or a processing duration corresponding to a first operation supported by the terminal operating state.

[0033] In some embodiments, the method further includes: determining third information, where the third information is used to indicate an AI model deployed on a terminal and / or network device, and / or to indicate an application scenario of the AI ​​model.

[0034] In some embodiments, the method also includes: performing a second operation based on the processing time corresponding to the first operation, wherein the second operation is used to instruct the network device to use an AI model method or a non-AI model method to process data, and the AI ​​model corresponding to the AI ​​model method is the AI ​​model after the network device performs the first operation.

[0035] In some embodiments, the method also includes: receiving fourth information based on the processing time corresponding to the first operation, the fourth information is used to indicate the second operation, wherein the second operation is used to instruct the network device to use an AI model method or a non-AI model method to process data, and the AI ​​model corresponding to the AI ​​model method is the AI ​​model after the network device performs the first operation.

[0036] According to a third aspect of an embodiment of the present disclosure, a communication device is provided, which is configured in a terminal and includes: a processing module for determining a processing time corresponding to a first operation related to AI model processing.

[0037] In some embodiments, the first operation includes at least one of the following: an operation for activating the AI ​​model; an operation for switching the AI ​​model; and an operation for shutting down the AI ​​model.

[0038] In some implementations, the first operations are different, and the processing durations corresponding to the first operations are different.

[0039] In some embodiments, the processing duration corresponding to the operation for activating the AI ​​model is greater than or equal to the processing duration corresponding to the operation for switching the AI ​​model; and / or, the processing duration corresponding to the operation for deactivating the AI ​​model is less than or equal to the processing duration corresponding to the operation for switching the AI ​​model.

[0040] In some implementations, the deployment method of the AI ​​model is different, and the processing time corresponding to the first operation is different.

[0041] In some embodiments, the AI ​​model is deployed on a terminal or a network device, and the processing time corresponding to the first operation is the first processing time; and, the AI ​​model is deployed on a terminal and a network device, and the processing time corresponding to the first operation is the second processing time; the processing times corresponding to the first operation are different, including: the first processing time is less than or equal to the second processing time.

[0042] In some implementations, the processing time corresponding to the first operation varies depending on the application scenario of the AI ​​model.

[0043] In some embodiments, the AI ​​models occupy different storage spaces, and the processing time corresponding to the first operation is different; or, the AI ​​models have different complexities, and the processing time corresponding to the first operation is different.

[0044] In some implementations, the capabilities corresponding to the terminals are different, and the processing durations corresponding to the first operations are different.

[0045] In some embodiments, the apparatus further includes: a sending module configured to send first information, where the first information is used to indicate a capability corresponding to the terminal and / or a processing duration corresponding to a first operation supported by the capability.

[0046] In some implementations, the terminal operation states corresponding to the terminals are different, and the processing durations corresponding to the first operations are different.

[0047] In some embodiments, the apparatus further includes: a sending module configured to send second information, where the second information is used to indicate a terminal operating state corresponding to the terminal and / or a processing duration corresponding to a first operation supported by the terminal operating state.

[0048] In some embodiments, the processing module is further used to determine third information, where the third information is used to indicate an AI model deployed on a terminal and / or network device, and / or to indicate an application scenario of the AI ​​model.

[0049] In some embodiments, the processing module is also used to: execute a second operation based on the processing time corresponding to the first operation, wherein the second operation is used to instruct the terminal to use an AI model method or a non-AI model method to process data, and the AI ​​model corresponding to the AI ​​model method is the AI ​​model after the terminal executes the first operation.

[0050] In some embodiments, the device also includes: a receiving module for receiving fourth information based on the processing time corresponding to the first operation, the fourth information is used to indicate the second operation, wherein the second operation is used to instruct the terminal to use an AI model method or a non-AI model method to process data, and the AI ​​model corresponding to the AI ​​model method is the AI ​​model after the terminal executes the first operation.

[0051] According to a fourth aspect of an embodiment of the present disclosure, a communication device is provided, which is configured in a network device and includes: a processing module for determining a processing time corresponding to a first operation related to AI model processing.

[0052] In some embodiments, the first operation includes at least one of the following: an operation for activating the AI ​​model; an operation for switching the AI ​​model; and an operation for shutting down the AI ​​model.

[0053] In some implementations, the first operations are different, and the processing durations corresponding to the first operations are different.

[0054] In some embodiments, the processing duration corresponding to the operation for activating the AI ​​model is greater than or equal to the processing duration corresponding to the operation for switching the AI ​​model; and / or, the processing duration corresponding to the operation for deactivating the AI ​​model is less than or equal to the processing duration corresponding to the operation for switching the AI ​​model.

[0055] In some implementations, the deployment method of the AI ​​model is different, and the processing time corresponding to the first operation is different.

[0056] In some embodiments, the AI ​​model is deployed on a terminal or a network device, and the processing time corresponding to the first operation is the first processing time; and, the AI ​​model is deployed on a terminal and a network device, and the processing time corresponding to the first operation is the second processing time; the processing times corresponding to the first operation are different, including: the first processing time is less than or equal to the second processing time.

[0057] In some implementations, the processing time corresponding to the first operation varies depending on the application scenario of the AI ​​model.

[0058] In some embodiments, the AI ​​models occupy different storage spaces, and the processing time corresponding to the first operation is different; or, the AI ​​models have different complexities, and the processing time corresponding to the first operation is different.

[0059] In some implementations, the capabilities corresponding to the terminals are different, and the processing durations corresponding to the first operations are different.

[0060] In some embodiments, the apparatus further includes: a receiving module configured to receive first information, where the first information is used to indicate a capability corresponding to the terminal and / or a processing duration corresponding to a first operation supported by the capability.

[0061] In some implementations, the terminal operation states corresponding to the terminals are different, and the processing durations corresponding to the first operations are different.

[0062] In some embodiments, the apparatus further includes: a receiving module configured to receive second information, where the second information is used to indicate a terminal operating state corresponding to the terminal and / or a processing duration corresponding to a first operation supported by the terminal operating state.

[0063] In some embodiments, the processing module is further used to determine third information, where the third information is used to indicate an AI model deployed on a terminal and / or network device, and / or to indicate an application scenario of the AI ​​model.

[0064] In some embodiments, the processing module is also used to: execute a second operation based on the processing time corresponding to the first operation, wherein the second operation is used to instruct the network device to use an AI model method or a non-AI model method to process data, and the AI ​​model corresponding to the AI ​​model method is the AI ​​model after the network device executes the first operation.

[0065] In some embodiments, the device also includes: a receiving module for receiving fourth information based on the processing time corresponding to the first operation, the fourth information is used to indicate the second operation, wherein the second operation is used to instruct the network device to use an AI model method or a non-AI model method to process data, and the AI ​​model corresponding to the AI ​​model method is the AI ​​model after the network device performs the first operation.

[0066] According to a fifth aspect of an embodiment of the present disclosure, a communication device is provided, comprising: a processor; a memory for storing processor-executable instructions; wherein the processor is configured to: execute the first aspect and any one of the methods in the first aspect.

[0067] According to a sixth aspect of an embodiment of the present disclosure, a communication device is provided, comprising: a processor; a memory for storing processor-executable instructions; wherein the processor is configured to: execute the second aspect and any one of the methods in the second aspect.

[0068] According to the seventh aspect of the embodiment of the present disclosure, a communication system is provided, the system including: a terminal for executing the first aspect and any one of the methods in the first aspect; a network device for executing the second aspect and any one of the methods in the second aspect.

[0069] According to an eighth aspect of an embodiment of the present disclosure, a non-temporary computer-readable storage medium is provided. When the instructions in the storage medium are executed by a processor of a terminal, the terminal is enabled to execute the first aspect and any one of the methods in the first aspect.

[0070] According to the ninth aspect of the embodiment of the present disclosure, a non-temporary computer-readable storage medium is provided. When the instructions in the storage medium are executed by the processor of the network device, the network device can execute the second aspect and any one of the methods in the second aspect.

[0071] The technical solution provided by the embodiments of the present disclosure can achieve the following beneficial effects: by determining the processing duration corresponding to the first operation related to AI model processing, it is possible to ensure that the terminal and the network device are time-aligned based on the processing duration. This allows the network device or terminal to call the AI ​​model deployed on the other end to perform corresponding processing after the processing duration, thereby improving the operating efficiency of the AI ​​model.

[0072] 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

[0073] 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.

[0074] Fig. 1 is a schematic diagram of a wireless communication system according to an exemplary embodiment.

[0075] Fig. 2 is a flow chart showing a communication method according to an exemplary embodiment.

[0076] Fig. 3 is a flow chart showing another communication method according to an exemplary embodiment.

[0077] Fig. 4 is a flow chart showing another communication method according to an exemplary embodiment.

[0078] Fig. 5 is a flow chart showing yet another communication method according to an exemplary embodiment.

[0079] Fig. 6 is a flow chart showing another communication method according to an exemplary embodiment.

[0080] Fig. 7 is a flow chart showing yet another communication method according to an exemplary embodiment.

[0081] Fig. 8 is a flow chart showing yet another communication method according to an exemplary embodiment.

[0082] Fig. 9 is a flow chart showing another communication method according to an exemplary embodiment.

[0083] Fig. 10 is a schematic diagram showing a communication device according to an exemplary embodiment.

[0084] Fig. 11 is a schematic diagram showing another communication device according to an exemplary embodiment.

[0085] Fig. 12 is a schematic diagram showing a communication device according to an exemplary embodiment.

[0086] Fig. 13 is a schematic diagram of another communication device according to an exemplary embodiment. DETAILED DESCRIPTION

[0087] 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.

[0088] The communication method involved in the present disclosure can be applied to the wireless communication system 100 shown in Figure 1. The network system may include a network device 110 and a terminal 120. It will be understood that the wireless communication system shown in Figure 1 is merely for illustrative purposes, 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.

[0089] 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 FDMA (SC-FDMA), and Carrier Sense Multiple Access with Collision Avoidance. 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 the 5th Generation Wireless Communication System (5G) network. The 5G network 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.

[0090] Furthermore, the network device 110 involved in the present disclosure may also be referred to as a wireless access network device. The wireless access network device may be: a base station, an evolved Node B (eNB), 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 receiving 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. When it is a vehicle-to-everything (V2X) communication system, the network device may also be an on-board device. 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.

[0091] Furthermore, the terminal 120 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 may be a handheld device with wireless connection function, a vehicle-mounted device, etc. At present, some examples of terminals are: smart phones (Mobile Phones), pocket personal computers (PPCs), handheld computers, personal digital assistants (PDAs), laptop computers, tablet computers, wearable devices, or vehicle-mounted devices, etc. In addition, when it is a vehicle-to-everything (V2X) communication system, the terminal device may 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.

[0092] In the embodiments of the present disclosure, the network device 110 and the terminal 120 can use any feasible wireless communication technology to achieve mutual data transmission. The transmission channel corresponding to the transmission of data or control information from the network device 110 to the terminal 120 is called a downlink channel (DL), and the transmission channel corresponding to the transmission of data or control information from the terminal 120 to the network device 110 is called an uplink channel (UL). It is understood that the network device involved in the embodiments of the present disclosure can be a base station. Of course, the network device can also be any other possible network device, and the terminal can be any possible terminal, and this disclosure is not limited thereto.

[0093] The widespread application of 5G technology has brought about tremendous changes in all aspects of people's lives. According to the ITU's vision, 5G will penetrate all areas of future society and build a comprehensive information ecosystem centered on users. Among them, 5G user experience rates can reach 100Mbit / s to 1Gbit / s, which can support ultimate service experiences such as mobile virtual reality; 5G peak rates can reach 10Gbit / s to 20Gbit / s, and traffic density can reach 10Mbit / s / m2, which can support the future growth of mobile service traffic by more than a thousand times; 5G connection density can reach 1 million / m 2 , effectively supporting massive numbers of IoT devices; 5G transmission latency can reach milliseconds, meeting the stringent requirements of the Internet of Vehicles and industrial control; 5G can support mobile speeds of 500 km / h, providing a good user experience in high-speed rail environments. As a representative of new infrastructure, 5G will reshape the future information society.

[0094] In recent years, AI technology has achieved continuous breakthroughs in numerous fields. The continued development of fields like intelligent voice and computer vision has not only brought a rich variety of applications to mobile devices, but has also found widespread application in education, transportation, home furnishings, healthcare, retail, security, and other fields. While bringing convenience to people's lives, it is also promoting industrial upgrading across various industries. AI technology is also rapidly interpenetrating with other disciplines. Its development integrates knowledge from different disciplines while also providing new directions and methods for their development.

[0095] During Release 18 of the 3rd Generation Partnership Project (3GPP), a research project on artificial intelligence (AI) technology in the radio access network (RAN) 1 was established. This project aims to investigate how to integrate AI technology into the radio air interface and explore how AI can assist in improving transmission technologies within the radio air interface.

[0096] For example, in wireless AI research, application cases of artificial intelligence include:

[0097] -AI-based channel state information (CSI) enhancement

[0098] -AI-based beam management

[0099] -AI-based positioning

[0100] In some discussions, there are scenarios where the following models are associated:

[0101] Model activation refers to the transition from a non-AI model processing state to a state where an AI model is used for processing.

[0102] Model switching, switching from one AI model to another.

[0103] Falling back from AI model processing to non-AI model processing, such as traditional processing that does not utilize AI models.

[0104] AI models can also come in various types, such as unilateral and bilateral models. A unilateral model means all parts of the AI ​​model are deployed on the same device. This can be entirely deployed on the terminal or entirely deployed on the network device. A bilateral model means part of the AI ​​model is deployed on the terminal, while the rest is deployed on the network device. In other words, different parts of the same AI model can be deployed on different devices. In this case, the AI ​​model's inference calculations require collaboration between the terminal and the network device.

[0105] However, starting or shutting down an AI model requires starting the corresponding hardware and software. Network devices and terminals have no idea how long it might take from receiving a model management command to executing it.

[0106] Therefore, the present disclosure determines the processing duration corresponding to the first operation related to AI model processing, thereby ensuring that the terminal and the network device are time-aligned based on the processing duration. This allows the network device or terminal to call the AI ​​model deployed on the other end to perform corresponding processing after the processing duration, thereby improving the operating efficiency of the AI ​​model.

[0107] FIG2 is a flow chart showing a communication method according to an exemplary embodiment. As shown in FIG2 , the method is executed by a terminal, and the method may include the following steps:

[0108] In step S11, a processing duration corresponding to a first operation related to AI model processing is determined.

[0109] In some embodiments, the terminal may determine a first operation related to AI model processing. For example, the first operation may also be referred to as a target operation. It is understood that the first operation merely represents a name for an operation related to AI model processing, and this disclosure does not limit the name of the operation. The terminal determines the processing duration corresponding to the first operation.

[0110] For example, the terminal receives a first operation sent by a network device. The first operation may be an operation related to AI model processing. For another example, a user may trigger the first operation through an external device such as a touch screen or keyboard of the terminal, so that the terminal can determine the first operation.

[0111] When the terminal determines the first operation, it can determine the processing time corresponding to the first operation. It can be understood that the processing time can be considered as the time required for the terminal to perform the above-mentioned first operation. In other words, the terminal can complete the first operation within the above-mentioned processing time.

[0112] Of course, in some cases, the first operation may also be performed by the network device. Therefore, in this case, the processing duration corresponding to the first operation can be considered to be the duration required for the network device to perform the first operation. It can be considered that the network device can complete the first operation within the above processing duration. In this example, the terminal determines the duration corresponding to the first operation for the purpose of determining at what time the second operation can be sent to the network device, for example, the second operation is used to trigger the network device to perform the corresponding task or perform data processing using the AI ​​model or non-AI model after executing the first operation.

[0113] In some embodiments, the first operation may be, for example, an operation of activating an AI model, an operation of switching an AI model, and / or an operation of shutting down an AI model.

[0114] In some embodiments, the terminal may further include the following steps:

[0115] In step S12, a first operation is performed.

[0116] In some embodiments, the terminal may perform the above-mentioned operations related to AI model processing.

[0117] For example, the first operation is an operation indicating the activation of a certain AI model, such as an operation of activating an AI model, and the terminal can activate the relevant AI model.

[0118] For another example, the first operation is an operation instructing to switch from one AI model to another AI model. For example, the terminal may switch the AI ​​model. For example, if a first AI model is running on the terminal, the terminal may switch the first AI model to a second AI model based on the first operation, so that the terminal can subsequently run the second AI model. It is understood that the second AI model is an AI model different from the first AI model.

[0119] For another example, the first operation is an operation to instruct to shut down a certain AI model, such as an operation to shut down the AI ​​model. The terminal can shut down the running AI model based on the first operation, so that the terminal can subsequently use a non-AI model method to perform corresponding data processing or execute certain tasks.

[0120] In step S13, after the processing time, a second operation is performed.

[0121] In some embodiments, after the processing time, the terminal may perform a second operation, wherein the second operation may be an operation of performing corresponding data processing using an AI model.

[0122] It can be understood that the above processing time is to ensure that the terminal can complete the execution of the first operation. Therefore, after the processing time, the first operation can be considered to have been completed. For example, after the processing time, the terminal can be considered to have completed the first operation. The terminal can receive a second operation, such as a second operation sent by a network device. The second operation can instruct the terminal to perform the corresponding task or perform data processing using the AI ​​model or non-AI model after executing the first operation. For example, if the first operation is an operation to activate the AI ​​model, the terminal can use the activated AI model to perform the corresponding task. For another example, if the first operation is an operation to switch the AI ​​model, the terminal can use the switched AI model to perform the corresponding task. For another example, if the first operation is an operation to shut down the AI ​​model, the terminal can use a non-AI model to perform the corresponding task.

[0123] Of course, if the AI ​​model is deployed on a network device, the terminal can determine that the network device has completed the first operation based on the above processing time. The terminal can send information indicating a second operation to the network device, and the second operation can be used to instruct the network device to perform the corresponding task or perform data processing using the AI ​​model or non-AI model after executing the first operation.

[0124] The present disclosure determines the processing duration corresponding to the first operation related to AI model processing, thereby ensuring that the terminal and the network device are time-aligned based on the processing duration. This allows the network device or terminal to call the AI ​​model deployed on the other end to perform corresponding processing after the processing duration, thereby improving the operating efficiency of the AI ​​model.

[0125] In the communication method provided by the embodiment of the present disclosure, the first operation includes at least one of the following: an operation for activating the AI ​​model; an operation for switching the AI ​​model; and an operation for shutting down the AI ​​model.

[0126] In some embodiments, the first operation related to AI model processing includes an operation for activating the AI ​​model.

[0127] It is understandable that the first operation can be used to activate a certain AI model. Activating an AI model can be understood as starting a certain AI model.

[0128] In some embodiments, the first operation related to AI model processing includes an operation for switching the AI ​​model.

[0129] It is understandable that the first operation can be used to switch the first AI model to the second AI model, wherein the first AI model can be any AI model, and the second AI model can be another AI model different from the first AI model.

[0130] In some embodiments, the first operation related to AI model processing includes an operation for shutting down the AI ​​model.

[0131] It is understandable that the first operation can be used to shut down a certain AI model, wherein the shut down AI model cannot be used.

[0132] In some embodiments, the first operation related to AI model processing includes: an operation for activating the AI ​​model, an operation for switching the AI ​​model. Alternatively, an operation for activating the AI ​​model, an operation for deactivating the AI ​​model. Alternatively, an operation for switching the AI ​​model, an operation for deactivating the AI ​​model. Alternatively, an operation for activating the AI ​​model, an operation for switching the AI ​​model, an operation for deactivating the AI ​​model.

[0133] The present disclosure provides a variety of first operations related to AI model processing to determine the processing duration corresponding to the operation, thereby ensuring that the terminal and network device are time-aligned based on the processing duration. This allows the network device or terminal to call the AI ​​model deployed on the other end after the processing duration to perform corresponding processing, thereby improving the operating efficiency of the AI ​​model.

[0134] In the communication method provided by the embodiment of the present disclosure, the first operation is different, and the processing time corresponding to the first operation is different.

[0135] In some embodiments, different first operations may correspond to different processing durations. In other words, different first operations performed by the terminal may correspond to different processing durations.

[0136] For example, the first operation is to activate the AI ​​model. The terminal needs to switch from a non-AI model processing mode to an AI model-based processing mode, and needs to load the software and hardware environment related to the AI ​​model. Therefore, it takes a certain amount of processing time to complete the first operation, that is, to activate the AI ​​model.

[0137] For example, the first operation involves switching AI models. The terminal needs to switch from the processing mode of the first AI model to the processing mode of the second AI model. The software and hardware environments associated with the second AI model need to be loaded, and the software and hardware environments associated with the first AI model need to be closed. Therefore, a certain amount of processing time is required to complete the first operation, i.e., switching AI models.

[0138] For example, the first operation is to disable the AI ​​model. The terminal needs to switch from an AI-based processing mode to a non-AI model processing mode. The software and hardware environments related to the AI ​​model need to be shut down. Therefore, it takes a certain amount of processing time to complete the first operation, that is, to disable the AI ​​model.

[0139] Of course, when the terminal performs the above-mentioned different first operations, since the operations required by the terminal to load and / or close the AI ​​model are different, the processing time required for different first operations is also different.

[0140] This disclosure determines different processing times for different first operations related to AI model processing. This ensures that the terminal and network device can be time-aligned based on different processing times for different operations. This allows the network device or terminal to invoke the AI ​​model deployed on the other end after the processing time, thereby improving the operating efficiency of the AI ​​model.

[0141] In the communication method provided by the embodiments of the present disclosure, the processing duration corresponding to the operation for activating the AI ​​model is greater than or equal to the processing duration corresponding to the operation for switching the AI ​​model; and / or, the processing duration corresponding to the operation for shutting down the AI ​​model is less than or equal to the processing duration corresponding to the operation for switching the AI ​​model.

[0142] In some embodiments, the processing duration corresponding to the operation for activating the AI ​​model is greater than or equal to the processing duration corresponding to the operation for switching the AI ​​model.

[0143] That is, the processing time for the terminal to activate the AI ​​model is longer than the processing time for switching the AI ​​model. Alternatively, the processing time for the terminal to activate the AI ​​model is equal to the processing time for switching the AI ​​model.

[0144] In some embodiments, the processing duration corresponding to the operation for shutting down the AI ​​model is less than or equal to the processing duration corresponding to the operation for switching the AI ​​model.

[0145] That is, the processing time for the terminal to shut down the AI ​​model is less than the processing time for switching the AI ​​model. Alternatively, the processing time for the terminal to shut down the AI ​​model is equal to the processing time for switching the AI ​​model.

[0146] This disclosure provides specific processing duration relationships for different first operations related to AI model processing. This ensures that terminals and network devices can time-align different operations based on different processing durations. This allows the network device or terminal to invoke the AI ​​model deployed on the other end after the processing duration, thereby improving the operating efficiency of the AI ​​model.

[0147] In the communication method provided in the embodiment of the present disclosure, the deployment method of the AI ​​model is different, and the processing time corresponding to the first operation is different.

[0148] In some embodiments, the deployment mode of the AI ​​model can be divided into unilateral deployment and bilateral deployment. Among them, unilateral deployment means that the AI ​​model is deployed on one device. For example, it can be deployed on a terminal or a network device. Bilateral deployment means that different parts of the AI ​​model can be deployed on different devices respectively. For example, the same AI model can be divided into two parts. One part of the AI ​​model can be deployed on the terminal, and the other part of the AI ​​model can be deployed on the network device. Of course, in some cases, one part of the AI ​​model can be deployed on terminal A, and the other part of the AI ​​model can be deployed on terminal B; or, one part of the AI ​​model can be deployed on network device A, and the other part of the AI ​​model can be deployed on network device B.

[0149] In some embodiments, the processing duration corresponding to the first operation involving a unilaterally deployed AI model may be different from the processing duration corresponding to the first operation involving a bilaterally deployed AI model.

[0150] For example, assuming that the first operation is to activate an AI model, the processing time corresponding to activating a unilaterally deployed AI model is different from the processing time corresponding to activating a bilaterally deployed AI model.

[0151] For another example, assuming that the first operation is an operation of switching AI models, the processing time corresponding to switching the unilaterally deployed AI model is different from the processing time corresponding to switching the bilaterally deployed AI model.

[0152] Of course, during the operation of switching AI models, the processing time corresponding to switching from a unilaterally deployed AI model to a bilaterally deployed AI model may be different from the processing time corresponding to switching from a bilaterally deployed AI model to a unilaterally deployed AI model.

[0153] For another example, assuming that the first operation is to shut down the AI ​​model, the processing time corresponding to shutting down the unilaterally deployed AI model is different from the processing time corresponding to shutting down the bilaterally deployed AI model.

[0154] This disclosure determines different processing times for different AI model deployment methods. This ensures that terminals and network devices can be time-aligned based on different processing times for different operations. This allows the network device or terminal to call the AI ​​model deployed on the other end for corresponding processing after the processing time, thereby improving the operating efficiency of the AI ​​model.

[0155] In the communication method provided by the embodiments of the present disclosure, the AI ​​model is deployed on a terminal or a network device, and the processing time corresponding to the first operation is the first processing time; and, the AI ​​model is deployed on a terminal and a network device, and the processing time corresponding to the first operation is the second processing time; the processing time corresponding to the first operation is different, including: the first processing time is less than or equal to the second processing time.

[0156] In some embodiments, the AI ​​model can be deployed on one device, for example, the same AI model is deployed on a terminal or a network device. The processing duration corresponding to the first operation is referred to as the first processing duration. The AI ​​model can also be deployed on multiple devices, for example, different parts of the same AI model are deployed on a terminal and a network device, respectively, or not on different terminals, or are deployed on different network devices. The processing duration corresponding to the first operation is referred to as the second processing duration.

[0157] In some embodiments, the first processing duration is less than the second processing duration.

[0158] For example, the processing time corresponding to operations related to unilaterally deployed AI model processing may be shorter than the processing time corresponding to operations related to bilaterally deployed AI model processing.

[0159] For example, the processing time corresponding to activating a unilaterally deployed AI model can be shorter than the processing time corresponding to activating a bilaterally deployed AI model.

[0160] For example, the processing time corresponding to switching a unilaterally deployed AI model can be shorter than the processing time corresponding to switching a bilaterally deployed AI model.

[0161] Of course, during the AI ​​model switching operation, the processing time corresponding to switching from a unilaterally deployed AI model to a bilaterally deployed AI model may be shorter than the processing time corresponding to switching from a bilaterally deployed AI model to a unilaterally deployed AI model. Alternatively, the processing time corresponding to switching from a unilaterally deployed AI model to a bilaterally deployed AI model may be longer than the processing time corresponding to switching from a bilaterally deployed AI model to a unilaterally deployed AI model.

[0162] For another example, the processing time corresponding to shutting down a unilaterally deployed AI model may be shorter than the processing time corresponding to shutting down a bilaterally deployed AI model.

[0163] In some embodiments, the first processing duration is equal to the second processing duration.

[0164] For example, the processing time corresponding to operations related to unilaterally deployed AI model processing can be equal to the processing time corresponding to operations related to bilaterally deployed AI model processing.

[0165] For example, the processing time corresponding to activating a unilaterally deployed AI model can be equal to the processing time corresponding to activating a bilaterally deployed AI model.

[0166] For example, the processing time corresponding to switching a unilaterally deployed AI model can be equal to the processing time corresponding to switching a bilaterally deployed AI model.

[0167] Of course, during the operation of switching AI models, the processing time corresponding to switching from a unilaterally deployed AI model to a bilaterally deployed AI model can be equal to the processing time corresponding to switching from a bilaterally deployed AI model to a unilaterally deployed AI model.

[0168] For another example, the processing time corresponding to shutting down a unilaterally deployed AI model can be equal to the processing time corresponding to shutting down a bilaterally deployed AI model.

[0169] This disclosure provides specific processing duration relationships for different AI model deployment methods. This ensures that terminals and network devices can be time-aligned based on different processing durations for different operations. This allows the network device or terminal to invoke the AI ​​model deployed on the other end after the processing duration, thereby improving the operating efficiency of the AI ​​model.

[0170] In the communication method provided in the embodiment of the present disclosure, the application scenarios of the AI ​​model are different, and the processing time corresponding to the first operation is different.

[0171] In some embodiments, the processing time corresponding to different first operations can be determined based on different application scenarios corresponding to the AI ​​model. It can be understood that different application scenarios of the AI ​​model can also be considered as different use cases of the AI ​​model.

[0172] Assuming that the use scenarios of the AI ​​model include beam prediction scenarios and definition scenarios, the processing time corresponding to the first operation in the beam prediction scenario may be different from the processing time corresponding to the first operation in the positioning scenario.

[0173] Of course, the use scenarios of the AI ​​model can also include CSI enhancement, etc. This disclosure does not limit the specific use scenarios of the AI ​​model, nor the number of use scenarios.

[0174] This disclosure determines different processing times for different AI model usage scenarios. This ensures that terminals and network devices can be time-aligned based on different processing times for different operations. This allows the network device or terminal to invoke the AI ​​model deployed on the other end for corresponding processing after the processing time, thereby improving the operating efficiency of the AI ​​model.

[0175] In the communication method provided by the embodiment of the present disclosure, the storage space occupied by the AI ​​model is different, and the processing time corresponding to the first operation is different; or, the complexity corresponding to the AI ​​model is different, and the processing time corresponding to the first operation is different.

[0176] In some embodiments, different AI models may occupy different storage spaces, in other words, the sizes of the AI ​​models may be different. Therefore, the processing time for performing the first operation on AI models of different sizes may be different.

[0177] For example, if the storage space occupied by the first AI model is larger than the storage space occupied by the second AI model, the processing time for performing the first operation on the first AI model may be greater than the processing time for performing the first operation on the second AI model.

[0178] In some embodiments, different AI models may correspond to different complexities, and the processing time for performing the first operation on AI models of different complexities may be different.

[0179] For example, if the complexity of the first AI model is greater than that of the second AI model, the processing time of performing the first operation on the first AI model may be greater than the processing time of performing the first operation on the second AI model.

[0180] In some embodiments, the complexity of the AI ​​model may or may not be related to the storage space occupied by the AI ​​model. For example, if the complexity of the AI ​​model is related to the storage space occupied by the AI ​​model, the higher the complexity of the AI ​​model, the larger the storage space occupied by the AI ​​model.

[0181] This disclosure can determine different processing times based on the different storage space occupied or complexity of AI models. This ensures that terminals and network devices can be time-aligned based on different processing times for different operations. This allows the network device or terminal to call the AI ​​model deployed on the other end after the processing time, thereby improving the operating efficiency of the AI ​​model.

[0182] In the communication method provided by the embodiment of the present disclosure, the capabilities corresponding to the terminals are different, and the processing duration corresponding to the first operation is different.

[0183] In some embodiments, different terminals may correspond to different capabilities. For example, terminals may include ordinary terminals and low-capability terminals. Terminals with different capabilities may have different processing times for executing the first operation. For example, terminal capabilities may include any possible capabilities, such as AI model processing capabilities, hardware capabilities, and software capabilities, and are not limited in this disclosure.

[0184] Among them, low-capability terminals can be called RedCap terminals.

[0185] For example, suppose that some terminals may execute the operations processed by the AI ​​model faster, while other terminals may take longer to execute the operations processed by the AI ​​model. Therefore, it can be considered that the capabilities of these terminals are different. Accordingly, the processing time corresponding to the first operation performed by terminals with different capabilities is also different.

[0186] It is understandable that different terminals may have different capabilities for different AI models.

[0187] For example, it can be assumed that there are a first terminal and a second terminal. The first terminal and the second terminal have different capabilities, so the processing time corresponding to the first terminal performing the operation related to the AI ​​model processing can be different from the processing time corresponding to the second terminal performing the operation related to the AI ​​model processing.

[0188] For another example, each terminal may have separate capabilities for different operations related to AI model processing. For example, the capability of a first terminal to activate an AI model differs from that of a second terminal. Therefore, the processing duration corresponding to the first terminal's operation to activate the AI ​​model may be different from that of the second terminal. It will be understood that different terminals may also have separate capabilities for switching AI models and shutting down AI models. For example, the capability of a first terminal to switch an AI model differs from that of a second terminal. Therefore, the processing duration corresponding to the first terminal's operation to switch an AI model may be different from that of the second terminal. For another example, the capability of a first terminal to shut down an AI model differs from that of a second terminal. Therefore, the processing duration corresponding to the first terminal's operation to shut down an AI model may be different from that of the second terminal.

[0189] For another example, each terminal may have separate capabilities depending on the deployment method of the AI ​​model. For example, the capability of the first terminal to execute a unilaterally deployed AI model is different from the capability of the second terminal to execute a unilaterally deployed AI model. And / or, the capability of the first terminal to execute a bilaterally deployed AI model is different from the capability of the second terminal to execute a bilaterally deployed AI model. Assuming that the capability of the first terminal is higher than that of the second terminal, it can be considered that the processing time of the unilaterally deployed AI model executed by the first terminal is less than the processing time of the unilaterally deployed AI model executed by the second terminal. And / or, the processing time of the bilaterally deployed AI model executed by the first terminal is less than the processing time of the bilaterally deployed AI model executed by the second terminal.

[0190] For another example, each terminal may have separate capabilities for different AI models, depending on the storage space or complexity. Assuming the capabilities of a first terminal are higher than those of a second terminal, then for AI models occupying the same storage space or having the same complexity, the processing time for the first terminal to execute the AI ​​model may be less than the processing time for the second terminal to execute the AI ​​model.

[0191] It can be understood that the higher the capability of a terminal is, the shorter the processing time corresponding to the operation of the terminal can be.

[0192] In some embodiments, the terminal may also have corresponding capabilities based on the configuration of any possible AI model, such as different application scenarios of the AI ​​model, which is not limited in this disclosure.

[0193] The present disclosure can determine different processing times for different terminal capabilities. This ensures that terminals and network devices can be time-aligned based on different processing times for different operations. This allows the network device or terminal to invoke the AI ​​model deployed on the other end after the processing time has expired to perform corresponding processing, thereby improving the operating efficiency of the AI ​​model.

[0194] In the communication method provided in the embodiment of the present disclosure, FIG3 is a flow chart of another communication method according to an exemplary embodiment. As shown in FIG3, the method may further include the following steps:

[0195] In step S21, the first information is sent.

[0196] In some embodiments, the terminal may send first information, wherein the first information is used to indicate a capability corresponding to the terminal and / or a processing duration corresponding to a first operation supported by the capability.

[0197] For example, the terminal sends first information indicating the capabilities of the terminal. A device receiving the first information, such as a network device, can determine the processing time corresponding to the terminal performing the first operation based on the capabilities of the terminal indicated in the first information.

[0198] For another example, a terminal sends first information indicating a processing duration corresponding to a first operation supported by a capability corresponding to the terminal. A device receiving the first information, such as a network device, can directly determine the processing duration corresponding to the terminal executing the first operation based on the first information.

[0199] For another example, a terminal sends first information indicating a capability corresponding to the terminal and a processing duration corresponding to a first operation supported by the capability. A device receiving the first information, such as a network device, can directly determine the processing duration corresponding to the terminal performing the first operation based on the first information.

[0200] The terminal disclosed herein can report its own capabilities and / or the processing time corresponding to the first operation corresponding to the capabilities, so that the network device can call the AI ​​model deployed on the terminal to perform corresponding processing after the processing time based on the information reported by the terminal, thereby improving the operating efficiency of the AI ​​model.

[0201] In the communication method provided by the embodiment of the present disclosure, the terminal operation states corresponding to the terminals are different, and the processing durations corresponding to the first operations are different.

[0202] In some embodiments, the terminal operating status may include, for example, the current available computing power, power level, etc. of the terminal. It is understood that the terminal operating status is used to describe the current usage status of the terminal, or the current operating status of the terminal. The processing duration corresponding to the first operation may be different for different terminal operating states.

[0203] For example, when the terminal currently has sufficient free computing power, the processing time corresponding to the first operation can be shorter. On the other hand, when the terminal currently has insufficient free computing power, the processing time corresponding to the first operation can be longer. In other words, it can be assumed that the more free computing power a terminal has, the shorter the processing time corresponding to the first operation performed by the terminal.

[0204] For example, when the terminal currently has sufficient battery power, the processing time corresponding to the first operation may be shorter. However, when the terminal has insufficient battery power, the processing time corresponding to the first operation may be longer. In other words, it can be assumed that the more battery power the terminal has, the shorter the processing time corresponding to the first operation performed by the terminal.

[0205] The present disclosure can determine different processing times for different terminal operating states. This ensures that the terminal and network device can be time-aligned based on different processing times for different operations. This allows the network device or terminal to call the AI ​​model deployed on the other end after the processing time, thereby improving the operating efficiency of the AI ​​model.

[0206] In the communication method provided in the embodiment of the present disclosure, FIG4 is a flow chart of another communication method according to an exemplary embodiment. As shown in FIG4, the method may further include the following steps:

[0207] In step S31, the second information is sent.

[0208] In some embodiments, the terminal may send second information, wherein the second information is used to indicate the terminal operation state corresponding to the terminal and / or the processing duration corresponding to the first operation supported by the terminal operation state.

[0209] For example, the terminal sends second information indicating a terminal operating state corresponding to the terminal. A device receiving the second information, such as a network device, can determine, based on the terminal operating state corresponding to the terminal indicated in the second information, a processing duration corresponding to the terminal performing the first operation in the terminal operating state.

[0210] For another example, a terminal sends second information indicating a processing duration corresponding to a first operation supported by a terminal operating state corresponding to the terminal. A device receiving the second information, such as a network device, can directly determine the processing duration corresponding to the terminal executing the first operation in the terminal operating state based on the second information.

[0211] For another example, a terminal sends second information indicating a corresponding terminal operating state and a processing duration corresponding to a first operation supported by the terminal operating state. A device receiving the second information, such as a network device, can directly determine, based on the second information, the processing duration corresponding to the terminal executing the first operation in the terminal operating state.

[0212] The terminal disclosed herein can report the terminal operating status and / or the processing time corresponding to the first operation supported by the terminal operating status, so that the network device can call the AI ​​model deployed on the terminal to perform corresponding processing after the processing time based on the information reported by the terminal, thereby improving the operating efficiency of the AI ​​model.

[0213] In the communication method provided in the embodiment of the present disclosure, FIG5 is a flow chart of another communication method according to an exemplary embodiment. As shown in FIG5, the method may further include the following steps:

[0214] In step S41 , third information is determined.

[0215] In some embodiments, the terminal may determine third information, wherein the third information is used to indicate an AI model deployed on the terminal and / or network device, and / or to indicate an application scenario of the AI ​​model.

[0216] Among them, the third information can also be called the description information of the AI ​​model. It can be used to describe the functions, configurations and other information of the relevant AI model. Therefore, for the AI ​​model deployed on the terminal side, the terminal can directly determine the description information of the relevant AI model. For the AI ​​model deployed on the network device side, the terminal can receive the third information sent by the network device to determine the functions, configurations, etc. of the relevant AI model. Of course, for AI models deployed bilaterally, the terminal can also receive the third information, which can be used only to describe the part of the AI ​​model deployed on the network device side, or the third information can describe the complete AI model, which is not limited in this disclosure.

[0217] For example, for an AI model deployed on a terminal, the terminal sends third information indicating the AI ​​model. A device receiving the third information, such as a network device, can determine, based on the AI ​​model indicated in the third information, the processing duration corresponding to the terminal performing the first operation on the AI ​​model.

[0218] For another example, for an AI model deployed on a terminal, the terminal sends third information indicating an application scenario of the AI ​​model. Alternatively, the third information indicates the functionality of the AI ​​model. A device receiving the third information, such as a network device, can determine, based on the third information, the processing duration corresponding to the first operation performed by the terminal on the AI ​​model.

[0219] For example, for an AI model deployed on a network device, the terminal receives third information indicating the AI ​​model, so that the terminal can determine, based on the AI ​​model indicated in the third information, the processing duration corresponding to the first operation performed by the network device on the AI ​​model.

[0220] For another example, for an AI model deployed on a network device, a terminal receives third information indicating an application scenario of the AI ​​model. Alternatively, the third information indicates the functionality of the AI ​​model. Based on the third information, the terminal can determine the processing duration corresponding to the first operation performed by the network device on the AI ​​model.

[0221] It is understood that the function of the AI ​​model and the application scenario of the AI ​​model can have the same meaning, that is, it is used to distinguish the AI ​​model for beam prediction, beam management, definition, etc. The present disclosure does not limit the specific function or specific application scenario of the AI ​​model.

[0222] The terminal disclosed herein can determine the AI ​​model and / or the application scenario of the AI ​​model, so that the terminal can call the AI ​​model deployed on the network device for corresponding processing after the processing time based on the above information, thereby improving the operating efficiency of the AI ​​model.

[0223] In the communication method provided by the embodiment of the present disclosure, the method may further include: executing a second operation based on the processing time corresponding to the first operation, wherein the second operation is used to instruct the terminal to use an AI model method or a non-AI model method to process data, and the AI ​​model corresponding to the AI ​​model method is the AI ​​model after the terminal executes the first operation.

[0224] In the communication method provided by the embodiment of the present disclosure, the method may further include: receiving fourth information based on the processing time corresponding to the first operation, the fourth information being used to indicate the second operation, wherein the second operation is used to instruct the terminal to use an AI model method or a non-AI model method to perform data processing, and the AI ​​model corresponding to the AI ​​model method is the AI ​​model after the terminal executes the first operation.

[0225] Based on the same concept, the present disclosure also provides a communication method executed by a network device side.

[0226] FIG6 is a flow chart showing another communication method according to an exemplary embodiment. As shown in FIG6 , the method is executed by a network device and may include the following steps:

[0227] In step S51, the processing duration corresponding to the first operation related to the AI ​​model processing is determined.

[0228] In some embodiments, the network device may determine a first operation related to AI model processing. For example, the first operation may also be referred to as a target operation. It is understood that the first operation is merely a name for an operation related to AI model processing, and this disclosure does not limit the name of the operation. The network device determines the processing duration corresponding to the first operation.

[0229] For example, the network device receives a first operation sent by the terminal. The first operation may be an operation related to AI model processing. For another example, the network device may generate the first operation, for example, based on a preset rule or receiving a first operation sent from another device, or the network device may generate the first operation by triggering some external device, etc., which is not limited in this disclosure.

[0230] When the network device determines the first operation, it can determine the processing duration corresponding to the first operation. It is understood that the processing duration can be considered as the time required for the network device to perform the first operation. In other words, the network device can complete the first operation within the processing duration.

[0231] Of course, in some cases, the first operation may also be performed by the terminal. Therefore, in this case, the processing duration corresponding to the first operation can be considered to be the duration required for the terminal to perform the first operation. It can be considered that the terminal can complete the first operation within the above processing duration. In this example, the network device determines the duration corresponding to the first operation for the purpose of determining at what time the second operation can be sent to the terminal, for example, the second operation is used to trigger the terminal to perform the corresponding task or perform data processing using the AI ​​model or non-AI model after executing the first operation.

[0232] In some embodiments, the first operation may be, for example, an operation of activating an AI model, an operation of switching an AI model, and / or an operation of shutting down an AI model.

[0233] In some embodiments, the network device may further include the following steps:

[0234] In step S52, a first operation is performed.

[0235] In some embodiments, the network device may perform the above-described operations related to AI model processing.

[0236] For example, the first operation is an operation indicating enabling a certain AI model, such as an operation of activating an AI model, and the network device can activate the relevant AI model.

[0237] For another example, the first operation is an operation instructing to switch from one AI model to another AI model. For example, the network device may switch the AI ​​model. For example, if a first AI model is running on the network device, the network device may switch the first AI model to a second AI model based on the first operation, so that the network device can subsequently run the second AI model. It is understood that the second AI model is an AI model different from the first AI model.

[0238] For another example, the first operation is an operation to shut down an AI model, such as shutting down an AI model. The network device can shut down the running AI model based on the first operation, so that the network device can subsequently use a non-AI model method to perform corresponding data processing or execute certain tasks.

[0239] In step S53, after the processing time, a second operation is performed.

[0240] In some embodiments, after the processing time, the network device may perform a second operation, wherein the second operation may be an operation of performing corresponding data processing using an AI model.

[0241] It can be understood that the above-mentioned processing time is to ensure that the network device can complete the execution of the first operation. Therefore, after the processing time, the first operation can be considered to have been completed. For example, after the processing time, the network device can be considered to have completed the execution of the first operation. The network device can receive a second operation, such as a second operation sent by the terminal. The second operation can instruct the network device to perform the corresponding task or perform data processing using the AI ​​model or non-AI model after executing the first operation. For example, if the first operation is an operation to activate the AI ​​model, the network device can use the activated AI model to perform the corresponding task. For another example, if the first operation is an operation to switch the AI ​​model, the network device can use the switched AI model to perform the corresponding task. For another example, if the first operation is an operation to shut down the AI ​​model, the network device can use a non-AI model to perform the corresponding task.

[0242] Of course, in the case where the AI ​​model is deployed on the terminal, the network device can determine that the terminal has completed the first operation based on the above processing time. The network device can send information indicating a second operation to the terminal, and the second operation can be used to instruct the terminal to perform the corresponding task or perform data processing using the AI ​​model or non-AI model after executing the first operation.

[0243] The present disclosure determines the processing duration corresponding to the first operation related to AI model processing, thereby ensuring that the terminal and the network device are time-aligned based on the processing duration. This allows the network device or terminal to call the AI ​​model deployed on the other end to perform corresponding processing after the processing duration, thereby improving the operating efficiency of the AI ​​model.

[0244] In the communication method provided by the embodiment of the present disclosure, the first operation includes at least one of the following: an operation for activating the AI ​​model; an operation for switching the AI ​​model; and an operation for shutting down the AI ​​model.

[0245] In some embodiments, the first operation related to AI model processing includes an operation for activating the AI ​​model.

[0246] It is understandable that the first operation can be used to activate a certain AI model. Activating an AI model can be understood as starting a certain AI model.

[0247] In some embodiments, the first operation related to AI model processing includes an operation for switching the AI ​​model.

[0248] It is understandable that the first operation can be used to switch the first AI model to the second AI model, wherein the first AI model can be any AI model, and the second AI model can be another AI model different from the first AI model.

[0249] In some embodiments, the first operation related to AI model processing includes an operation for shutting down the AI ​​model.

[0250] It is understandable that the first operation can be used to shut down a certain AI model, wherein the shut down AI model cannot be used.

[0251] In some embodiments, the first operation related to AI model processing includes: an operation for activating the AI ​​model, an operation for switching the AI ​​model. Alternatively, an operation for activating the AI ​​model, an operation for deactivating the AI ​​model. Alternatively, an operation for switching the AI ​​model, an operation for deactivating the AI ​​model. Alternatively, an operation for activating the AI ​​model, an operation for switching the AI ​​model, an operation for deactivating the AI ​​model.

[0252] The present disclosure provides a variety of first operations related to AI model processing to determine the processing duration corresponding to the operation, thereby ensuring that the terminal and network device are time-aligned based on the processing duration. This allows the network device or terminal to call the AI ​​model deployed on the other end after the processing duration to perform corresponding processing, thereby improving the operating efficiency of the AI ​​model.

[0253] In the communication method provided by the embodiment of the present disclosure, the first operation is different, and the processing time corresponding to the first operation is different.

[0254] In some embodiments, different first operations may correspond to different processing durations. In other words, different first operations performed by the network device may correspond to different processing durations.

[0255] For example, the first operation is to activate an AI model. The network device needs to switch from a non-AI model-based processing mode to an AI model-based processing mode, and needs to load the software and hardware environment related to the AI ​​model. Therefore, it takes a certain amount of processing time to complete the first operation, that is, to activate the AI ​​model.

[0256] For example, the first operation involves switching AI models. The network device needs to switch from processing the first AI model to processing the second AI model. The software and hardware environments associated with the second AI model must be loaded, and the software and hardware environments associated with the first AI model must be shut down. Therefore, completing the first operation (i.e., switching AI models) requires a certain amount of processing time.

[0257] For example, the first operation is to shut down an AI model. The network device needs to switch from an AI-based processing mode to a non-AI model-based processing mode. The software and hardware environments associated with the AI ​​model need to be shut down. Therefore, it takes a certain amount of processing time to complete the first operation, shutting down the AI ​​model.

[0258] Of course, when a network device performs the above-mentioned different first operations, since the network device needs to perform different operations of loading and / or closing the AI ​​model, the processing time required for different first operations is also different.

[0259] This disclosure determines different processing times for different first operations related to AI model processing. This ensures that the terminal and network device can be time-aligned based on different processing times for different operations. This allows the network device or terminal to invoke the AI ​​model deployed on the other end after the processing time, thereby improving the operating efficiency of the AI ​​model.

[0260] In the communication method provided by the embodiments of the present disclosure, the processing duration corresponding to the operation for activating the AI ​​model is greater than or equal to the processing duration corresponding to the operation for switching the AI ​​model; and / or, the processing duration corresponding to the operation for shutting down the AI ​​model is less than or equal to the processing duration corresponding to the operation for switching the AI ​​model.

[0261] In some embodiments, the processing duration corresponding to the operation for activating the AI ​​model is greater than or equal to the processing duration corresponding to the operation for switching the AI ​​model.

[0262] That is, the processing time for the network device to activate the AI ​​model is longer than the processing time for switching the AI ​​model. Alternatively, the processing time for the network device to activate the AI ​​model is equal to the processing time for switching the AI ​​model.

[0263] In some embodiments, the processing duration corresponding to the operation for shutting down the AI ​​model is less than or equal to the processing duration corresponding to the operation for switching the AI ​​model.

[0264] That is, the processing time of the network device shutting down the AI ​​model is less than the processing time of switching the AI ​​model. Alternatively, the processing time of the network device shutting down the AI ​​model is equal to the processing time of switching the AI ​​model.

[0265] This disclosure provides specific processing duration relationships for different first operations related to AI model processing. This ensures that terminals and network devices can time-align different operations based on different processing durations. This allows the network device or terminal to invoke the AI ​​model deployed on the other end after the processing duration, thereby improving the operating efficiency of the AI ​​model.

[0266] In the communication method provided in the embodiment of the present disclosure, the deployment method of the AI ​​model is different, and the processing time corresponding to the first operation is different.

[0267] In some embodiments, the deployment mode of the AI ​​model can be divided into unilateral deployment and bilateral deployment. Among them, unilateral deployment means that the AI ​​model is deployed on one device. For example, it can be deployed on a terminal or a network device. Bilateral deployment means that different parts of the AI ​​model can be deployed on different devices respectively. For example, the same AI model can be divided into two parts. One part of the AI ​​model can be deployed on the terminal, and the other part of the AI ​​model can be deployed on the network device. Of course, in some cases, one part of the AI ​​model can be deployed on terminal A, and the other part of the AI ​​model can be deployed on terminal B; or, one part of the AI ​​model can be deployed on network device A, and the other part of the AI ​​model can be deployed on network device B.

[0268] In some embodiments, the processing duration corresponding to the first operation involving a unilaterally deployed AI model may be different from the processing duration corresponding to the first operation involving a bilaterally deployed AI model.

[0269] For example, assuming that the first operation is to activate an AI model, the processing time corresponding to activating a unilaterally deployed AI model is different from the processing time corresponding to activating a bilaterally deployed AI model.

[0270] For another example, assuming that the first operation is an operation of switching AI models, the processing time corresponding to switching the unilaterally deployed AI model is different from the processing time corresponding to switching the bilaterally deployed AI model.

[0271] Of course, during the operation of switching AI models, the processing time corresponding to switching from a unilaterally deployed AI model to a bilaterally deployed AI model may be different from the processing time corresponding to switching from a bilaterally deployed AI model to a unilaterally deployed AI model.

[0272] For another example, assuming that the first operation is to shut down the AI ​​model, the processing time corresponding to shutting down the unilaterally deployed AI model is different from the processing time corresponding to shutting down the bilaterally deployed AI model.

[0273] This disclosure determines different processing times for different AI model deployment methods. This ensures that terminals and network devices can be time-aligned based on different processing times for different operations. This allows the network device or terminal to call the AI ​​model deployed on the other end for corresponding processing after the processing time, thereby improving the operating efficiency of the AI ​​model.

[0274] In the communication method provided by the embodiments of the present disclosure, the AI ​​model is deployed in a terminal or a network device, and the processing time corresponding to the first operation is the first processing time; and, the AI ​​model is deployed in a terminal and a network device, and the processing time corresponding to the first operation is the second processing time; the processing time corresponding to the first operation is different, including: the first processing time is less than or equal to the second processing time.

[0275] In some embodiments, the AI ​​model can be deployed on one device, for example, the same AI model is deployed on a terminal or a network device. The processing duration corresponding to the first operation is referred to as the first processing duration. The AI ​​model can also be deployed on multiple devices, for example, different parts of the same AI model are deployed on a terminal and a network device, respectively, or not on different terminals, or are deployed on different network devices. The processing duration corresponding to the first operation is referred to as the second processing duration.

[0276] In some embodiments, the first processing duration is less than the second processing duration.

[0277] For example, the processing time corresponding to operations related to unilaterally deployed AI model processing may be shorter than the processing time corresponding to operations related to bilaterally deployed AI model processing.

[0278] For example, the processing time corresponding to activating a unilaterally deployed AI model can be shorter than the processing time corresponding to activating a bilaterally deployed AI model.

[0279] For example, the processing time corresponding to switching a unilaterally deployed AI model can be shorter than the processing time corresponding to switching a bilaterally deployed AI model.

[0280] Of course, during the AI ​​model switching operation, the processing time corresponding to switching from a unilaterally deployed AI model to a bilaterally deployed AI model may be shorter than the processing time corresponding to switching from a bilaterally deployed AI model to a unilaterally deployed AI model. Alternatively, the processing time corresponding to switching from a unilaterally deployed AI model to a bilaterally deployed AI model may be longer than the processing time corresponding to switching from a bilaterally deployed AI model to a unilaterally deployed AI model.

[0281] For another example, the processing time corresponding to shutting down a unilaterally deployed AI model may be shorter than the processing time corresponding to shutting down a bilaterally deployed AI model.

[0282] In some embodiments, the first processing duration is equal to the second processing duration.

[0283] For example, the processing time corresponding to operations related to unilaterally deployed AI model processing can be equal to the processing time corresponding to operations related to bilaterally deployed AI model processing.

[0284] For example, the processing time corresponding to activating a unilaterally deployed AI model can be equal to the processing time corresponding to activating a bilaterally deployed AI model.

[0285] For example, the processing time corresponding to switching a unilaterally deployed AI model can be equal to the processing time corresponding to switching a bilaterally deployed AI model.

[0286] Of course, during the operation of switching AI models, the processing time corresponding to switching from a unilaterally deployed AI model to a bilaterally deployed AI model can be equal to the processing time corresponding to switching from a bilaterally deployed AI model to a unilaterally deployed AI model.

[0287] For another example, the processing time corresponding to shutting down a unilaterally deployed AI model can be equal to the processing time corresponding to shutting down a bilaterally deployed AI model.

[0288] This disclosure provides specific processing duration relationships for different AI model deployment methods. This ensures that terminals and network devices can be time-aligned based on different processing durations for different operations. This allows the network device or terminal to invoke the AI ​​model deployed on the other end after the processing duration, thereby improving the operating efficiency of the AI ​​model.

[0289] In the communication method provided in the embodiment of the present disclosure, the application scenarios of the AI ​​model are different, and the processing time corresponding to the first operation is different.

[0290] In some embodiments, the processing durations corresponding to different first operations can be determined based on different application scenarios corresponding to the AI ​​model. Different application scenarios of the AI ​​model can be understood as different use cases of the AI ​​model.

[0291] Assuming that the use scenarios of the AI ​​model include beam prediction scenarios and definition scenarios, the processing time corresponding to the first operation in the beam prediction scenario may be different from the processing time corresponding to the first operation in the positioning scenario.

[0292] Of course, the use scenarios of the AI ​​model can also include CSI enhancement, etc. This disclosure does not limit the specific use scenarios of the AI ​​model, nor the number of use scenarios.

[0293] This disclosure determines different processing times for different AI model usage scenarios. This ensures that terminals and network devices can be time-aligned based on different processing times for different operations. This allows the network device or terminal to invoke the AI ​​model deployed on the other end for corresponding processing after the processing time, thereby improving the operating efficiency of the AI ​​model.

[0294] In the communication method provided by the embodiment of the present disclosure, the storage space occupied by the AI ​​model is different, and the processing time corresponding to the first operation is different; or, the complexity corresponding to the AI ​​model is different, and the processing time corresponding to the first operation is different.

[0295] In some embodiments, different AI models may occupy different storage spaces, in other words, the sizes of the AI ​​models may be different. Therefore, the processing time for performing the first operation on AI models of different sizes may be different.

[0296] For example, if the storage space occupied by the first AI model is larger than the storage space occupied by the second AI model, the processing time for performing the first operation on the first AI model may be greater than the processing time for performing the first operation on the second AI model.

[0297] In some embodiments, different AI models may correspond to different complexities, and the processing time for performing the first operation on AI models of different complexities may be different.

[0298] For example, if the complexity of the first AI model is greater than the complexity of the second AI model, the processing time for operating the first AI model may be greater than the processing time for performing the first operation on the second AI model.

[0299] In some embodiments, the complexity of the AI ​​model may or may not be related to the storage space occupied by the AI ​​model. For example, if the complexity of the AI ​​model is related to the storage space occupied by the AI ​​model, the higher the complexity of the AI ​​model, the larger the storage space occupied by the AI ​​model.

[0300] This disclosure can determine different processing times based on the different storage space occupied or complexity of AI models. This ensures that terminals and network devices can be time-aligned based on different processing times for different operations. This allows the network device or terminal to call the AI ​​model deployed on the other end after the processing time, thereby improving the operating efficiency of the AI ​​model.

[0301] In the communication method provided by the embodiment of the present disclosure, the capabilities corresponding to the terminals are different, and the processing duration corresponding to the first operation is different.

[0302] In some embodiments, different terminals may correspond to different capabilities. For example, terminals may include ordinary terminals and low-capability terminals. Terminals with different capabilities may have different processing times for executing the first operation. For example, terminal capabilities may include any possible capabilities, such as AI model processing capabilities, hardware capabilities, and software capabilities, and are not limited in this disclosure.

[0303] Among them, low-capability terminals can be called RedCap terminals.

[0304] For example, suppose that some terminals may execute the operations processed by the AI ​​model faster, while other terminals may take longer to execute the operations processed by the AI ​​model. Therefore, it can be considered that the capabilities of these terminals are different. Accordingly, the processing time corresponding to the first operation performed by terminals with different capabilities is also different.

[0305] It is understandable that different terminals may have different capabilities for different AI models.

[0306] For example, it can be assumed that there are a first terminal and a second terminal. The first terminal and the second terminal have different capabilities, so the processing time corresponding to the first terminal performing the operation related to the AI ​​model processing can be different from the processing time corresponding to the second terminal performing the operation related to the AI ​​model processing.

[0307] For another example, each terminal may have separate capabilities for different operations related to AI model processing. For example, the capability of a first terminal to activate an AI model differs from that of a second terminal. Therefore, the processing duration corresponding to the first terminal's operation to activate the AI ​​model may be different from that of the second terminal. It will be understood that different terminals may also have separate capabilities for switching AI models and shutting down AI models. For example, the capability of a first terminal to switch an AI model differs from that of a second terminal. Therefore, the processing duration corresponding to the first terminal's operation to switch an AI model may be different from that of the second terminal. For another example, the capability of a first terminal to shut down an AI model differs from that of a second terminal. Therefore, the processing duration corresponding to the first terminal's operation to shut down an AI model may be different from that of the second terminal.

[0308] For another example, each terminal may have separate capabilities depending on the deployment method of the AI ​​model. For example, the capability of the first terminal to execute a unilaterally deployed AI model is different from the capability of the second terminal to execute a unilaterally deployed AI model. And / or, the capability of the first terminal to execute a bilaterally deployed AI model is different from the capability of the second terminal to execute a bilaterally deployed AI model. Assuming that the capability of the first terminal is higher than that of the second terminal, it can be considered that the processing time of the unilaterally deployed AI model executed by the first terminal is less than the processing time of the unilaterally deployed AI model executed by the second terminal. And / or, the processing time of the bilaterally deployed AI model executed by the first terminal is less than the processing time of the bilaterally deployed AI model executed by the second terminal.

[0309] For another example, each terminal may have separate capabilities for different AI models, depending on the storage space or complexity. Assuming the capabilities of a first terminal are higher than those of a second terminal, then for AI models occupying the same storage space or having the same complexity, the processing time for the first terminal to execute the AI ​​model may be less than the processing time for the second terminal to execute the AI ​​model.

[0310] It can be understood that the higher the capability of a terminal is, the shorter the processing time corresponding to the operation of the terminal can be.

[0311] In some embodiments, the terminal may also have corresponding capabilities based on the configuration of any possible AI model, such as different application scenarios of the AI ​​model, which is not limited in this disclosure.

[0312] The present disclosure can determine different processing times for different terminal capabilities. This ensures that terminals and network devices can be time-aligned based on different processing times for different operations. This allows the network device or terminal to invoke the AI ​​model deployed on the other end after the processing time has expired to perform corresponding processing, thereby improving the operating efficiency of the AI ​​model.

[0313] In the communication method provided in the embodiment of the present disclosure, FIG7 is a flow chart of another communication method according to an exemplary embodiment. As shown in FIG7 , the method may further include the following steps:

[0314] In step S61, first information is received.

[0315] In some embodiments, the network device may receive first information, wherein the first information is used to indicate a capability corresponding to the terminal and / or a processing duration corresponding to a first operation supported by the capability.

[0316] For example, the network device receives first information indicating the capabilities of the terminal, so that the network device can determine the processing time corresponding to the terminal performing the first operation according to the capabilities of the terminal indicated in the first information.

[0317] For another example, the network device receives first information indicating a processing duration corresponding to a first operation supported by a capability corresponding to the terminal, so that the network device can directly determine the processing duration corresponding to the terminal executing the first operation based on the first information.

[0318] For another example, the network device receives first information indicating the capability corresponding to the terminal and the processing duration corresponding to the first operation supported by the capability, so that the network device can directly determine the processing duration corresponding to the terminal performing the first operation based on the first information.

[0319] The network device disclosed herein can receive the terminal's reported capabilities and / or the processing time corresponding to the first operation corresponding to the capabilities, so that the network device can call the AI ​​model deployed on the terminal to perform corresponding processing after the processing time based on the information reported by the terminal, thereby improving the operating efficiency of the AI ​​model.

[0320] In the communication method provided by the embodiment of the present disclosure, the terminal operation states corresponding to the terminals are different, and the processing durations corresponding to the first operations are different.

[0321] In some embodiments, the terminal operating status may include, for example, the current available computing power, power level, etc. of the terminal. It is understood that the terminal operating status is used to describe the current usage status of the terminal, or the current operating status of the terminal. The processing duration corresponding to the first operation may be different for different terminal operating states.

[0322] For example, when the terminal currently has sufficient free computing power, the processing time corresponding to the first operation can be shorter. On the other hand, when the terminal currently has insufficient free computing power, the processing time corresponding to the first operation can be longer. In other words, it can be assumed that the more free computing power a terminal has, the shorter the processing time corresponding to the first operation performed by the terminal.

[0323] For example, when the terminal currently has sufficient battery power, the processing time corresponding to the first operation may be shorter. However, when the terminal has insufficient battery power, the processing time corresponding to the first operation may be longer. In other words, it can be assumed that the more battery power the terminal has, the shorter the processing time corresponding to the first operation performed by the terminal.

[0324] The present disclosure can determine different processing times for different terminal operating states. This ensures that the terminal and network device can be time-aligned based on different processing times for different operations. This allows the network device or terminal to call the AI ​​model deployed on the other end after the processing time, thereby improving the operating efficiency of the AI ​​model.

[0325] In the communication method provided in the embodiment of the present disclosure, FIG8 is a flow chart of another communication method according to an exemplary embodiment. As shown in FIG8, the method may further include the following steps:

[0326] In step S71, second information is received.

[0327] In some embodiments, the network device may receive second information, wherein the second information is used to indicate a terminal operating state corresponding to the terminal and / or a processing duration corresponding to a first operation supported by the terminal operating state.

[0328] For example, the network device receives second information indicating a terminal operation state corresponding to the terminal, so that the network device can determine the processing time corresponding to the terminal performing the first operation in the terminal operation state according to the terminal operation state corresponding to the terminal indicated in the second information.

[0329] For another example, the network device receives second information indicating a processing duration corresponding to a first operation supported by a terminal operating state corresponding to the terminal, so that the network device can directly determine the processing duration corresponding to the terminal performing the first operation in the terminal operating state based on the second information.

[0330] For another example, the network device receives second information indicating a terminal operating state corresponding to the terminal and a processing duration corresponding to a first operation supported by the terminal operating state, so that the network device can directly determine the processing duration corresponding to the terminal performing the first operation in the terminal operating state based on the second information.

[0331] The network device disclosed herein can receive the terminal operating status reported by the terminal and / or the processing time corresponding to the first operation supported by the terminal operating status, so that the network device can call the AI ​​model deployed on the terminal to perform corresponding processing after the processing time based on the information reported by the terminal, thereby improving the operating efficiency of the AI ​​model.

[0332] In the communication method provided in the embodiment of the present disclosure, FIG9 is a flow chart of another communication method according to an exemplary embodiment. As shown in FIG9 , the method may further include the following steps:

[0333] In step S81 , third information is determined.

[0334] In some embodiments, the network device may determine third information, wherein the third information is used to indicate an AI model deployed on the terminal and / or the network device, and / or to indicate an application scenario of the AI ​​model.

[0335] Among them, the third information can also be called the description information of the AI ​​model. It can be used to describe the functions, configurations and other information of the relevant AI model. Therefore, for the AI ​​model deployed on the network device side, the network device can directly determine the description information of the relevant AI model. For the AI ​​model deployed on the terminal side, the network device can receive the third information sent by the terminal to determine the functions, configurations, etc. of the relevant AI model. Of course, for AI models deployed bilaterally, the network device can also receive the third information, which can be used only to describe the part of the AI ​​model deployed on the terminal side, or the third information can describe the complete AI model, which is not limited in this disclosure.

[0336] For example, for an AI model deployed on a network device, the network device sends third information indicating the AI ​​model. A device receiving the third information, such as a terminal, can determine, based on the AI ​​model indicated in the third information, the processing duration corresponding to the first operation performed by the network device on the AI ​​model.

[0337] For another example, for an AI model deployed on a network device, the network device sends third information indicating an application scenario of the AI ​​model. Alternatively, the third information indicates the functionality of the AI ​​model. A device receiving the third information, such as a terminal, can determine, based on the third information, the processing duration corresponding to the first operation performed by the network device on the AI ​​model.

[0338] For example, for an AI model deployed on the terminal side, the network device may receive third information indicating the AI ​​model, so that the network device can determine the processing time corresponding to the terminal performing the first operation on the AI ​​model based on the AI ​​model indicated in the third information.

[0339] For another example, for an AI model deployed on a terminal, the network device may receive third information indicating an application scenario of the AI ​​model. Alternatively, the third information may indicate the functionality of the AI ​​model. The network device may then determine, based on the third information, the processing duration corresponding to the terminal performing a first operation on the AI ​​model.

[0340] It is understood that the function of the AI ​​model and the application scenario of the AI ​​model can have the same meaning, that is, it is used to distinguish the AI ​​model for beam prediction, beam management, definition, etc. The present disclosure does not limit the specific function or specific application scenario of the AI ​​model.

[0341] The network device disclosed herein can determine the AI ​​model and / or the application scenario of the AI ​​model, so that the network device can call the AI ​​model deployed on the terminal to perform corresponding processing after the processing time based on the above information, thereby improving the operating efficiency of the AI ​​model.

[0342] In the communication method provided by the embodiment of the present disclosure, the method may further include: executing a second operation based on the processing time corresponding to the first operation, wherein the second operation is used to instruct the network device to use an AI model method or a non-AI model method to process data, and the AI ​​model corresponding to the AI ​​model method is the AI ​​model after the network device executes the first operation.

[0343] In the communication method provided by the embodiment of the present disclosure, the method also includes: receiving fourth information based on the processing time corresponding to the first operation, the fourth information is used to indicate the second operation, wherein the second operation is used to instruct the network device to use an AI model method or a non-AI model method to process data, and the AI ​​model corresponding to the AI ​​model method is the AI ​​model after the network device performs the first operation.

[0344] Next, the above solution will be described with more specific embodiments.

[0345] In some embodiments, the terminal may determine, based on a preset rule, that a second operation is performed after a preset time period. It is understood that the terminal may receive information sent by a network device, which may instruct the terminal to perform the first operation. Based on the preset rule, the terminal determines a time corresponding to the execution of the first operation, i.e., a preset time. The terminal determines that the second operation is performed after the preset time period.

[0346] The preset time may be the processing time corresponding to the first operation described in each embodiment in FIG. 2 to FIG. 9 .

[0347] For example, the terminal receives signaling sent by a network device, and the signaling may be any one or more of a radio resource control (RRC) signaling, a medium access control control element (MAC CE), and downlink control information (DCI). Of course, the signaling may also be any other possible signaling, which is not limited in the present disclosure. The signaling indicates a first operation. The terminal determines the processing duration corresponding to the first operation, that is, the preset duration. After the preset duration, the terminal performs the second operation. It can be understood that the terminal can trigger the execution of the second operation by itself. For example, the first operation instructs the terminal to activate the AI ​​model for beam prediction. After the preset time, the terminal triggers itself to use the AI ​​model for beam prediction to perform the corresponding beam prediction task.

[0348] For another example, a first operation instructs the terminal to switch AI models. It can be assumed that after the terminal processes data using AI model 1, it can output a 10-bit result. The terminal feeds back the 10-bit result to the network device. It can be assumed that after the terminal processes data using AI model 2, it can output a 20-bit result. The terminal feeds back the 20-bit result to the network device. When the first operation instructs the terminal to switch from AI model 1 to AI model 2, it is assumed that the terminal determines the time of the first operation to be t. Before time t, the terminal feeds back the 10-bit result to the network device. Based on the first operation, the terminal determines the processing time corresponding to executing the first operation to be n. After t+n, it can be considered that the terminal has completed the switch from AI model 1 to AI model 2, and the terminal feeds back the 20-bit result to the network device. Of course, for the time period corresponding to n, the terminal can be set not to send any information to the network device. Alternatively, the terminal does not send any AI model output results to the network device.

[0349] It is understood that the terminal and network device in the above embodiment can be interchangeable. Specifically, the network device can determine, based on preset rules, that after a preset time period, the second operation is performed. It is also understood that the network device can receive information sent by the terminal, which can instruct the network device to perform the first operation. Based on the preset rules, the network device determines the time corresponding to the execution of the first operation, i.e., the preset time. The network device determines that after the preset time period, the second operation is performed.

[0350] For example, the network device receives signaling sent by the terminal, and the signaling may be any one or more of RRC signaling, MAC CE, and uplink control information (UCI). Of course, the signaling may also be any other possible signaling, which is not limited in the present disclosure. The signaling indicates a first operation. The network device determines the processing duration corresponding to the first operation, that is, the preset duration. After the preset duration, the network device performs the second operation. It can be understood that the network device can trigger the execution of the second operation by itself. For example, the first operation instructs the terminal to activate the AI ​​model for beam prediction. After the preset time, the network device triggers itself to use the AI ​​model for beam prediction to perform the corresponding beam prediction task.

[0351] For another example, a first operation instructs the network device to switch AI models. It can be assumed that after the network device processes data using AI model 1, it can output a 10-bit result. The network device feeds back the 10-bit result to the terminal. It can be assumed that after the network device processes data using AI model 2, it can output a 20-bit result. The network device feeds back the 20-bit result to the terminal. When the first operation instructs the network device to switch from AI model 1 to AI model 2, it is assumed that the network device determines the time for the first operation to be t. Before time t, the network device feeds back the 10-bit result to the terminal. Based on the first operation, the network device determines the processing time corresponding to executing the first operation to be n. After t + n, the network device is considered to have completed the switch from AI model 1 to AI model 2, and the network device feeds back the 20-bit result to the terminal. Of course, for the time period corresponding to n, the network device can be set not to send any information to the terminal. Alternatively, the network device does not send any AI model output results to the terminal.

[0352] In some embodiments, the terminal may determine a preset duration based on preset rules. After the preset duration, the terminal receives information from a network device indicating a second operation. The terminal then performs the second operation. It is understood that the terminal may also receive information from a network device indicating the terminal to perform a first operation. Based on preset rules, the terminal determines a time corresponding to performing the first operation, i.e., a preset time. After the preset time, the terminal receives information from the network device indicating the terminal to perform the second operation. The terminal then performs the second operation.

[0353] The preset time may be the processing time corresponding to the first operation described in each embodiment in FIG. 2 to FIG. 9 .

[0354] For example, a terminal receives first signaling from a network device instructing the terminal to perform a first operation. The first signaling may be any one or more of RRC signaling, MAC CE, and DCI. Of course, the first signaling may also be any other possible signaling, which is not limited in this disclosure. The first signaling indicates the first operation. The terminal determines the processing duration corresponding to the first operation, i.e., a preset duration. After the preset duration, the terminal receives second signaling from the network device instructing the terminal to perform a second operation. The second signaling may be any one or more of RRC signaling, MAC CE, and DCI. The terminal performs the second operation. It is understood that the terminal may receive the second signaling from the network device after the preset duration to trigger the terminal to perform the second operation. For example, the first operation instructs the terminal to activate an AI model for beam prediction. After the preset time, the terminal receives the second signaling. This triggers the terminal to use the AI ​​model for beam prediction to perform the corresponding beam prediction task.

[0355] For another example, a first operation instructs the terminal to switch AI models. It can be assumed that after processing data using AI model 1, the terminal can output a 10-bit result. The terminal feeds back the 10-bit result to the network device. It can be assumed that after processing data using AI model 2, the terminal can output a 20-bit result. The terminal feeds back the 20-bit result to the network device. When the first operation instructs the terminal to switch from AI model 1 to AI model 2, it is assumed that the terminal determines the time for the first operation to be t. Before time t, the terminal feeds back the 10-bit result to the network device. Based on the first operation, the terminal determines the processing duration corresponding to executing the first operation to be n. After time t+n, it can be considered that the terminal has completed the switch from AI model 1 to AI model 2. At time t', after t+n, the terminal receives second signaling from the network device instructing the terminal to execute a second operation. If the terminal determines to execute the second operation, the terminal feeds back the 20-bit result to the network device. Of course, for the time period corresponding to n, and for the time period from t+n until time t', the terminal can be set not to send any information to the network device. Alternatively, the terminal does not send any AI model output results to the network device.

[0356] It is understood that the terminal and network device in the above embodiment can be interchangeable. That is, the network device can determine, based on preset rules, after a preset time period. Then, after receiving a second signaling from the terminal to instruct the network device to perform a second operation. It is also understood that the network device can receive a first signaling from the terminal, which can instruct the network device to perform a first operation. Based on preset rules, the network device determines a time corresponding to performing the first operation, i.e., a preset time. After the preset time period, the network device receives a second signaling from the terminal to instruct the network device to perform a second operation, and the network device performs the second operation.

[0357] For example, a network device receives first signaling from a terminal instructing the network device to perform a first operation. The first signaling may be any one or more of RRC signaling, MAC CE, and UCI. Of course, the first signaling may also be any other possible signaling, and this disclosure is not limited thereto. The first signaling indicates the first operation. The network device determines the processing duration corresponding to the first operation, i.e., a preset duration. After the preset duration, the network device receives second signaling from the terminal instructing the network device to perform a second operation. The second signaling may be any one or more of RRC signaling, MAC CE, and UCI. The network device performs the second operation. It is understood that the network device may receive the second signaling from the terminal after the preset duration to trigger the network device to perform the second operation. For example, the first operation instructs the network device to activate an AI model for beam prediction. After the preset time, the network device receives the second signaling. This triggers the network device to use the AI ​​model for beam prediction to perform the corresponding beam prediction task.

[0358] For another example, a first operation instructs the network device to switch AI models. Assume that after processing data using AI model 1, the network device can output a 10-bit result. The network device feeds back the 10-bit result to the terminal. Assume that after processing data using AI model 2, the network device can output a 20-bit result. The network device feeds back the 20-bit result to the terminal. When the first operation instructs the network device to switch from AI model 1 to AI model 2, assume that the network device determines the time for the first operation to be t. Before time t, the network device feeds back the 10-bit result to the terminal. Based on the first operation, the network device determines the processing duration corresponding to executing the first operation to be n. After t+n, the network device is considered to have completed the switch from AI model 1 to AI model 2. At t', after t+n, the network device receives second signaling from the terminal, instructing the network device to execute the second operation. If the network device determines to execute the second operation, the network device feeds back the 20-bit result to the terminal. Of course, for the time period corresponding to n, and for the time period from t+n until t', the network device can be configured not to send any information to the terminal. Alternatively, the network device does not send any AI model output results to the terminal.

[0359] 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.

[0360] Based on the same concept, the embodiments of the present disclosure also provide a communication device and equipment.

[0361] It is understandable that the communication devices and equipment provided by the embodiments of the present disclosure include hardware structures and / or software modules corresponding to the execution of each function in order to realize the above functions. In combination with the units and algorithm steps of each example disclosed in the embodiments of the present disclosure, the embodiments of the present disclosure can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the technical solution of the embodiments of the present disclosure.

[0362] FIG10 is a schematic diagram of a communication device according to an exemplary embodiment. Referring to FIG10 , the device 200 is configured in a terminal and includes: a processing module 201 for determining a processing duration corresponding to a first operation related to AI model processing.

[0363] The present disclosure determines the processing duration corresponding to the first operation related to AI model processing, thereby ensuring that the terminal and the network device are time-aligned based on the processing duration. This allows the network device or terminal to call the AI ​​model deployed on the other end to perform corresponding processing after the processing duration, thereby improving the operating efficiency of the AI ​​model.

[0364] In some embodiments, the first operation includes at least one of the following: an operation for activating the AI ​​model; an operation for switching the AI ​​model; and an operation for shutting down the AI ​​model.

[0365] The present disclosure provides a variety of first operations related to AI model processing to determine the processing duration corresponding to the operation, thereby ensuring that the terminal and network device are time-aligned based on the processing duration. This allows the network device or terminal to call the AI ​​model deployed on the other end after the processing duration to perform corresponding processing, thereby improving the operating efficiency of the AI ​​model.

[0366] In some implementations, the first operations are different, and the processing durations corresponding to the first operations are different.

[0367] This disclosure determines different processing times for different first operations related to AI model processing. This ensures that the terminal and network device can be time-aligned based on different processing times for different operations. This allows the network device or terminal to invoke the AI ​​model deployed on the other end after the processing time, thereby improving the operating efficiency of the AI ​​model.

[0368] In some embodiments, the processing duration corresponding to the operation for activating the AI ​​model is greater than or equal to the processing duration corresponding to the operation for switching the AI ​​model; and / or, the processing duration corresponding to the operation for deactivating the AI ​​model is less than or equal to the processing duration corresponding to the operation for switching the AI ​​model.

[0369] This disclosure provides specific processing duration relationships for different operations related to AI model processing. This ensures that terminals and network devices can time-align different operations based on different processing durations. This allows the network device or terminal to invoke the AI ​​model deployed on the other end after the processing duration, thereby improving the operating efficiency of the AI ​​model.

[0370] In some implementations, the deployment method of the AI ​​model is different, and the processing time corresponding to the first operation is different.

[0371] This disclosure determines different processing times for different AI model deployment methods. This ensures that terminals and network devices can be time-aligned based on different processing times for different operations. This allows the network device or terminal to call the AI ​​model deployed on the other end for corresponding processing after the processing time, thereby improving the operating efficiency of the AI ​​model.

[0372] In some embodiments, the AI ​​model is deployed on a terminal or a network device, and the processing time corresponding to the first operation is the first processing time; and, the AI ​​model is deployed on a terminal and a network device, and the processing time corresponding to the first operation is the second processing time; the processing times corresponding to the first operation are different, including: the first processing time is less than or equal to the second processing time.

[0373] This disclosure provides specific processing duration relationships for different AI model deployment methods. This ensures that terminals and network devices can be time-aligned based on different processing durations for different operations. This allows the network device or terminal to invoke the AI ​​model deployed on the other end after the processing duration, thereby improving the operating efficiency of the AI ​​model.

[0374] In some implementations, the processing time corresponding to the first operation varies depending on the application scenario of the AI ​​model.

[0375] This disclosure determines different processing times for different AI model usage scenarios. This ensures that terminals and network devices can be time-aligned based on different processing times for different operations. This allows the network device or terminal to invoke the AI ​​model deployed on the other end for corresponding processing after the processing time, thereby improving the operating efficiency of the AI ​​model.

[0376] In some embodiments, the AI ​​models occupy different storage spaces, and the processing time corresponding to the first operation is different; or, the AI ​​models have different complexities, and the processing time corresponding to the first operation is different.

[0377] This disclosure can determine different processing times based on the different storage space occupied or complexity of AI models. This ensures that terminals and network devices can be time-aligned based on different processing times for different operations. This allows the network device or terminal to call the AI ​​model deployed on the other end after the processing time, thereby improving the operating efficiency of the AI ​​model.

[0378] In some implementations, the capabilities corresponding to the terminals are different, and the processing durations corresponding to the first operations are different.

[0379] The present disclosure can determine different processing times for different terminal capabilities. This ensures that terminals and network devices can be time-aligned based on different processing times for different operations. This allows the network device or terminal to invoke the AI ​​model deployed on the other end after the processing time has expired to perform corresponding processing, thereby improving the operating efficiency of the AI ​​model.

[0380] In some embodiments, the apparatus 200 further includes: a sending module 202, configured to send first information, where the first information is used to indicate the capability corresponding to the terminal and / or the processing duration corresponding to the first operation supported by the capability.

[0381] The terminal disclosed herein can report its own capabilities and / or the processing time corresponding to the first operation corresponding to the capabilities, so that the network device can call the AI ​​model deployed on the terminal to perform corresponding processing after the processing time based on the information reported by the terminal, thereby improving the operating efficiency of the AI ​​model.

[0382] In some implementations, the terminal operation states corresponding to the terminals are different, and the processing durations corresponding to the first operations are different.

[0383] The present disclosure can determine different processing times for different terminal states. This ensures that the terminal and network device can be time-aligned based on different processing times for different operations. This allows the network device or terminal to call the AI ​​model deployed on the other end after the processing time, thereby improving the operating efficiency of the AI ​​model.

[0384] In some embodiments, the apparatus 200 further includes: a sending module 202, configured to send second information, where the second information is used to indicate a terminal operating state corresponding to the terminal and / or a processing duration corresponding to a first operation supported by the terminal operating state.

[0385] The terminal disclosed herein can report the terminal status and / or the processing time corresponding to the first operation supported by the terminal status, so that the network device can call the AI ​​model deployed on the terminal to perform corresponding processing after the processing time based on the information reported by the terminal, thereby improving the operating efficiency of the AI ​​model.

[0386] In some embodiments, the processing module 201 is further used to determine third information, where the third information is used to indicate an AI model deployed on a terminal and / or network device, and / or to indicate an application scenario of the AI ​​model.

[0387] The terminal disclosed herein can determine the AI ​​model and / or the application scenario of the AI ​​model, so that the terminal can call the AI ​​model deployed on the network device for corresponding processing after the processing time based on the above information, thereby improving the operating efficiency of the AI ​​model.

[0388] In some embodiments, the processing module 201 is also used to: perform a second operation based on the processing time corresponding to the first operation, wherein the second operation is used to instruct the terminal to use an AI model method or a non-AI model method to process data, and the AI ​​model corresponding to the AI ​​model method is the AI ​​model after the terminal executes the first operation.

[0389] In some embodiments, the device 200 also includes: a receiving module 203, which is used to receive fourth information based on the processing time corresponding to the first operation, and the fourth information is used to indicate the second operation, wherein the second operation is used to instruct the terminal to use an AI model method or a non-AI model method to process data, and the AI ​​model corresponding to the AI ​​model method is the AI ​​model after the terminal executes the first operation.

[0390] FIG11 is a schematic diagram of another communication device according to an exemplary embodiment. Referring to FIG11 , the device 300 is configured in a network device and includes a processing module 301 for determining a processing duration corresponding to a first operation related to AI model processing.

[0391] The present disclosure determines the processing duration corresponding to the first operation related to AI model processing, thereby ensuring that the terminal and the network device are time-aligned based on the processing duration. This allows the network device or terminal to call the AI ​​model deployed on the other end to perform corresponding processing after the processing duration, thereby improving the operating efficiency of the AI ​​model.

[0392] In some embodiments, the first operation includes at least one of the following: an operation for activating the AI ​​model; an operation for switching the AI ​​model; and an operation for shutting down the AI ​​model.

[0393] The present disclosure provides a variety of first operations related to AI model processing to determine the processing duration corresponding to the operation, thereby ensuring that the terminal and network device are time-aligned based on the processing duration. This allows the network device or terminal to call the AI ​​model deployed on the other end after the processing duration to perform corresponding processing, thereby improving the operating efficiency of the AI ​​model.

[0394] In some implementations, the first operations are different, and the processing durations corresponding to the first operations are different.

[0395] This disclosure determines different processing times for different first operations related to AI model processing. This ensures that the terminal and network device can be time-aligned based on different processing times for different operations. This allows the network device or terminal to invoke the AI ​​model deployed on the other end after the processing time, thereby improving the operating efficiency of the AI ​​model.

[0396] In some embodiments, the processing duration corresponding to the operation for activating the AI ​​model is greater than or equal to the processing duration corresponding to the operation for switching the AI ​​model; and / or, the processing duration corresponding to the operation for deactivating the AI ​​model is less than or equal to the processing duration corresponding to the operation for switching the AI ​​model.

[0397] This disclosure provides specific processing duration relationships for different first operations related to AI model processing. This ensures that terminals and network devices can time-align different operations based on different processing durations. This allows the network device or terminal to invoke the AI ​​model deployed on the other end after the processing duration, thereby improving the operating efficiency of the AI ​​model.

[0398] In some implementations, the deployment method of the AI ​​model is different, and the processing time corresponding to the first operation is different.

[0399] This disclosure determines different processing times for different AI model deployment methods. This ensures that terminals and network devices can be time-aligned based on different processing times for different operations. This allows the network device or terminal to call the AI ​​model deployed on the other end for corresponding processing after the processing time, thereby improving the operating efficiency of the AI ​​model.

[0400] In some embodiments, the AI ​​model is deployed on a terminal or a network device, and the processing time corresponding to the first operation is the first processing time; and, the AI ​​model is deployed on a terminal and a network device, and the processing time corresponding to the first operation is the second processing time; the processing times corresponding to the first operation are different, including: the first processing time is less than or equal to the second processing time.

[0401] This disclosure provides specific processing duration relationships for different AI model deployment methods. This ensures that terminals and network devices can be time-aligned based on different processing durations for different operations. This allows the network device or terminal to invoke the AI ​​model deployed on the other end after the processing duration, thereby improving the operating efficiency of the AI ​​model.

[0402] In some implementations, the processing time corresponding to the first operation varies depending on the application scenario of the AI ​​model.

[0403] This disclosure determines different processing times for different AI model usage scenarios. This ensures that terminals and network devices can be time-aligned based on different processing times for different operations. This allows the network device or terminal to invoke the AI ​​model deployed on the other end for corresponding processing after the processing time, thereby improving the operating efficiency of the AI ​​model.

[0404] In some embodiments, the AI ​​models occupy different storage spaces, and the processing time corresponding to the first operation is different; or, the AI ​​models have different complexities, and the processing time corresponding to the first operation is different.

[0405] This disclosure can determine different processing times based on the different storage space occupied or complexity of AI models. This ensures that terminals and network devices can be time-aligned based on different processing times for different operations. This allows the network device or terminal to call the AI ​​model deployed on the other end after the processing time, thereby improving the operating efficiency of the AI ​​model.

[0406] In some implementations, the capabilities corresponding to the terminals are different, and the processing durations corresponding to the first operations are different.

[0407] The present disclosure can determine different processing times for different terminal capabilities. This ensures that terminals and network devices can be time-aligned based on different processing times for different operations. This allows the network device or terminal to invoke the AI ​​model deployed on the other end after the processing time has expired to perform corresponding processing, thereby improving the operating efficiency of the AI ​​model.

[0408] In some embodiments, the apparatus 300 further includes: a receiving module 302, configured to receive first information, where the first information is used to indicate a capability corresponding to the terminal and / or a processing duration corresponding to a first operation supported by the capability.

[0409] The network device disclosed herein can receive the terminal's reported capabilities and / or the processing time corresponding to the first operation corresponding to the capabilities, so that the network device can call the AI ​​model deployed on the terminal to perform corresponding processing after the processing time based on the information reported by the terminal, thereby improving the operating efficiency of the AI ​​model.

[0410] In some implementations, the terminal operation states corresponding to the terminals are different, and the processing durations corresponding to the first operations are different.

[0411] The present disclosure can determine different processing times for different terminal states. This ensures that the terminal and network device can be time-aligned based on different processing times for different operations. This allows the network device or terminal to call the AI ​​model deployed on the other end after the processing time, thereby improving the operating efficiency of the AI ​​model.

[0412] In some embodiments, the apparatus 300 further includes: a receiving module 302, configured to receive second information, where the second information is used to indicate a terminal operating state corresponding to the terminal and / or a processing duration corresponding to a first operation supported by the terminal operating state.

[0413] The network device disclosed herein can receive the terminal status reported by the terminal and / or the processing time corresponding to the first operation supported by the terminal status, so that the network device can call the AI ​​model deployed on the terminal to perform corresponding processing after the processing time based on the information reported by the terminal, thereby improving the operating efficiency of the AI ​​model.

[0414] In some embodiments, the processing module 301 is further used to determine third information, where the third information is used to indicate an AI model deployed on a terminal and / or network device, and / or to indicate an application scenario of the AI ​​model.

[0415] The network device disclosed herein can determine the AI ​​model and / or the application scenario of the AI ​​model, so that the network device can call the AI ​​model deployed on the terminal to perform corresponding processing after the processing time based on the above information, thereby improving the operating efficiency of the AI ​​model.

[0416] In some embodiments, the processing module 301 is also used to: perform a second operation based on the processing time corresponding to the first operation, wherein the second operation is used to instruct the network device to use an AI model method or a non-AI model method to process data, and the AI ​​model corresponding to the AI ​​model method is the AI ​​model after the network device performs the first operation.

[0417] In some embodiments, the device 300 also includes: a receiving module 302, which is used to receive fourth information based on the processing time corresponding to the first operation, and the fourth information is used to indicate the second operation, wherein the second operation is used to instruct the network device to use an AI model method or a non-AI model method to process data, and the AI ​​model corresponding to the AI ​​model method is the AI ​​model after the network device performs the first operation.

[0418] It is understood that the apparatus 300 may further include a sending module. It should be understood that the apparatus 200 and the apparatus 300 are not limited to the modules shown in the figures, and may further include other corresponding modules according to actual conditions, which is not limited in the present disclosure.

[0419] Regarding the apparatus in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0420] Figure 12 is a schematic diagram of a communication device according to an exemplary embodiment. For example, device 400 can be any terminal such as 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, etc.

[0421] 12 , device 400 may include one or more of the following components: a processing component 402 , a memory 404 , a power component 406 , a multimedia component 408 , an audio component 410 , an input / output (I / O) interface 412 , a sensor component 414 , and a communication component 416 .

[0422] Processing component 402 generally controls the overall operation of device 400, such as operations associated with display, phone calls, data communications, camera operation, and recording operations. Processing component 402 may include one or more processors 420 to execute instructions to perform all or part of the steps of the above-described method. In addition, processing component 402 may include one or more modules to facilitate interaction between processing component 402 and other components. For example, processing component 402 may include a multimedia module to facilitate interaction between multimedia component 408 and processing component 402.

[0423] The memory 404 is configured to store various types of data to support operations on the device 400. Examples of such data include instructions for any application or method operating on the device 400, contact data, phone book data, messages, pictures, videos, etc. The memory 404 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.

[0424] The power component 406 provides power to the various components of the device 400. The power component 406 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power to the device 400.

[0425] The multimedia component 408 includes a screen that provides an output interface between the device 400 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 touch, slide, 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 408 includes a front camera and / or a rear camera. When the device 400 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 a focal length and optical zoom capability.

[0426] The audio component 410 is configured to output and / or input audio signals. For example, the audio component 410 includes a microphone (MIC) that is configured to receive external audio signals when the device 400 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 404 or transmitted via the communication component 416. In some embodiments, the audio component 410 also includes a speaker for outputting audio signals.

[0427] I / O interface 412 provides an interface between processing component 402 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.

[0428] The sensor assembly 414 includes one or more sensors for providing various aspects of the status assessment of the device 400. For example, the sensor assembly 414 can detect the open / closed state of the device 400, the relative positioning of components, such as the display and keypad of the device 400. The sensor assembly 414 can also detect changes in the position of the device 400 or a component of the device 400, the presence or absence of user contact with the device 400, the orientation or acceleration / deceleration of the device 400, and temperature changes of the device 400. The sensor assembly 414 may include a proximity sensor configured to detect the presence of nearby objects without any physical contact. The sensor assembly 414 may also include a light sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor assembly 414 may also include an accelerometer, a gyroscope sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.

[0429] The communication component 416 is configured to facilitate wired or wireless communication between the device 400 and other devices. The device 400 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 416 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 416 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.

[0430] In an exemplary embodiment, the device 400 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 methods.

[0431] In an exemplary embodiment, a non-transitory computer-readable storage medium including instructions is also provided, such as a memory 404 including instructions, which can be executed by the processor 420 of the device 400 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.

[0432] FIG13 is a schematic diagram of another communication device according to an exemplary embodiment. For example, device 500 may be provided as a base station or a server. Referring to FIG13 , device 500 includes a processing component 522, which further includes one or more processors, and memory resources represented by memory 532 for storing instructions executable by processing component 522, such as applications. The applications stored in memory 532 may include one or more modules, each corresponding to a set of instructions. Furthermore, processing component 522 is configured to execute instructions to perform the above-described method.

[0433] The device 500 may also include a power supply component 526 configured to perform power management of the device 500, a wired or wireless network interface 550 configured to connect the device 500 to a network, and an input / output (I / O) interface 558. The device 500 may operate based on an operating system stored in the memory 532, such as Windows Server™, Mac OS X™, Unix™, Linux™, FreeBSD™, or the like.

[0434] In some embodiments, the present disclosure further provides a communication system including a terminal and a network device. The terminal can execute the methods described in Figures 2 to 5 . The network device can execute the methods described in Figures 6 to 9 . For details, please refer to the description of the above embodiments, and this disclosure will not be repeated here.

[0435] This disclosure determines the processing duration corresponding to operations related to AI model processing, thereby ensuring that the terminal and network device are time-aligned based on the processing duration. This allows the network device or terminal to call the AI ​​model deployed on the other end to perform corresponding processing after the processing duration, thereby improving the operating efficiency of the AI ​​model.

[0436] It is further understood that in this disclosure, "plurality" refers to two or more, and other quantifiers are similar. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, "A and / or B" can mean: A exists alone, A and B exist simultaneously, and B exists alone. The character " / " generally indicates that the related objects 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.

[0437] 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.

[0438] 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 scenarios. For example, the word "in response to" used herein can be interpreted as "at..." or "when..." or "if" or "if".

[0439] 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.

[0440] 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.

[0441] 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. A communication method, characterized in that: The method is executed by a terminal, and includes: Determine the processing time corresponding to the first operation related to the artificial intelligence AI model processing.

2. The method according to claim 1, characterized in that The first operation includes at least one of the following: Actions used to activate AI models; Operations used to switch AI models; Operation used to shut down the AI ​​model.

3. The method according to claim 2, characterized in that The first operations are different, and the processing durations corresponding to the first operations are different.

4. The method according to claim 3, characterized in that The processing time corresponding to the operation for activating the AI ​​model is greater than or equal to the processing time corresponding to the operation for switching the AI ​​model; and / or, The processing duration corresponding to the operation for shutting down the AI ​​model is less than or equal to the processing duration corresponding to the operation for switching the AI ​​model.

5. The method according to claim 1 or 2, characterized in that: The deployment method of the AI ​​model is different, and the processing time corresponding to the first operation is different.

6. The method according to claim 5, characterized in that The AI ​​model is deployed on the terminal or the network device, and the processing duration corresponding to the first operation is a first processing duration; and, the AI ​​model is deployed on the terminal and the network device, and the processing duration corresponding to the first operation is a second processing duration; The processing time corresponding to the first operation is different, including: The first processing duration is less than or equal to the second processing duration.

7. The method according to claim 1 or 2, characterized in that: The application scenarios of the AI ​​model are different, and the processing time corresponding to the first operation is different.

8. The method according to claim 1 or 2, characterized in that: The AI ​​models occupy different storage spaces, and the processing time corresponding to the first operation is different; or, The AI ​​models correspond to different complexities, and the processing times corresponding to the first operations are different.

9. The method according to any one of claims 1 to 8, characterized in that: The capabilities corresponding to the terminals are different, and the processing durations corresponding to the first operations are different.

10. The method according to claim 9, characterized in that The method further comprises: Sending first information, where the first information is used to indicate a capability corresponding to the terminal and / or a processing duration corresponding to the first operation supported by the capability.

11. The method according to claim 1 or 2, characterized in that: The terminal operation states corresponding to the terminals are different, and the processing durations corresponding to the first operations are different.

12. The method according to claim 11, characterized in that The method further comprises: Sending second information, where the second information is used to indicate a terminal operating state corresponding to the terminal and / or a processing duration corresponding to the first operation supported by the terminal operating state.

13. The method according to any one of claims 1 to 12, characterized in that: The method further comprises: Determine third information, where the third information is used to indicate the AI ​​model deployed on the terminal and / or the network device, and / or to indicate an application scenario of the AI ​​model.

14. A communication method, characterized in that: The method is performed by a network device and includes: Determine the processing time corresponding to the first operation related to the artificial intelligence AI model processing.

15. The method according to claim 14, characterized in that The first operation includes at least one of the following: Actions used to activate AI models; Operations used to switch AI models; Operation used to shut down the AI ​​model.

16. The method according to claim 15, characterized in that The first operations are different, and the processing durations corresponding to the first operations are different.

17. The method according to claim 16, characterized in that The processing time corresponding to the operation for activating the AI ​​model is greater than or equal to the processing time corresponding to the operation for switching the AI ​​model; and / or, The processing duration corresponding to the operation for shutting down the AI ​​model is less than or equal to the processing duration corresponding to the operation for switching the AI ​​model.

18. The method according to claim 14 or 15, characterized in that The deployment method of the AI ​​model is different, and the processing time corresponding to the first operation is different.

19. The method according to claim 18, characterized in that The AI ​​model is deployed in the terminal or the network device, and the processing duration corresponding to the first operation is a first processing duration; and, the AI ​​model is deployed in the terminal and the network device, and the processing duration corresponding to the first operation is a second processing duration; The processing time corresponding to the first operation is different, including: The first processing duration is less than or equal to the second processing duration.

20. The method according to claim 14 or 15, characterized in that The application scenarios of the AI ​​model are different, and the processing time corresponding to the first operation is different.

21. The method according to claim 14 or 15, characterized in that The AI ​​models occupy different storage spaces, and the processing time corresponding to the first operation is different; or, The AI ​​models correspond to different complexities, and the processing times corresponding to the first operations are different.

22. The method according to any one of claims 14 to 21, characterized in that: The capabilities corresponding to the terminals are different, and the processing duration corresponding to the first operation is different.

23. The method according to claim 22, characterized in that The method further comprises: First information is received, where the first information is used to indicate a capability corresponding to the terminal and / or a processing duration corresponding to the first operation supported by the capability.

24. The method according to claim 14 or 15, characterized in that The terminal operation status corresponding to the terminal is different, and the processing time corresponding to the first operation is different.

25. The method according to claim 24, characterized in that The method further comprises: Second information is received, where the second information is used to indicate a terminal operating state corresponding to the terminal and / or a processing duration corresponding to the first operation supported by the terminal operating state.

26. The method according to any one of claims 14 to 25, characterized in that: The method further comprises: Determine third information, where the third information is used to indicate the AI ​​model deployed on the terminal and / or the network device, and / or to indicate an application scenario of the AI ​​model.

27. A terminal, characterized in that: The terminal comprises: A processing module is used to determine the processing time corresponding to the first operation related to the artificial intelligence AI model processing.

28. A network device, characterized in that: The network equipment includes: A processing module is used to determine the processing time corresponding to the first operation related to the artificial intelligence AI model processing.

29. A communication device, characterized in that: include: processor; a memory for storing processor-executable instructions; Wherein, the processor is configured to: execute the method described in any one of claims 1 to 13.

30. A communication device, characterized in that: include: processor; a memory for storing processor-executable instructions; Wherein, the processor is configured to: execute the method described in any one of claims 14 to 26.

31. A communication system, characterized in that: The system comprises: A terminal, configured to execute the method according to any one of claims 1 to 13; A network device, configured to execute the method described in any one of claims 14 to 26.

32. A non-transitory computer-readable storage medium, characterized in that: When the instructions in the storage medium are executed by a processor of a terminal, the terminal is enabled to execute the method according to any one of claims 1 to 13.

33. A non-transitory computer-readable storage medium, characterized in that When the instructions in the storage medium are executed by a processor of a network device, the network device is enabled to execute the method according to any one of claims 14 to 26.

Images