Artificial intelligence communication method and device and storage medium

Abstract

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

Description

Artificial intelligence communication method, device and storage medium Technical Field

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

[0002] In recent years, artificial intelligence (AI) technology has achieved continuous breakthroughs in various fields. Among related technologies, AI is being introduced into wireless air interfaces to assist in improving wireless air interface transmission technology. Currently, AI technology is supported for processing within wireless air interfaces, including AI model training and model inference applications.

[0003] Summary of the Invention

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

[0005] According to a first aspect of an embodiment of the present disclosure, an AI communication method is provided. The method is executed by a terminal, and includes: determining a processing time, where the processing time is the time for processing an AI function or an AI model.

[0006] According to a second aspect of an embodiment of the present disclosure, an AI communication method is provided, which is executed by a network device and includes: receiving first information, where the first information is used to determine a processing time, where the processing time is the time for processing an AI function or an AI model.

[0007] According to a third aspect of an embodiment of the present disclosure, there is provided an AI communication device, comprising: a processing module, configured to determine a processing time, wherein the processing time is the time for processing an AI function or an AI model.

[0008] According to a fourth aspect of the fundamentally disclosed embodiment, an AI communication device is provided, comprising: a receiving module for receiving first information, wherein the first information is used to determine a processing time, and the processing time is the time for processing an AI function or an AI model.

[0009] According to a fifth aspect of an embodiment of the present disclosure, an AI communication device is provided, comprising: a processor; and 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.

[0010] According to a sixth aspect of an embodiment of the present disclosure, an AI 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.

[0011] According to a seventh aspect of an embodiment of the present disclosure, an AI communication system is provided, the system including: a terminal for executing the method described in the first aspect or any one of the embodiments of the first aspect; and a network device for executing the method described in the second aspect or any one of the embodiments of the second aspect.

[0012] According to an eighth aspect of an embodiment of the present disclosure, a storage medium is provided. When instructions in the storage medium are executed by a processor of a terminal, the terminal is enabled to execute the method described in the first aspect or any one of the embodiments of the first aspect.

[0013] According to the ninth aspect of the embodiment of the present disclosure, a 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 method described in the second aspect or any one of the embodiments of the second aspect.

[0014] The technical solution provided by the embodiments of the present disclosure may include the following beneficial effects: by determining the processing time, which is the time for processing the AI ​​function or AI model, the time for processing the AI ​​function or AI model can be determined, thereby reducing the complexity of subsequent processing processes based on the AI ​​function or AI model, thereby improving the operating efficiency of the AI ​​function or AI model.

[0015] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] 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.

[0017] Fig. 1 is a schematic diagram of a wireless communication system according to an exemplary embodiment.

[0018] Fig. 2 is a flowchart showing an AI communication method according to an exemplary embodiment.

[0019] Fig. 3 is a flow chart showing another AI communication method according to an exemplary embodiment.

[0020] Fig. 4 is a flow chart showing another AI communication method according to an exemplary embodiment.

[0021] Fig. 5 is a flowchart showing another AI communication method according to an exemplary embodiment.

[0022] Fig. 6 is a flowchart showing another AI communication method according to an exemplary embodiment.

[0023] Fig. 7 is a flowchart showing another AI communication method according to an exemplary embodiment.

[0024] Fig. 8 is a flowchart showing another AI communication method according to an exemplary embodiment.

[0025] Fig. 9 is a flowchart showing another AI communication method according to an exemplary embodiment.

[0026] Fig. 10 is a flowchart showing another AI communication method according to an exemplary embodiment.

[0027] Fig. 11 is a flowchart showing another AI communication method according to an exemplary embodiment.

[0028] Fig. 12 is a flowchart showing another AI communication method according to an exemplary embodiment.

[0029] Fig. 13 is a flowchart showing another AI communication method according to an exemplary embodiment.

[0030] Fig. 14 is a flowchart showing another AI communication method according to an exemplary embodiment.

[0031] Fig. 15 is a flowchart showing another AI communication method according to an exemplary embodiment.

[0032] Fig. 16 is a flowchart showing another AI communication method according to an exemplary embodiment.

[0033] Fig. 17 is a flowchart showing another AI communication method according to an exemplary embodiment.

[0034] Fig. 18 is a flowchart showing another AI communication method according to an exemplary embodiment.

[0035] Fig. 19 is a flowchart showing another AI communication method according to an exemplary embodiment.

[0036] Fig. 20 is a flowchart showing another AI communication method according to an exemplary embodiment.

[0037] FIG21 is a flowchart showing another AI communication method according to an exemplary embodiment.

[0038] Fig. 22 is a flowchart showing another AI communication method according to an exemplary embodiment.

[0039] Fig. 23 is a flowchart showing another AI communication method according to an exemplary embodiment.

[0040] Fig. 24 is a flowchart showing another AI communication method according to an exemplary embodiment.

[0041] Fig. 25 is a flowchart showing another AI communication method according to an exemplary embodiment.

[0042] Fig. 26 is a flowchart showing another AI communication method according to an exemplary embodiment.

[0043] Fig. 27 is a flowchart showing another AI communication method according to an exemplary embodiment.

[0044] Fig. 28 is a flowchart showing another AI communication method according to an exemplary embodiment.

[0045] FIG29 is a flowchart showing another AI communication method according to an exemplary embodiment.

[0046] Fig. 30 is a flowchart showing another AI communication method according to an exemplary embodiment.

[0047] FIG31 is a schematic diagram showing method interaction of an AI communication system according to an exemplary embodiment.

[0048] FIG32 is a block diagram showing an AI communication device according to an exemplary embodiment.

[0049] Fig. 33 is a block diagram showing another AI communication device according to an exemplary embodiment.

[0050] Fig. 34 is a block diagram showing another AI communication device according to an exemplary embodiment.

[0051] Fig. 35 is a block diagram showing another AI communication device according to an exemplary embodiment. DETAILED DESCRIPTION

[0052] 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.

[0053] 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.

[0054] 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.

[0055] 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.

[0056] 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.

[0057] 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.

[0058] 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.

[0059] In recent years, artificial intelligence (AI) technology has achieved continuous breakthroughs in various fields. Among related technologies, AI is being introduced into wireless air interfaces to assist in improving wireless air interface transmission technology. Currently, AI technology is supported for processing within wireless air interfaces, including AI model training and model inference applications.

[0060] In wireless AI research, an AI feature use case refers to a communication scenario in which AI is used to perform a communication operation to achieve a specific purpose. For example, AI feature use cases include:

[0061] -AI-based channel state information (CSI) enhancement

[0062] -AI-based beam management

[0063] -AI-based positioning

[0064] In some scenarios, multiple AI functions are defined for a certain AI feature use case. For example, for beam enhancement, AI function 1 supports the identification (ID) of the predicted optimal beam, and AI function 2 supports the prediction of the optimal beam and the measurement results of the corresponding beam. The implementation of AI functions relies on AI models. Different AI functions may be implemented by different AI models. In addition, the number of AI models corresponding to a certain AI function is also different. This results in different processing times for AI functions or AI models, such as different processing times for activating or switching AI functions or AI models.

[0065] In other scenarios, when an AI model is deployed on a terminal, it registers the AI ​​model with the network device and obtains the AI ​​model ID. However, this AI model ID is specific only to the logical AI model. A logical AI model may have different physical AI models. In other words, the number of physical AI models corresponding to a single AI model ID may also vary. This results in different processing times for AI functions or AI models, such as activating or switching AI functions or AI models.

[0066] However, the relevant technologies lack a clear understanding of the processing time for AI functions or AI models. This clarity is crucial for AI communications based on these functions or models. For example, activating or switching an AI function or AI model requires starting the corresponding software and hardware. Network devices and terminals must specify the processing time and, after this time, invoke the AI ​​model deployed on the other end to implement the corresponding AI function.

[0067] Therefore, the present disclosure provides an artificial intelligence communication method, which determines the processing time of the AI ​​function or AI model by clarifying the processing time of the AI ​​function or AI model, thereby reducing the complexity of the subsequent processing process based on the AI ​​function or AI model. For example, it can ensure that the terminal and network equipment are time-aligned based on the processing duration, and can process the AI ​​model or AI function synchronously to improve the operating efficiency of the AI ​​function or AI model.

[0068] The processing of AI functions or AI models involved in the embodiments of the present disclosure, or the "processing" involved in processing AI functions or AI models may be one or more of activation, switching, configuration, reasoning, etc.

[0069] FIG2 is a flowchart showing an AI communication method according to an exemplary embodiment. As shown in FIG2 , the AI ​​communication method is executed by a terminal, and the method may include the following steps.

[0070] In step S11 , a processing time is determined, where the processing time is the time required to process the AI ​​function or AI model.

[0071] In one embodiment, the terminal may determine a processing time for processing an AI function or an AI model.

[0072] For example, the time to process an AI function. Since the AI ​​models corresponding to different AI functions may be different, and the number of AI models corresponding to different AI functions may also be different. Therefore, the time to process different AI functions is also different. In some cases, the more AI models corresponding to an AI function, the longer the processing time may be for processing the AI ​​function. In other cases, the AI ​​model corresponding to the AI ​​function is complex, and the processing time may be longer than that of an AI function with a simple corresponding AI model. The processing time of AI functions in different situations may be different, and this disclosure does not limit it. In this embodiment, the terminal can determine the processing time of different AI functions.

[0073] Another example is the time it takes to process an AI model. Because different AI model IDs correspond to different numbers of physical AI models, in some cases, the more physical AI models an AI model ID corresponds to, the longer the AI ​​model processing time may be. The processing time of different AI models may also vary. In this embodiment, the terminal can determine the processing time of different AI models.

[0074] For another example, the same AI function or AI model may have different processing times due to different environments, such as being deployed on different terminals. In this embodiment, the terminal can determine the processing time of the same AI function or AI model.

[0075] The present disclosure determines the processing time to determine the time for processing an AI function or AI model, thereby reducing the complexity of subsequent processing processes based on the AI ​​function or AI model, thereby improving the operating efficiency of the AI ​​function or AI model.

[0076] In one embodiment, the AI ​​communication method provided in the embodiment of the present disclosure can process AI functions or AI models based on processing time.

[0077] FIG3 is a flowchart showing an AI communication method according to an exemplary embodiment. As shown in FIG3 , the AI ​​communication method is executed by a terminal, and the method may include the following steps.

[0078] In step S21 , the AI ​​function or AI model is processed based on the processing time.

[0079] The processing time is the time it takes to process the AI ​​function or AI model. In one embodiment, the terminal may process the AI ​​function or AI model based on the determined processing time. During the processing time, the terminal may perform the corresponding processing on the AI ​​function or AI model. After the processing time, the terminal may be deemed to have completed the corresponding processing on the AI ​​function or AI model.

[0080] For example, taking the activation time for activating a certain AI function as an example, the terminal can determine the activation time for activating the AI ​​function. When the user invokes the AI ​​function, the terminal activates the AI ​​function based on the determined activation time. After the activation time has elapsed, the AI ​​function activation is considered complete, and the user can use the AI ​​function.

[0081] FIG4 is a flowchart showing an AI communication method according to an exemplary embodiment. As shown in FIG4 , the AI ​​communication method is executed by a terminal, and the method may include the following steps.

[0082] In step S31 , a processing time is determined, where the processing time is the time required to process the AI ​​function or AI model.

[0083] In step S32 , the AI ​​function or AI model is processed based on the processing time.

[0084] In this embodiment, the terminal can determine the processing time and then perform corresponding processing on the AI ​​function or AI model based on the processing time. The present disclosure determines the processing time of different AI functions or AI models and processes the AI ​​functions or AI models based on the processing time, thereby determining the time for processing the AI ​​function or AI model, thereby reducing the complexity of subsequent processing based on the AI ​​function or AI model, and improving the operating efficiency of the AI ​​function or AI model.

[0085] In some embodiments, in the AI ​​communication method provided by the present disclosure, the processing time of different AI functions or different AI models is the same.

[0086] In one embodiment, the terminal may determine that the processing times of different AI functions or different AI models are the same. That is, the processing times of different AI functions or different AI models are determined to be the same processing time. Compared to determining the processing time for each different AI function or AI model, this embodiment can improve efficiency.

[0087] In one implementation, FIG5 is a flowchart of an AI communication method according to an exemplary embodiment. As shown in FIG5 , the AI ​​communication method is executed by a terminal, and the method may include the following steps.

[0088] In step S41 , it is determined that the processing times of different AI functions or different AI models are the same.

[0089] In some cases, taking AI functions as an example, the terminal can determine the processing time of different AI functions based on the most complex AI function among the different AI functions. Since the more complex the AI ​​function, the longer its processing time is. Therefore, the processing time determined based on the most complex AI function can often be applied to other AI functions with relatively lower complexity among the above different AI models.

[0090] It can be understood that the processing time determined based on the most complex AI function among different AI functions can ensure that the corresponding processing of the above-mentioned AI function with the highest complexity is completed within the processing time. At the same time, it can also ensure as much as possible that the corresponding processing of other AI functions with relatively low complexity is completed within the processing time.

[0091] It is further understandable that, still taking the AI ​​function as an example, the terminal can also determine the processing time of different AI functions based on the AI ​​function with relatively high complexity among different AI functions, but not the highest. By determining the processing time of different AI functions based on the AI ​​function with relatively high complexity among different AI functions, it can be ensured as much as possible that most of the above-mentioned different AI functions can complete the corresponding processing within the processing time. At the same time, since the complexity is not the highest, the processing time will not be too long, thereby improving efficiency. For example, when processing an AI function with lower complexity among different AI functions, it may only take a very short time to complete the corresponding processing. However, since the determined processing time is based on the AI ​​function with the highest complexity, the processing time is too long, resulting in that even if the corresponding processing of the AI ​​function has been completed, it is still necessary to wait for the processing time before continuing other processing, which wastes time and reduces efficiency.

[0092] In other cases, still taking the AI ​​function as an example, the terminal may also determine the processing time of different AI functions based on the most frequently used AI function among the different AI functions.

[0093] It is understandable that in this embodiment, the AI ​​function is used for explanation, but the implementation methods involved are also applicable to AI models, and this disclosure does not limit them.

[0094] In some implementations, the terminal may process different AI functions or AI models based on the same determined processing time.

[0095] In some implementations, FIG6 is a flowchart illustrating an AI communication method according to an exemplary embodiment. As shown in FIG6 , the AI ​​communication method is executed by a terminal, and the method may include the following steps.

[0096] In step S51 , it is determined that the processing times of different AI functions or different AI models are the same.

[0097] In step S52 , different AI functions or different AI models are processed based on the determined same processing time.

[0098] The processing time includes, for example, the activation time of an AI function or AI model, the switching time of an AI function or AI model, and the time to switch from a non-AI state to an AI state. The processing time for different AI functions or different AI models can be defined separately.

[0099] The execution process of step S51 in this embodiment is similar to that of step S41 and will not be repeated here.

[0100] The present disclosure improves efficiency by ensuring that the processing times of different AI functions or AI models are the same. By processing different AI functions or AI models based on the determined processing times, the complexity of the processing is reduced, thereby improving the operating efficiency of the AI ​​functions or AI models.

[0101] In some embodiments, in the AI ​​communication method provided by the present disclosure, the processing time of different AI functions or different AI models of the same terminal is the same.

[0102] In one embodiment, the terminal may determine that the processing times of different AI functions or different AI models of the same terminal are the same. It can be considered that since the terminals are the same, the software environment and hardware environment of the different AI functions or AI models are the same. Therefore, the terminal determines the processing times of the different AI functions or different AI models of the same terminal as the same processing time.

[0103] In one implementation, FIG7 is a flowchart of an AI communication method according to an exemplary embodiment. As shown in FIG7 , the AI ​​communication method is executed by a terminal, and the method may include the following steps.

[0104] In step S61 , it is determined that the processing times of different AI functions or different AI models of the same terminal are the same.

[0105] For example, different terminals have different computing power and storage space. Processing AI functions or AI models requires the support of the terminal's computing power and storage space. Computing power can be understood as the terminal's processing capabilities. It can be assumed that the higher the terminal's computing power and the larger its storage space, the shorter the processing time required to process the AI ​​function or AI model. In other words, the computing power and storage space of a terminal affect the time it takes to process the AI ​​function or AI model. The computing power and storage space of the same terminal are the same. Therefore, the terminal can ensure that the processing time for different AI functions or different AI models on the same terminal is the same, which can improve efficiency.

[0106] In some implementations, the terminal may process different AI functions or different AI models of the same terminal based on the same determined processing time.

[0107] In some implementations, FIG8 is a flowchart illustrating an AI communication method according to an exemplary embodiment. As shown in FIG8 , the AI ​​communication method is executed by a terminal, and the method may include the following steps.

[0108] In step S71 , it is determined that the processing times of different AI functions or different AI models of the same terminal are the same.

[0109] In step S72 , different AI functions or different AI models of the same terminal are processed based on the determined same processing time.

[0110] The execution process of step S71 and step S61 in this embodiment is similar and will not be repeated here.

[0111] The present disclosure improves efficiency by ensuring that different AI functions or AI models on the same terminal have the same processing time. By processing different AI functions or AI models based on the determined processing time, the complexity of the processing process is reduced, thereby improving the operating efficiency of the AI ​​functions or AI models.

[0112] In some embodiments, in the artificial intelligence communication method provided by the present disclosure, the processing time of different AI functions or different AI models corresponding to the same AI feature use case of the same terminal is the same.

[0113] In one embodiment, the terminal may determine that the processing time of different AI functions or different AI models corresponding to the same AI feature use case of the same terminal is the same. The AI ​​feature use case is a communication scenario that achieves its corresponding purpose based on a communication operation. For example, AI is used to predict channel information in the time domain. For another example, beam management in the spatial domain can be performed based on AI. The AI ​​feature use case includes at least one AI function or AI model. The AI ​​functions or AI models corresponding to the same AI feature use case have similarities. Specifically, taking AI-based beam management as an example, AI-based beam management includes multiple AI functions. For example, AI function 1 may be measuring the best beam ID, and AI function 2 may be predicting the best beam and the measurement result of the corresponding beam. It can be considered that the above-mentioned AI function 1 and AI function 2 are similar. Since there may be similarities between the AI ​​functions or AI models of the same AI feature use case, the terminal may determine that the processing time of different AI functions or AI models of the same AI feature use case of the same terminal is the same.

[0114] In one implementation, FIG9 is a flowchart of an AI communication method according to an exemplary embodiment. As shown in FIG9 , the AI ​​communication method is executed by a terminal, and the method may include the following steps.

[0115] In step S81, it is determined that the processing times of different AI functions or different AI models corresponding to the same AI feature use case of the same terminal are the same.

[0116] In this embodiment, the terminal may determine the AI ​​feature use case of the same terminal, and for the AI ​​feature use case, determine that the processing time of different AI functions or different AI models corresponding to the AI ​​feature use case is the same.

[0117] In some implementations, the terminal may process different AI functions or different AI models corresponding to the same AI feature use case of the same terminal based on the determined same processing time.

[0118] In some implementations, FIG10 is a flowchart illustrating an AI communication method according to an exemplary embodiment. As shown in FIG10 , the AI ​​communication method is executed by a terminal, and the method may include the following steps.

[0119] In step S91 , it is determined that the processing times of different AI functions or different AI models corresponding to the same AI feature use case of the same terminal are the same.

[0120] In step S92, based on the determined same processing time, different AI functions or different AI models corresponding to the same AI feature use case of the same terminal are processed.

[0121] The execution process of step S91 in this embodiment is similar to that of step S81 and will not be repeated here.

[0122] By determining that the processing time for different AI functions or different AI models corresponding to the same AI feature use case on the same terminal is the same, the present disclosure is more targeted and the processing time determined is more accurate. By processing different AI functions or AI models corresponding to the same AI feature use case on the same terminal based on the determined processing time, the complexity of the processing process is reduced, thereby improving the operating efficiency of the AI ​​functions or AI models.

[0123] In some embodiments, in the artificial intelligence communication method provided by the present disclosure, the processing time of different AI functions or different AI models in the same deployment mode of the same terminal is the same.

[0124] In one embodiment, the terminal may determine that the processing time of different AI functions or different AI models in the same deployment mode of the same terminal is the same.

[0125] Among them, the deployment methods of AI functions or AI models include unilateral deployment and bilateral deployment. Taking the AI ​​model as an example, the one-sided deployment model refers to deployment on one device. For example, the AI ​​model is deployed on a terminal or network device. The two-sided deployment model means that part of the AI ​​model is deployed on the terminal and the other part is deployed on the network device. For example, the AI ​​functions or AI models corresponding to AI feature use cases such as AI-based positioning and AI-based beam management are usually deployed in a unilateral manner. AI-based CSI compression usually adopts a bilateral deployment method.

[0126] It is understandable that the deployment methods corresponding to the above-mentioned AI feature use cases are only exemplary, and this disclosure does not limit the specific deployment method adopted by the AI ​​feature use cases.

[0127] In this embodiment, different deployment methods affect the time required to process an AI function or AI model. Often, AI functions or AI models with the same deployment method have relatively similar processing times. Therefore, the terminal can determine that the processing times of different AI functions or different AI models with the same deployment method on the same terminal are the same.

[0128] In one implementation, FIG11 is a flowchart of an AI communication method according to an exemplary embodiment. As shown in FIG11 , the AI ​​communication method is executed by a terminal, and the method may include the following steps.

[0129] In step S101 , it is determined that the processing times of different AI functions or different AI models in the same deployment mode of the same terminal are the same.

[0130] In this embodiment, the terminal can determine the deployment mode of the same terminal, including unilateral deployment or bilateral deployment. This can determine the AI ​​functions or AI models with the same deployment mode. For AI functions or AI models with the same deployment mode, their processing time is determined to be the same.

[0131] For example, for an AI function or AI model deployed unilaterally on the same terminal, its processing time is determined to be time 1. For an AI function or AI model deployed bilaterally on the same terminal, its processing time is determined to be time 2. Of course, the aforementioned AI function or AI model deployed bilaterally on the same terminal may also determine its processing time to be time 1, and this disclosure is not limited thereto.

[0132] For another example, for the same terminal, the deployment method is to deploy the AI ​​function or AI model on the terminal, and its processing time is determined to be time 3. For the same terminal, the deployment method is to deploy the AI ​​function or AI model on the network device, and its processing time is determined to be time 4. Of course, for the above-mentioned AI function or AI model deployed on the same terminal, its processing time can also be determined to be time 3, and this disclosure is not limited to this.

[0133] It can be understood that time 1, time 2, time 3 and time 4 in this embodiment are described as examples and do not represent specific times, and this disclosure does not make specific limitations on this.

[0134] In some implementations, the terminal may process different AI functions or different AI models in the same deployment mode of the same terminal based on the same determined processing time.

[0135] In some implementations, FIG12 is a flowchart illustrating an AI communication method according to an exemplary embodiment. As shown in FIG12 , the AI ​​communication method is executed by a terminal, and the method may include the following steps.

[0136] In step S111 , it is determined that the processing times of different AI functions or different AI models in the same deployment mode of the same terminal are the same.

[0137] In step S112, based on the determined same processing time, different AI functions or different AI models of the same terminal with the same deployment mode are processed.

[0138] The execution process of step S111 in this embodiment is similar to that of step S101 and will not be repeated here.

[0139] The present disclosure determines that the processing time for different AI functions or different AI models corresponding to the same deployment method on the same terminal is the same, making the determined processing time more targeted and accurate. By processing different AI functions or AI models corresponding to the same deployment method on the same terminal based on the determined processing time, the complexity of the processing process is reduced, thereby improving the operating efficiency of the AI ​​functions or AI models.

[0140] In some embodiments, in the artificial intelligence communication method provided by the present disclosure, different AI functions or different AI models have different processing times.

[0141] In one embodiment, the terminal may also determine that the processing time of different AI functions or different AI models is different. That is, the processing time is determined for each AI function or AI model. In this embodiment, the processing time of the AI ​​function or AI model can be determined in a targeted manner.

[0142] In one implementation, FIG13 is a flowchart of an AI communication method according to an exemplary embodiment. As shown in FIG13 , the AI ​​communication method is executed by a terminal, and the method may include the following steps.

[0143] In step S121 , it is determined that the processing times of different AI functions or different AI models are different.

[0144] In this embodiment, the terminal can determine the processing time for different AI functions or AI models. Taking AI functions as an example, the terminal can determine the processing time for each different AI function based on the complexity of the AI ​​function, the deployment method of the AI ​​function, the number of AI models corresponding to the AI ​​function, etc. Alternatively, taking AI models as an example, the terminal can also determine the processing time for each different AI model based on the complexity of the AI ​​model, the deployment method of the AI ​​model, the number of physical AI models corresponding to the AI ​​model ID, etc.

[0145] In some implementations, the terminal may process different AI functions or different AI models respectively based on the determined different processing times.

[0146] In some implementations, FIG14 is a flowchart of an AI communication method according to an exemplary embodiment. As shown in FIG14 , the AI ​​communication method is executed by a terminal, and the method may include the following steps.

[0147] In step S131, it is determined that the processing time of different AI functions or different AI models is different.

[0148] In step S132 , different AI functions or different AI models are processed based on the determined different processing times.

[0149] The execution process of step S131 and step S121 in this embodiment is similar and will not be repeated here.

[0150] By determining that different AI functions or AI models have different processing times, the present disclosure enables targeted determination of processing times for different AI functions or AI models, resulting in more accurate processing times. By processing different AI functions or AI models based on the determined processing times, the complexity of the processing process is reduced, thereby improving the operational efficiency of the AI ​​functions or AI models.

[0151] In some embodiments, in the artificial intelligence communication method provided by the present disclosure, different AI functions or different AI models of different terminals have different processing times.

[0152] In one embodiment, for different AI functions or different AI models on different terminals, since the corresponding terminals are different, their software and hardware environments can be considered to be different. The terminals can determine that the processing time of different AI functions or different AI models on different terminals is different. That is, the processing time of different AI functions or different AI models on different terminals is determined separately.

[0153] In one implementation, FIG15 is a flowchart of an AI communication method according to an exemplary embodiment. As shown in FIG15 , the AI ​​communication method is executed by a terminal, and the method may include the following steps.

[0154] In step S141 , it is determined that different AI functions or different AI models of different terminals have different processing times.

[0155] In this embodiment, since the computing power, storage space, etc. of different terminals are different, the terminals can determine the processing time for different AI functions or different AI models of different terminals respectively.

[0156] In some implementations, the terminal may process different AI functions or different AI models of different terminals respectively based on the determined different processing times.

[0157] In some implementations, FIG16 is a flowchart illustrating an AI communication method according to an exemplary embodiment. As shown in FIG16 , the AI ​​communication method is executed by a terminal, and the method may include the following steps.

[0158] In step S151 , it is determined that different AI functions or different AI models of different terminals have different processing times.

[0159] In step S152 , different AI functions or different AI models of different terminals are processed based on the determined different processing times.

[0160] The execution process of step S151 and step S141 in this embodiment is similar and will not be repeated here.

[0161] By determining that different AI functions or AI models on different terminals have different processing times, the present disclosure can specifically determine the processing times of different AI functions or AI models, making the processing times more accurate. By processing different AI functions or AI models on different terminals based on the determined processing times, the complexity of the processing process is reduced, thereby improving the operating efficiency of the AI ​​functions or AI models.

[0162] In some embodiments, in the artificial intelligence communication method provided by the present disclosure, different AI feature use cases of the same terminal correspond to different AI functions or different AI models with different processing times.

[0163] In one embodiment, for the same terminal, there are large differences in the AI ​​functions or AI models corresponding to different AI feature use cases. Therefore, the terminal can determine that the processing time of different AI functions or different AI models corresponding to the AI ​​feature use cases of the same terminal is different.

[0164] In one implementation, FIG17 is a flowchart of an AI communication method according to an exemplary embodiment. As shown in FIG17 , the AI ​​communication method is executed by a terminal, and the method may include the following steps.

[0165] In step S161 , it is determined that different AI functions or different AI models corresponding to different AI feature use cases of the same terminal have different processing times.

[0166] In this embodiment, the terminal determines the AI ​​function or AI model corresponding to each AI feature use case for different AI feature use cases of the same terminal, and determines the processing time of different AI functions or different AI models corresponding to different AI use cases.

[0167] In some implementations, the terminal may process different AI functions or different AI models corresponding to different AI feature use cases of the same terminal based on the determined different processing times.

[0168] In some implementations, FIG18 is a flowchart of an AI communication method according to an exemplary embodiment. As shown in FIG18 , the AI ​​communication method is executed by a terminal, and the method may include the following steps.

[0169] In step S171 , it is determined that different AI functions or different AI models corresponding to different AI feature use cases of the same terminal have different processing times.

[0170] In step S172 , based on the determined different processing times, different AI functions or different AI models corresponding to different AI feature use cases of the same terminal are processed.

[0171] The execution process of step S171 in this embodiment is similar to that of step S161 and will not be repeated here.

[0172] The present disclosure determines that the processing times for different AI functions or different AI models corresponding to different AI feature use cases on the same terminal are different, making the determined processing times more targeted and accurate. By processing different AI functions or AI models corresponding to different AI feature use cases on the same terminal based on the determined processing times, the complexity of the processing process is reduced, thereby improving the operating efficiency of the AI ​​functions or AI models.

[0173] In some embodiments, in the artificial intelligence communication method provided by the present disclosure, the processing time of different AI functions or different AI models in different deployment modes of the same terminal is different.

[0174] In one embodiment, because different deployment methods affect the time required to process an AI function or AI model, the terminal can determine that the processing time of different AI functions or different AI models in different deployment methods of the same terminal is different. In other words, the processing time of the AI ​​functions or AI models in different deployment methods of the same terminal can be determined separately.

[0175] For example, for different AI functions deployed unilaterally, the processing time is determined as Time 1. For different AI functions deployed bilaterally, the processing time is determined as Time 2, with Time 1 and Time 2 being different. In other words, different processing times are determined for AI functions deployed differently, enabling more targeted and accurate determination of the processing time for each AI function.

[0176] In one implementation, FIG19 is a flowchart of an AI communication method according to an exemplary embodiment. As shown in FIG19 , the AI ​​communication method is executed by a terminal, and the method may include the following steps.

[0177] In step S181 , it is determined that the processing times of different AI functions or different AI models in different deployment modes of the same terminal are different.

[0178] In this embodiment, the terminal can determine the deployment mode of different AI functions or AI models based on the fact that different AI functions or AI models are the same. For each deployment mode, the processing time of the corresponding different AI functions or AI models is determined respectively.

[0179] In some implementations, the terminal may process different AI functions or different AI models of the same terminal in different deployment modes based on the determined different processing times.

[0180] FIG20 is a flowchart showing an AI communication method according to an exemplary embodiment. As shown in FIG20 , the AI ​​communication method is executed by a terminal, and the method may include the following steps.

[0181] In step S191 , it is determined that processing times of different AI functions or different AI models in different deployment modes of the same terminal are different.

[0182] In step S192, based on the determined different processing times, different AI functions or different AI models of different deployment modes of the same terminal are processed. The execution process of step S191 in this embodiment is similar to that of step S181 and will not be repeated here.

[0183] The present disclosure determines that the processing times for different AI functions or different AI models corresponding to different deployment methods of the same terminal are different, making the determined processing times more targeted and accurate. By processing different AI functions or AI models corresponding to different deployment methods of the same terminal based on the determined processing times, the complexity of the processing process is reduced, thereby improving the operating efficiency of the AI ​​functions or AI models.

[0184] In some embodiments, in the artificial intelligence communication method provided by the present disclosure, the processing time of the same AI function or the same AI model of different terminals is the same; or, the processing time of the same AI function or the same AI model of different terminals is different.

[0185] In one embodiment, in some cases, the processing time for the same AI function or the same AI model on different terminals can be determined to be the same. That is, regardless of the terminal corresponding to the AI ​​function or AI model, the same processing time can be determined. This can save time in determining the same AI function or the same AI model on different terminals, improving efficiency. In other cases, the processing time for the same AI function or the same AI model on different terminals can also be determined to be different. Because the computing power, storage space, etc. of different terminals are different, even if it is the same AI function or AI model, the processing time required for different terminals to process it is different. Therefore, the terminal can determine the processing time for the same AI function or AI model on different terminals separately. The processing time of the same AI function or AI model on each terminal is determined in a targeted manner, and the processing time is more accurate.

[0186] In some implementations, FIG21 is a flowchart of an AI communication method according to an exemplary embodiment. As shown in FIG21 , the AI ​​communication method is executed by a terminal, and the method may include the following steps.

[0187] In step S201 , it is determined that the processing time of the same AI function or the same AI model of different terminals is the same.

[0188] In this embodiment, a terminal determines a processing time for a certain AI function or AI model, and further determines that the processing time of the AI ​​function or AI model is the same across different terminals.

[0189] In some implementations, the terminal may process the same AI function or the same AI model on different terminals based on the determined same processing time.

[0190] In one implementation, FIG22 is a flowchart of an AI communication method according to an exemplary embodiment. As shown in FIG22 , the AI ​​communication method is executed by a terminal, and the method may include the following steps.

[0191] In step S211 , it is determined that the processing time of the same AI function or the same AI model of different terminals is the same.

[0192] In step S212 , the same AI function or the same AI model of different terminals is processed based on the determined same processing time.

[0193] The execution process of step S211 in this embodiment is similar to that of step S201 and will not be repeated here.

[0194] In some implementations, FIG23 is a flowchart illustrating an AI communication method according to an exemplary embodiment. As shown in FIG23 , the AI ​​communication method is executed by a terminal, and the method may include the following steps.

[0195] In step S221 , it is determined that the processing times of the same AI function or the same AI model of different terminals are different.

[0196] In this embodiment, the terminal may determine different terminals corresponding to the same AI function or AI model. For each terminal, the processing time of the same AI function or AI model is determined. For example, the processing time of the same AI function or AI model may be determined based on the computing power of different terminals. For another example, the terminal may also determine the processing time of the same AI function or AI model based on the storage space of different terminals. The above-mentioned determination of the processing time of the same AI function or AI model based on the computing power and / or storage space of different terminals is only exemplary, and this disclosure does not limit this.

[0197] In some implementations, FIG24 is a flowchart of an AI communication method according to an exemplary embodiment. As shown in FIG24 , the AI ​​communication method is executed by a terminal, and the method may include the following steps.

[0198] In step S231 , it is determined that the processing times of the same AI function or the same AI model of different terminals are different.

[0199] In step S232 , the same AI function or the same AI model of different terminals is processed based on the determined different processing times.

[0200] The execution process of step S231 in this embodiment is similar to that of step S221 and will not be repeated here.

[0201] The present disclosure can improve efficiency by determining whether the processing time of the same AI function or the same AI model on different terminals is the same or different, or can more accurately determine the processing time of the same AI function or AI model on each terminal. Based on the determined processing time, the same AI function or the same AI model on different terminals is processed, reducing the complexity of the processing process and improving the operating efficiency of the AI ​​function or AI model.

[0202] In some embodiments, in the artificial intelligence communication method provided by the present disclosure, the processing of the AI ​​function or AI model includes at least one of the following: activation of the AI ​​function or AI model, switching of the AI ​​function or AI model, configuration of the AI ​​function or AI model, and reasoning of the AI ​​function or AI model.

[0203] Activating an AI function or AI model can be understood as starting a certain AI function or AI model. Switching an AI function or AI model can be understood as switching the current AI function or AI model to a target AI function or AI model, or activating an AI function or target AI model so that the terminal switches from a non-AI state to an AI state. Configuring an AI function or AI model can be understood as configuring the environment for the AI ​​function or AI model. Reasoning an AI function or AI model can be understood as the process of using data to predict or infer an AI function or AI model.

[0204] In this implementation, the terminal may determine the processing time for performing any of the above-mentioned processing on the AI ​​function or AI model.

[0205] The present disclosure determines the processing time to determine the time for processing the AI ​​function or AI model, thereby reducing the complexity of the subsequent processing process based on the AI ​​function or AI model, thereby improving the operating efficiency of the AI ​​function or AI model.

[0206] In some embodiments, in the artificial intelligence communication method provided herein, processing includes at least one of the following: activation of an AI function or AI model, or switching of an AI function or AI model. Processing time is determined based on a target model, or based on the target model and a currently used model.

[0207] In one embodiment, the activation time of an AI function or AI model and the switching time of the AI ​​function or AI model may be determined based on a target model, which is the activated AI model or the switched AI model.

[0208] FIG25 is a flowchart of an AI communication method according to an exemplary embodiment. As shown in FIG25 , the AI ​​communication method is executed by a terminal, and the method may include the following steps.

[0209] In step S241 , the processing time is determined based on the target model.

[0210] For example, the terminal activates a target model, and the activation time is determined based on the target model. In some cases, the time to activate the target model can be determined based on the complexity of the target model. The target model is an activated AI model. In other cases, the terminal activates the target model and switches from a non-AI state to an AI state. The time at which the terminal switches from the non-AI state to the AI ​​state can also be determined based on the target model. Specifically, the time at which the terminal switches from the non-AI state to the AI ​​state can be determined based on the activation time of the target model.

[0211] For another example, when switching from the currently used AI model to the target model, the switching time can be determined based on the target model. The target model is the AI ​​model after switching. In some cases, the time to switch from the currently used AI model to the target model can be determined based on the complexity of the target model. In other cases, since switching from the currently used AI model to the target model requires activation of the target model, the terminal can determine the time to switch from the currently used AI model to the target model based on the activation time of the target model.

[0212] In one embodiment, the activation time of an AI function or AI model and the switching time of the AI ​​function or AI model can be determined based on a target model and a currently used model. The target model is the activated AI model or the switched AI model.

[0213] FIG26 is a flowchart showing an AI communication method according to an exemplary embodiment. As shown in FIG26 , the AI ​​communication method is executed by a terminal, and the method may include the following steps.

[0214] In step S251 , the processing time is determined based on the target model and the current usage model.

[0215] For example, when switching from the currently used AI model to the target model, the switching time can be determined based on the currently used model and the target model. In some cases, the terminal can determine the time to switch from the currently used AI model to the target model based on the complexity of the currently used model and the target model. Specifically, the time to switch from the currently used AI model to the target model can be determined based on the more complex model between the currently used model and the target model. In other cases, the terminal can determine the time to switch from the currently used AI model to the target model based on the time when the currently used model is turned off and the time when the target model is activated. Specifically, the time to switch from the currently used AI model to the target model can be determined based on the larger value of the time when the currently used model is turned off and the time when the target model is activated.

[0216] It can be understood that the above-mentioned determination of the time to activate the target model based on the complexity of the target model is only an illustrative example. This disclosure does not limit how the terminal determines the activation time of the AI ​​model, the switching time of the AI ​​model, etc. based on the target model.

[0217] The present disclosure determines the processing time of an AI function or an AI model by determining the processing time based on a target model, or determining the time of an AI function or an AI model based on a currently used model and a target model, thereby reducing the complexity of subsequent processing processes based on the AI ​​function or the AI ​​model and improving the operating efficiency of the AI ​​function or the AI ​​model.

[0218] In some embodiments, in the artificial intelligence communication method provided herein, a first portion of an AI function or AI model is deployed on a terminal, and a second portion is deployed on a network device. The processing time is determined based on the processing time of the first portion of the AI ​​function or AI model. Alternatively, the processing time may be determined based on the processing time of the second portion of the AI ​​function or AI model.

[0219] FIG27 is a flowchart of an AI communication method according to an exemplary embodiment. As shown in FIG27 , the AI ​​communication method is executed by a terminal, and the method may include the following steps.

[0220] In step S261 , the processing time is determined based on the processing time of the first portion of the AI ​​function or AI model, and / or the processing time is determined based on the processing time of the second portion of the AI ​​function or AI model.

[0221] In one embodiment, if the deployment mode of the AI ​​function or AI model is bilateral deployment, the processing time of the AI ​​function or AI model can be determined based on the first part of the AI ​​function or AI model deployed on the terminal.

[0222] For example, if the activation time of the first part of the AI ​​function or AI model is time 1, then the activation time of the AI ​​function or AI model can be determined based on the activation time of the first part of the AI ​​function or AI model, that is, determined as time 1.

[0223] In one embodiment, the terminal may also determine the processing time of the AI ​​function or AI model based on the second part of the AI ​​function or AI model deployed on the network device.

[0224] For example, if the activation time of the second AI function or AI model is time 2, the activation time of the AI ​​function or AI model can be determined based on the activation time of the second AI function or AI model, that is, determined as time 2.

[0225] In one implementation, the terminal may also determine the processing time of the AI ​​function or AI model based on the first and second parts of the AI ​​function or AI model.

[0226] For example, the terminal may determine the processing time according to the larger value of time 1 and time 2.

[0227] The present disclosure determines the processing time based on the processing time of the first part of the AI ​​function or AI model, and / or determines the processing time based on the processing time of the second part of the AI ​​function or AI model, and can flexibly determine the processing time of the AI ​​function or AI model.

[0228] In some embodiments, FIG28 is a flowchart of an AI communication method according to an exemplary embodiment. As shown in FIG28 , the AI ​​communication method is executed by a terminal, and the method may include the following steps.

[0229] In step S271, first information is sent, where the first information is used by the network device to determine a processing time.

[0230] In one embodiment, the terminal may send first information to the network device, where the first information includes the processing time, so that the network device can determine the processing time and ensure time alignment between the terminal and the network device.

[0231] In this embodiment, taking the activation of an AI function as an example, the terminal determines the activation time for the AI ​​function and sends first information containing the time to the network device. This allows the network device to determine the activation time for the AI ​​function. After the time has elapsed, the terminal and the network device can simultaneously determine that the AI ​​function activation is complete. This allows them to perform other processing on the AI ​​function.

[0232] By sending the first information, the present disclosure can ensure that the terminal and the network device are time-aligned based on the processing duration, and can synchronously process the AI ​​model or AI function to improve the operating efficiency of the AI ​​function or AI model.

[0233] In some embodiments, in the artificial intelligence communication method provided by the present disclosure, processing time corresponds to different AI models or AI functions.

[0234] In this embodiment, the first information sent by the terminal includes processing time, and the processing time corresponds to different AI functions or AI models. That is, the processing time corresponding to different AI functions or AI models is the same. Therefore, the processing time in the first information can be used by the network device to determine the processing time of different AI functions or AI models.

[0235] By sending the first information, the present disclosure can ensure that the terminal and the network device are time-aligned based on the processing duration, and can synchronously process the AI ​​model or AI function to improve the operating efficiency of the AI ​​function or AI model.

[0236] In some embodiments, in the artificial intelligence communication method provided by the present disclosure, the first information includes information for indicating an AI function or an AI model, and a processing time corresponding to the AI ​​function or the AI ​​model.

[0237] In this embodiment, the first information includes the processing times corresponding to different AI functions or AI models. That is, different AI functions or AI models have different processing times. Therefore, the network device can determine the processing times corresponding to different AI functions or AI models based on the information indicating the AI ​​function or AI model in the first information and the processing times corresponding to the AI ​​function or AI model.

[0238] By sending the first information, the present disclosure can ensure that the terminal and the network device are time-aligned based on the processing duration, and can synchronously process the AI ​​model or AI function to improve the operating efficiency of the AI ​​function or AI model.

[0239] Based on the same concept, the present disclosure also provides an AI communication method, which is executed by a network device.

[0240] FIG29 is a flowchart showing an AI communication method according to an exemplary embodiment. As shown in FIG29 , the method includes the following steps.

[0241] In step S281, first information is received.

[0242] In one embodiment, a network device receives first information sent by a terminal. The first information includes a processing time of an AI function or an AI model, which is used by the network device to determine the processing time of the AI ​​function or the AI ​​model. That is, the network device can determine the processing time of the AI ​​function or the AI ​​model based on the first information.

[0243] In some embodiments, FIG30 is a flowchart of an AI communication method according to an exemplary embodiment. As shown in FIG30 , the AI ​​communication method is executed by a terminal, and the method may include the following steps.

[0244] In step S291, first information is received.

[0245] In step S292 , a processing time of the AI ​​function or AI model is determined based on the first information.

[0246] In this embodiment, the network device can determine the processing time of the same AI function or AI model as that of the terminal based on the processing time of the AI ​​function or AI model included in the first information.

[0247] In step S293 , the AI ​​function or AI model is processed based on the processing time.

[0248] In this embodiment, the network device may process the AI ​​function or AI model based on the processing time. For example, the network device may activate the AI ​​function or AI model.

[0249] The present disclosure can determine the processing time by receiving first information through a network device. The first information is used by the network device to determine the processing time of the AI ​​function or AI model. This ensures that the terminal and the network device process the AI ​​model or AI function synchronously, thereby improving the operating efficiency of the AI ​​function or AI model.

[0250] In some embodiments, in the AI ​​communication method provided by the present disclosure, the processing time of different AI functions or different AI models is the same.

[0251] In one embodiment, the processing time for different AI functions or different AI models is the same, which can improve efficiency compared to having different processing times for each different AI function or AI model.

[0252] The present disclosure determines that the processing time of different AI functions or AI models is the same through network devices, which can improve efficiency and enable the terminal and network device to process the AI ​​model or AI function synchronously to improve the operating efficiency of the AI ​​function or AI model.

[0253] In some embodiments, in the AI ​​communication method provided by the present disclosure, the processing time of different AI functions or different AI models of the same terminal is the same.

[0254] In one embodiment, since the terminals are the same, the software environment and hardware environment of different AI functions or AI models are the same, and therefore, the processing time of different AI functions or different AI models of the same terminal can be the same.

[0255] For example, different terminals have different computing power and storage space. Processing AI functions or AI models requires the support of the terminal's computing power and storage space. Computing power can be understood as the terminal's processing capabilities. It can be assumed that the higher the terminal's computing power and the larger its storage space, the shorter the processing time required to process the AI ​​function or AI model. In other words, the computing power and storage space of a terminal affect the processing time of the AI ​​function or AI model. The same terminal has the same computing power and storage space. Therefore, the processing time of different AI functions or different AI models on the same terminal is the same.

[0256] The present disclosure can improve efficiency by ensuring that different AI functions or AI models on the same terminal have the same processing time through network devices. It can also enable the terminal and network devices to synchronously process the AI ​​model or AI function, thereby improving the operating efficiency of the AI ​​function or AI model.

[0257] In some embodiments, in the artificial intelligence communication method provided by the present disclosure, the processing time of different AI functions or different AI models corresponding to the same AI feature use case of the same terminal is the same.

[0258] In one embodiment, the network device determines, based on the first information, that processing times of different AI functions or different AI models corresponding to the same AI feature use case of the same terminal are the same. Because similarities may exist between the AI ​​functions or AI models of the same AI feature use case, the processing times of different AI functions or AI models of the same AI feature use case of the same terminal are the same.

[0259] This disclosure uses network devices to determine that the processing time for different AI functions or different AI models corresponding to the same AI feature use case on the same terminal is the same, which is more targeted and more accurate. It can enable the terminal and network device to synchronously process the AI ​​model or AI function, thereby improving the operating efficiency of the AI ​​function or AI model.

[0260] In some embodiments, in the artificial intelligence communication method provided by the present disclosure, the processing time of different AI functions or different AI models in the same deployment mode of the same terminal is the same.

[0261] In one embodiment, the network device determines, based on the first information, that the processing times of different AI functions or different AI models in the same deployment mode of the same terminal are the same.

[0262] AI functions or AI models can be deployed in two ways: unilaterally and bilaterally. Different deployment methods affect the time required to process an AI function or AI model. Often, AI functions or AI models deployed in the same way have similar processing times. Therefore, different AI functions or AI models deployed in the same way on the same terminal will have the same processing time.

[0263] For example, the processing time of an AI function or AI model deployed unilaterally on the same terminal is time 1. The processing time of an AI function or AI model deployed bilaterally on the same terminal is time 2. Of course, the processing time of the AI ​​function or AI model deployed bilaterally on the same terminal may also be time 1, and this disclosure is not limited thereto.

[0264] For another example, for the same terminal, the deployment method is to deploy the AI ​​function or AI model on the terminal, and its processing time is time 3. For the same terminal, the deployment method is to deploy the AI ​​function or AI model on the network device, and its processing time is time 4. Of course, for the above-mentioned AI function or AI model deployed on the same terminal, its processing time can also be time 3, and this disclosure is not limited to this.

[0265] It can be understood that time 1, time 2, time 3 and time 4 in this embodiment are described as examples and do not represent specific times, and this disclosure does not make specific limitations on this.

[0266] The present disclosure uses network devices to determine that the processing time for different AI functions or different AI models corresponding to the same deployment method of the same terminal is the same, which is more targeted and the processing time is more accurate. It can enable the terminal and network device to synchronously process the AI ​​model or AI function, thereby improving the operating efficiency of the AI ​​function or AI model.

[0267] In some embodiments, in the artificial intelligence communication method provided by the present disclosure, the processing time of different AI functions or different AI models is different.

[0268] In one embodiment, the network device determines, based on the first information, that different AI functions or different AI models have different processing times. That is, the processing time is determined for each AI function or AI model. In this embodiment, the processing time of the AI ​​function or AI model can be determined in a targeted manner.

[0269] In this embodiment, the terminal can determine the processing time for different AI functions or AI models. Taking AI functions as an example, the terminal can determine the processing time for each different AI function based on the complexity of the AI ​​function, the deployment method of the AI ​​function, the number of AI models corresponding to the AI ​​function, etc. Alternatively, taking AI models as an example, the terminal can also determine the processing time for each different AI model based on the complexity of the AI ​​model, the deployment method of the AI ​​model, the number of physical AI models corresponding to the AI ​​model ID, etc.

[0270] The present disclosure uses network devices to determine that the processing times of different AI functions or different AI models are different, making it possible to determine the processing times of different AI functions or different AI models in a targeted and more accurate manner. This enables terminals and network devices to synchronously process AI models or AI functions, thereby improving the operating efficiency of AI functions or AI models.

[0271] In some embodiments, in the artificial intelligence communication method provided by the present disclosure, different AI functions or different AI models of different terminals have different processing times.

[0272] In one embodiment, for different AI functions or different AI models on different terminals, since the corresponding terminals are different, their software and hardware environments can be considered to be different. Based on the first information, the network device can determine that the processing times of different AI functions or different AI models on different terminals are different. That is, the processing times of different AI functions or different AI models on different terminals are determined separately.

[0273] In this embodiment, since the computing power, storage space, etc. of different terminals are different, the processing time can be determined separately for different AI functions or different AI models of different terminals.

[0274] The present disclosure uses network devices to determine that the processing times of different AI functions or different AI models on different terminals are different, which can be targeted and more accurate. It can also enable terminals and network devices to synchronously process AI models or AI functions, thereby improving the operating efficiency of AI functions or AI models.

[0275] In some embodiments, in the artificial intelligence communication method provided by the present disclosure, different AI feature use cases of the same terminal correspond to different AI functions or different AI models with different processing times.

[0276] In one embodiment, for the same terminal, there are large differences in the AI ​​functions or AI models corresponding to different AI feature use cases. Therefore, based on the first information, the network device can determine that the processing times of different AI functions or different AI models corresponding to the AI ​​feature use cases of the same terminal are different.

[0277] This disclosure uses network devices to determine that the processing times of different AI functions or different AI models corresponding to different AI feature use cases on the same terminal are different, making the processing time more targeted and accurate. This enables the terminal and network device to synchronously process the AI ​​model or AI function, thereby improving the operating efficiency of the AI ​​function or AI model.

[0278] In some embodiments, in the artificial intelligence communication method provided by the present disclosure, the processing time of different AI functions or different AI models in different deployment modes of the same terminal is different.

[0279] In one embodiment, because different deployment methods affect the time required to process an AI function or AI model, the network device can determine, based on the first information, that the processing times of different AI functions or different AI models in different deployment methods for the same terminal are different. In other words, the processing times of AI functions or AI models in different deployment methods for the same terminal can be determined separately.

[0280] For example, for different AI functions deployed unilaterally, the processing time is determined as Time 1. For different AI functions deployed bilaterally, the processing time is determined as Time 2, with Time 1 and Time 2 being different. In other words, different processing times are determined for AI functions deployed differently, enabling more targeted and accurate determination of the processing time for each AI function.

[0281] The present disclosure determines that the processing times for different AI functions or different AI models corresponding to different deployment methods of the same terminal are different, making the determined processing time more targeted and more accurate. By processing different AI functions or AI models corresponding to different deployment methods of the same terminal based on the determined processing time, the terminal and network device can synchronously process the AI ​​model or AI function, thereby improving the operating efficiency of the AI ​​function or AI model.

[0282] In some embodiments, in the artificial intelligence communication method provided by the present disclosure, the processing time of the same AI function or the same AI model of different terminals is the same; or, the processing time of the same AI function or the same AI model of different terminals is different.

[0283] In one embodiment, in some cases, for the same AI function or the same AI model on different terminals, the network device can determine, based on the first information, that the processing time is the same. That is, regardless of the terminal corresponding to the AI ​​function or AI model, the same processing time can be determined. This can save time in determining the same AI function or the same AI model on different terminals, improving efficiency. In other cases, for the same AI function or the same AI model on different terminals, the network device can also determine, based on the first information, that the processing time is different. Because different terminals have different computing power, storage space, etc., even if it is the same AI function or AI model, the processing time required for different terminals to process it will vary. Therefore, the terminal can determine the processing time for the same AI function or AI model on different terminals separately. This allows the processing time of the same AI function or AI model to be determined specifically for each terminal, resulting in more accurate processing time.

[0284] The present disclosure can improve efficiency by determining whether the processing time of the same AI function or the same AI model of different terminals is the same or different, or can more accurately determine the processing time of the same AI function or AI model of each terminal in a targeted manner. Based on the determined processing time, the same AI function or the same AI model of different terminals is processed, which enables the terminals and network devices to synchronously process the AI ​​model or AI function, thereby improving the operating efficiency of the AI ​​function or AI model.

[0285] In some embodiments, in the artificial intelligence communication method provided by the present disclosure, the processing of the AI ​​function or AI model includes at least one of the following: activation of the AI ​​function or AI model, switching of the AI ​​function or AI model, configuration of the AI ​​function or AI model, and reasoning of the AI ​​function or AI model.

[0286] Activating an AI function or AI model can be understood as starting a certain AI function or AI model. Switching an AI function or AI model can be understood as switching the current AI function or AI model to a target AI function or AI model, or activating an AI function or target AI model so that the terminal switches from a non-AI state to an AI state. Configuring an AI function or AI model can be understood as configuring the environment for the AI ​​function or AI model. Reasoning an AI function or AI model can be understood as the process of using data to predict or infer an AI function or AI model.

[0287] In this implementation, the network device can determine the processing time for performing any of the above-mentioned processing on the AI ​​function or AI model based on the first information.

[0288] The present disclosure determines the processing time through the network device, thereby ensuring that the terminal and the network device are time-aligned based on the processing duration, and can synchronously process the AI ​​model or AI function to improve the operating efficiency of the AI ​​function or AI model.

[0289] In some embodiments, in the artificial intelligence communication method provided herein, processing includes at least one of the following: activation of an AI function or AI model, or switching of an AI function or AI model. Processing time is determined based on a target model, or based on the target model and a currently used model.

[0290] In one embodiment, the activation time of an AI function or AI model and the switching time of the AI ​​function or AI model may be determined based on a target model, which is the activated AI model or the switched AI model.

[0291] For example, the activation time is determined based on the target model. In some cases, the time to activate the target model can be determined based on the complexity of the target model. The target model is the activated AI model. In other cases, activating the target model switches the device from a non-AI state to an AI state. The time to switch from the non-AI state to the AI ​​state can also be determined based on the target model. Specifically, the time to switch the terminal from the non-AI state to the AI ​​state can be determined based on the activation time of the target model.

[0292] For another example, when switching from a currently used AI model to a target model, the switching time can be determined based on the target model. The target model is the AI ​​model after the switch. In some cases, the time to switch from the currently used AI model to the target model can be determined based on the complexity of the target model. In other cases, since switching from the currently used AI model to the target model requires activating the target model, the time to switch from the currently used AI model to the target model is determined based on the activation time of the target model.

[0293] In one embodiment, the activation time of an AI function or AI model and the switching time of the AI ​​function or AI model can be determined based on a target model and a currently used model. The target model is the activated AI model or the switched AI model.

[0294] For example, when switching from the currently used AI model to the target model, the switching time can be determined based on the currently used model and the target model. In some cases, the time to switch from the currently used AI model to the target model is determined based on the complexity of the currently used model and the target model. Specifically, the time to switch from the currently used AI model to the target model can be determined based on the more complex model between the currently used model and the target model. In other cases, the time to switch from the currently used AI model to the target model is determined based on the time when the currently used model is turned off and the time when the target model is activated. Specifically, the time to switch from the currently used AI model to the target model can be determined based on the larger value of the time when the currently used model is turned off and the time when the target model is activated.

[0295] It can be understood that the above-mentioned determination of the time to activate the target model based on the complexity of the target model is only an illustrative example. This disclosure does not limit how to determine the activation time of the AI ​​model, the switching time of the AI ​​model, etc. based on the target model.

[0296] The present disclosure determines the processing time based on the target model, or determines the time of the AI ​​function or AI model based on the currently used model and the target model, thereby ensuring that the terminal and the network device are time-aligned based on the processing duration, and can process the AI ​​model or AI function synchronously to improve the operating efficiency of the AI ​​function or AI model.

[0297] In some embodiments, in the artificial intelligence communication method provided herein, a first portion of an AI function or AI model is deployed on a terminal, and a second portion is deployed on a network device. The processing time is determined based on the processing time of the first portion of the AI ​​function or AI model. Alternatively, the processing time may be determined based on the processing time of the second portion of the AI ​​function or AI model.

[0298] In one embodiment, if the deployment mode of the AI ​​function or AI model is bilateral deployment, the processing time of the AI ​​function or AI model can be determined based on the first part of the AI ​​function or AI model deployed on the terminal.

[0299] For example, if the activation time of the first part of the AI ​​function or AI model is time 1, then the activation time of the AI ​​function or AI model can be determined based on the activation time of the first part of the AI ​​function or AI model, that is, determined as time 1.

[0300] In one embodiment, the processing time of the AI ​​function or AI model is determined based on the second part of the AI ​​function or AI model deployed on the network device.

[0301] For example, if the activation time of the second AI function or AI model is time 2, the activation time of the AI ​​function or AI model can be determined based on the activation time of the second AI function or AI model, that is, determined as time 2.

[0302] In one embodiment, a processing time of the AI ​​function or AI model is determined based on the first and second parts of the AI ​​function or AI model.

[0303] For example, the processing time is determined based on the larger value of time 1 and time 2.

[0304] The present disclosure determines the processing time based on the processing time of the first part of the AI ​​function or AI model, and / or determines the processing time based on the processing time of the second part of the AI ​​function or AI model, and can flexibly determine the processing time of the AI ​​function or AI model.

[0305] In some embodiments, in the artificial intelligence communication method provided by the present disclosure, processing time corresponds to different AI models or AI functions.

[0306] In this embodiment, the first information received and sent by the network device includes processing time, and the processing time corresponds to different AI functions or AI models. That is, the processing time corresponding to different AI functions or AI models is the same. Therefore, the network device can determine the processing time of different AI functions or AI models based on the processing time in the first information.

[0307] The present disclosure receives the first information through a network device, which can ensure that the terminal and the network device are time-aligned based on the processing duration, and can synchronously process the AI ​​model or AI function to improve the operating efficiency of the AI ​​function or AI model.

[0308] In some embodiments, in the artificial intelligence communication method provided by the present disclosure, the first information includes information for indicating an AI function or an AI model, and a processing time corresponding to the AI ​​function or the AI ​​model.

[0309] In this embodiment, the first information includes the processing times corresponding to different AI functions or AI models. That is, different AI functions or AI models have different processing times. Therefore, the network device can determine the processing times corresponding to different AI functions or AI models based on the information indicating the AI ​​function or AI model in the first information and the processing times corresponding to the AI ​​function or AI model.

[0310] The present disclosure receives the first information through a network device, which can ensure that the terminal and the network device are time-aligned based on the processing duration, and can synchronously process the AI ​​model or AI function to improve the operating efficiency of the AI ​​function or AI model.

[0311] 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.

[0312] Based on the same concept, the embodiments of the present disclosure also provide an AI communication system.

[0313] Figure 31 is a schematic diagram illustrating a method interaction of an AI communication system according to an exemplary embodiment. As shown in Figure 31 , the embodiment of the present disclosure relates to an AI communication system, and the AI ​​communication method includes the following steps.

[0314] In step S301 , the processing time is determined.

[0315] In step S302, first information is sent, where the first information is used by the second communication device to determine a processing time.

[0316] In one embodiment, a first communications device determines a processing time and sends first information to a second communications device in communication with the first communications device. The first information includes the processing time. The second communications device may determine the processing time based on the first information. The first communications device and the second communications device may process an AI function or AI model based on the processing time.

[0317] In the embodiments of the present disclosure, in a scenario where a first communication device interacts with a second communication device, the first communication device may be a terminal or a network device, and the second communication device may be a network device or a terminal. The relevant information processing process of the second communication device in this interaction scenario is the same or similar to that of the first communication device in this interaction scenario. For details on the relevant information processing process of the second communication device in this interaction scenario, please refer to the above-mentioned embodiments related to the first communication device, and the embodiments of the present disclosure will not be further detailed here.

[0318] Based on the same concept, an embodiment of the present disclosure also provides an AI communication device.

[0319] It is understandable that the AI ​​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 the various examples 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.

[0320] FIG32 is a schematic diagram of an AI communication device according to an exemplary embodiment. Referring to FIG32 , the device 200 is configured in a terminal and includes a processing module 201 for determining a processing time, where the processing time is the time required to process an AI function or AI model.

[0321] In one embodiment, the processing time of different AI functions or different AI models is the same.

[0322] In one embodiment, different AI functions or different AI models of the same terminal have the same processing time.

[0323] In one embodiment, the processing time of different AI functions or different AI models corresponding to the same AI feature use case of the same terminal is the same.

[0324] In one embodiment, the processing time of different AI functions or different AI models in the same deployment mode of the same terminal is the same.

[0325] In one embodiment, the processing time of different AI functions or different AI models is different.

[0326] In one embodiment, different AI functions or different AI models of different terminals have different processing times.

[0327] In one embodiment, different AI feature use cases of the same terminal correspond to different AI functions or different AI models with different processing times.

[0328] In one embodiment, different AI functions or different AI models in different deployment modes of the same terminal have different processing times.

[0329] In one embodiment, the processing time of the same AI function or the same AI model on different terminals is the same, or the processing time of the same AI function or the same AI model on different terminals is different.

[0330] In one embodiment, the processing includes at least one of the following: activation of an AI model, switching of an AI model, configuration of an AI model, and reasoning of an AI model.

[0331] In one embodiment, the processing includes at least one of: activating an AI model or switching an AI model. The processing time is determined based on a target model. Alternatively, the processing time is determined based on the target model and the currently used model. The target model is the activated AI model or the switched AI model.

[0332] In one embodiment, a first portion of an AI function or AI model is deployed on a terminal, and a second portion of the AI ​​function or AI model is deployed on a network device. The processing time is determined based on the processing time of the first portion of the AI ​​function or AI model. Alternatively, the processing time is determined based on the processing time of the second portion of the AI ​​function or AI model.

[0333] In one embodiment, the apparatus further includes: a sending module 202, configured to send first information, where the first information is used by the network device to determine a processing time.

[0334] In one embodiment, the processing time corresponds to different AI models or AI functions.

[0335] In one embodiment, the first information includes information indicating an AI function or an AI model, and a processing time corresponding to the AI ​​function or the AI ​​model.

[0336] Figure 33 is a schematic diagram of another AI communication device according to an exemplary embodiment. Referring to Figure 33 , the device 300 is configured in a network device and includes a receiving module 301 for receiving first information, the first information being used to determine a processing time, where the processing time is the time required to process an AI function or AI model.

[0337] In one embodiment, the processing time of different AI functions or different AI models is the same.

[0338] In one embodiment, different AI functions or different AI models of the same terminal have the same processing time.

[0339] In one embodiment, the processing time of different AI functions or different AI models corresponding to the same AI feature use case of the same terminal is the same.

[0340] In one embodiment, the processing time of different AI functions or different AI models in the same deployment mode of the same terminal is the same.

[0341] In one embodiment, the processing time of different AI functions or different AI models is different.

[0342] In one embodiment, different AI functions or different AI models of different terminals have different processing times.

[0343] In one embodiment, different AI feature use cases of the same terminal correspond to different AI functions or different AI models with different processing times.

[0344] In one embodiment, different AI functions or different AI models in different deployment modes of the same terminal have different processing times.

[0345] In one embodiment, the processing time of the same AI function or the same AI model of different terminals is the same; or, the processing time of the same AI function or the same AI model of different terminals is different.

[0346] In one embodiment, the processing includes at least one of the following: activation of an AI model, switching of an AI model, configuration of an AI model, and reasoning of an AI model.

[0347] In one embodiment, the processing includes at least one of the following: activation of the AI ​​model, switching of the AI ​​model; the processing time is determined based on the target model; or, the processing time is determined based on the target model and the currently used model; the target model is the activated AI model, or the switched AI model.

[0348] In one embodiment, it is characterized in that the first part of the AI ​​function or AI model is deployed on the terminal, and the second part of the AI ​​function or AI model is deployed on the network device; the processing time is determined based on the processing time of the first part of the AI ​​function or AI model; and / or, the processing time is determined based on the processing time of the second part of the AI ​​function or AI model.

[0349] In one embodiment, the processing time corresponds to different AI models or AI functions.

[0350] In one embodiment, the first information includes information indicating an AI function or an AI model, and a processing time corresponding to the AI ​​function or the AI ​​model.

[0351] 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.

[0352] Figure 34 is a schematic diagram of an AI 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.

[0353] 34 , 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 .

[0354] 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.

[0355] 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.

[0356] 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.

[0357] 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.

[0358] 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.

[0359] 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.

[0360] 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 an optical 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.

[0361] 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.

[0362] 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.

[0363] 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.

[0364] Figure 35 is a schematic diagram of another artificial intelligence communication device according to an exemplary embodiment. For example, device 500 can be provided as a base station or a server.

[0365] 35 , device 500 includes a processing component 522, which further includes one or more processors, and memory resources represented by memory 532 for storing instructions, such as applications, that can be executed by processing component 522. 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 the instructions to perform the above-described method.

[0366] 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.

[0367] 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.

[0368] The present disclosure determines the processing time and clarifies the processing time of the AI ​​function or AI model, thereby determining the time for processing the AI ​​function or AI model, thereby reducing the complexity of subsequent processing processes based on the AI ​​function or AI model. For example, it can ensure that the terminal and network equipment are time-aligned based on the processing duration, and can process the AI ​​model or AI function synchronously to improve the operating efficiency of the AI ​​function or AI model.

[0369] It is further understood that in the present disclosure, "plurality" refers to two or more than two, and other quantifiers are similar. "And / or" describes the association relationship of related objects, indicating that three relationships may exist. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. The character " / " generally indicates that the related objects before and after are in an "or" relationship. The singular forms "a", "the" and "the" are also intended to include the plural forms, unless the context clearly indicates otherwise.

[0370] 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.

[0371] 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".

[0372] 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.

[0373] 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.

[0374] It should be understood that the present disclosure is not limited to the exact structures described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the scope of the appended claims.

Claims

1. An artificial intelligence (AI) communication method, characterized in that: The method is executed by a terminal, and includes: Determine a processing time, where the processing time is the time to process the AI ​​function or AI model.

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

3. The method according to claim 2, characterized in that The processing time for different AI functions or different AI models on the same terminal is the same.

4. The method according to claim 2, characterized in that: The processing time for different AI functions or different AI models corresponding to the same AI feature use case on the same terminal is the same.

5. The method according to claim 2, characterized in that: The processing time of different AI functions or different AI models in the same deployment mode on the same terminal is the same.

6. The method according to claim 1, characterized in that The processing time for different AI functions or different AI models varies.

7. The method according to claim 6, characterized in that The processing time of different AI functions or different AI models on different terminals is different.

8. The method according to claim 6, characterized in that Different AI feature use cases of the same terminal correspond to different AI functions or different AI models, and the processing time is different.

9. The method according to claim 6, characterized in that The processing time of different AI functions or different AI models in different deployment modes of the same terminal is different.

10. The method according to claim 1, characterized in that The processing time of the same AI function or the same AI model on different terminals is the same; or, The processing time of the same AI function or the same AI model on different terminals is different.

11. The method according to any one of claims 1 to 10, characterized in that: The processing includes at least one of the following: Activation of AI models, switching of AI models, configuration of AI models, and reasoning of AI models.

12. The method according to any one of claims 1 to 10, characterized in that: The processing includes at least one of the following: activation of an AI model, switching of an AI model; The processing time is determined based on a target model; or, The processing time is determined based on the target model and the current usage model; The target model is the activated AI model or the switched AI model.

13. The method according to any one of claims 1 to 10, characterized in that The first part of the AI ​​function or AI model is deployed on the terminal, and the second part of the AI ​​function or AI model is deployed on the network device; The processing time is determined based on the processing time of the first part of the AI ​​function or AI model; and / or, The processing time is determined based on the processing time of the second part of the AI ​​function or AI model.

14. The method according to any one of claims 1 to 13, characterized in that: The method further comprises: First information is sent, where the first information is used by the network device to determine the processing time.

15. The method according to claim 14, characterized in that The processing time corresponds to different AI models or AI functions.

16. The method according to claim 14, characterized in that The first information includes information for indicating an AI function or an AI model, and a processing time corresponding to the AI ​​function or the AI ​​model.

17. An artificial intelligence (AI) communication method, characterized in that: The method is performed by a network device and includes: Receive first information, where the first information is used to determine a processing time, where the processing time is the time for processing an AI function or an AI model.

18. The method according to claim 17, characterized in that The processing time for different AI functions or different AI models is the same.

19. The method according to claim 18, characterized in that The processing time for different AI functions or different AI models on the same terminal is the same.

20. The method according to claim 18, characterized in that The processing time for different AI functions or different AI models corresponding to the same AI feature use case on the same terminal is the same.

21. The method according to claim 18, characterized in that The processing time of different AI functions or different AI models in the same deployment mode on the same terminal is the same.

22. The method according to claim 17, characterized in that The processing time for different AI functions or different AI models varies.

23. The method according to claim 22, characterized in that The processing time of different AI functions or different AI models on different terminals is different.

24. The method according to claim 22, characterized in that Different AI feature use cases of the same terminal correspond to different AI functions or different AI models, and the processing time is different.

25. The method according to claim 22, characterized in that The processing time of different AI functions or different AI models in different deployment modes of the same terminal is different.

26. The method according to claim 17, characterized in that The processing time of the same AI function or the same AI model on different terminals is the same; or, The processing time of the same AI function or the same AI model on different terminals is different.

27. The method according to any one of claims 17 to 26, characterized in that The processing includes at least one of the following: Activation of AI models, switching of AI models, configuration of AI models, and reasoning of AI models.

28. The method according to any one of claims 17 to 26, characterized in that The processing includes at least one of the following: activation of an AI model, switching of an AI model; The processing time is determined based on a target model; or, The processing time is determined based on the target model and the current usage model; The target model is the activated AI model or the switched AI model.

29. The method according to any one of claims 17 to 26, characterized in that The first part of the AI ​​function or AI model is deployed on the terminal, and the second part of the AI ​​function or AI model is deployed on the network device; The processing time is determined based on the processing time of the first part of the AI ​​function or AI model; and / or, The processing time is determined based on the processing time of the second part of the AI ​​function or AI model.

30. The method according to claim 17, characterized in that The processing time corresponds to different AI models or AI functions.

31. The method according to claim 17, characterized in that The first information includes information for indicating an AI function or an AI model, and a processing time corresponding to the AI ​​function or the AI ​​model.

32. An artificial intelligence (AI) communication device, characterized in that: include: The processing module is used to determine the processing time, where the processing time is the time for processing the AI ​​function or AI model.

33. An artificial intelligence (AI) communication device, characterized in that: include: A receiving module is used to receive first information, where the first information is used to determine a processing time, where the processing time is the time for processing an AI function or an AI model.

34. An artificial intelligence 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 16.

35. An artificial intelligence 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 17 to 31.

36. A 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 16.

37. A 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 described in any one of claims 17 to 31.

38. A communication system, characterized in that: include: A terminal, configured to execute the method according to any one of claims 1 to 16; A network device, configured to execute the method according to any one of claims 17 to 31.

Images