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 steps of determining first time, wherein the first time is used for representing processing time for processing an AI task based on an AI model; and performing AI communication processing based on the AI model based on the first time. According to the method and the device, the time for communication processing based on the AI model is determined by determining the first time.

Description

Artificial intelligence communication method, device and storage medium Technical Field

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

[0002] In recent years, artificial intelligence (AI) technology has made continuous breakthroughs in many fields. AI technology is gradually cross-penetrating into other disciplines, providing new directions and methods for the development of different disciplines.

[0003] In related technologies, the 3rd Generation Partnership Project (3GPP) has established a research project on artificial intelligence technology in wireless air interfaces. This project aims to study the introduction of AI technology in wireless air interfaces and explore how AI technology can assist in improving wireless air interface transmission technology.

[0004] Summary of the Invention

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

[0006] According to a first aspect of an embodiment of the present disclosure, an artificial intelligence (AI) communication method is provided, which is executed by a first communication device, including determining a first time, where the first time is used to represent the processing time of processing an AI task based on an AI model; and based on the first time, performing AI communication processing based on the AI ​​model.

[0007] In one embodiment, the first time is represented based on at least one of the following: absolute time; communication time unit; AI time unit, and the AI ​​time unit is determined based on a preset AI task.

[0008] In another embodiment, the AI ​​time unit includes the processing time for processing a preset AI task based on the AI ​​model; or the AI ​​time unit includes the computing power resources for processing a preset AI task based on the AI ​​model.

[0009] In yet another embodiment, performing AI communication processing based on an AI model based on the first time includes:

[0010] Sending a processing time based on the first time representation to a second communication device that communicates with the first communication device; obtaining a second time, where the second time is the time for performing AI communication processing and is determined by the second communication device based on the first time; and performing AI communication processing of the AI ​​model with the second communication device based on the second time.

[0011] In yet another embodiment, performing AI communication based on an AI model based on the first time includes:

[0012] Based on the processing time represented by the first time, a second time is determined, where the second time is the time for performing AI communication processing; based on the second time, AI communication processing of the AI ​​model is performed.

[0013] In another embodiment, the processing time represented by the first time includes at least one of the following: the processing time corresponding to the AI ​​model supported by the first communication device, and the processing time is based on the first time representation; or the processing time selected from the processing time set, and the processing time set includes the processing time based on the first time representation.

[0014] In yet another embodiment, the AI ​​model-based AI communication processing includes at least one of the following: reasoning of the AI ​​model, activation of the AI ​​model, and switching of the AI ​​model.

[0015] In another embodiment, the AI ​​model includes at least one of an AI function and a model corresponding to the AI ​​function.

[0016] In yet another embodiment, the first communication device is a terminal, and the second communication device is a network device; or the first communication device is a network device, and the second communication device is a terminal.

[0017] According to a second aspect of an embodiment of the present disclosure, there is provided an AI communication method, which is performed by a second device. The method includes:

[0018] receiving a first time sent by a first communication device, where the first time is used to indicate a processing time for processing an AI task based on an AI model;

[0019] Based on the first time, AI communication processing based on the AI ​​model is performed.

[0020] In one embodiment, the first time is represented based on at least one of the following: absolute time; communication time unit; AI time unit, and the AI ​​time unit is determined based on a preset AI task.

[0021] In another embodiment, the AI ​​time unit includes the processing time for processing a preset AI task based on the AI ​​model; or the AI ​​time unit includes the computing power resources for processing a preset AI task based on the AI ​​model.

[0022] In yet another embodiment, performing AI communication based on an AI model based on the first time includes:

[0023] Based on the processing time represented by the first time, determine a second time, where the second time is the time for performing AI communication processing; send the second time to the first communication device; and perform AI communication processing of the AI ​​model with the first communication device based on the second time.

[0024] In yet another embodiment, performing AI communication based on the first time includes:

[0025] Based on the processing time represented by the first time, a second time is determined, where the second time is the time for performing AI communication processing; based on the second time, AI communication processing of the AI ​​model is performed.

[0026] In another embodiment, the processing time represented by the first time includes at least one of the following:

[0027] a processing time corresponding to an AI model supported by the first communication device, the processing time being represented based on the first time; or

[0028] A processing time selected from a processing time set, wherein the processing time set includes a processing time based on the first time representation.

[0029] In yet another embodiment, performing AI communication based on the first time includes:

[0030] Based on the processing time represented by the first time, a second time is determined, where the second time is the communication time represented by the communication time unit; and based on the second time, AI communication processing of the AI ​​model is performed.

[0031] In another embodiment, the AI ​​communication processing based on the AI ​​model includes at least one of the following:

[0032] AI model reasoning, AI model activation, and AI model switching.

[0033] In another embodiment, the AI ​​model includes at least one of an AI function and a model corresponding to the AI ​​function.

[0034] In yet another embodiment, the first communication device is a terminal, and the second communication device is a network device; or the first communication device is a network device, and the second communication device is a terminal.

[0035] According to a third aspect of an embodiment of the present disclosure, there is provided an AI communication apparatus, executed by a first communication device, the apparatus including:

[0036] A processing unit is configured to determine a first time, where the first time is used to represent a processing time for processing an AI task based on an AI model; and based on the first time, perform AI communication processing based on the AI ​​model.

[0037] In one embodiment, the first time is represented based on at least one of the following: absolute time; communication time unit; AI time unit, and the AI ​​time unit is determined based on a preset AI task.

[0038] In another embodiment, the AI ​​time unit includes the processing time for processing a preset AI task based on the AI ​​model; or the AI ​​time unit includes the computing power resources for processing a preset AI task based on the AI ​​model.

[0039] In another embodiment, the AI ​​communication device further includes a sending unit and a receiving unit, the sending unit is used to send a processing time based on the first time representation to a second communication device that communicates with the first communication device; the receiving unit is used to obtain a second time, which is the time for performing AI communication processing and is determined by the second communication device based on the first time; the processing unit and the second communication device perform AI communication processing of the AI ​​model based on the second time.

[0040] In another embodiment, the processing unit performs AI communication based on the AI ​​model based on the first time in the following manner: determining a second time based on the processing time represented by the first time, the second time being the time for performing AI communication processing; and performing AI communication processing of the AI ​​model based on the second time.

[0041] In another embodiment, the processing time of processing the AI ​​task represented by the first time includes at least one of the following: the processing time corresponding to the AI ​​model supported by the first communication device, and the processing time is based on the first time representation; or

[0042] A processing time selected from a processing time set, wherein the processing time set includes a processing time based on the first time representation.

[0043] In another embodiment, the AI ​​communication processing based on the AI ​​model includes at least one of the following:

[0044] AI model reasoning, AI model activation, and AI model switching.

[0045] In another embodiment, the AI ​​model includes at least one of an AI function and a model corresponding to the AI ​​function.

[0046] In yet another embodiment, the first communication device is a terminal, and the second communication device is a network device; or the first communication device is a network device, and the second communication device is a terminal.

[0047] According to a fourth aspect of an embodiment of the present disclosure, there is provided an AI communication apparatus, which is executed by a second communication device, and the apparatus includes:

[0048] A processing unit is used to receive a first time sent by a first communication device, where the first time is used to represent the processing time of processing an AI task based on an AI model; and to perform AI communication processing based on the AI ​​model based on the first time.

[0049] In one embodiment, the first time is represented based on at least one of the following: absolute time; communication time unit; AI time unit, and the AI ​​time unit is determined based on a preset AI task.

[0050] In another embodiment, the AI ​​time unit includes the processing time of a preset AI task based on the AI ​​model; or the AI ​​time unit includes the computing power resources of a preset AI task based on the AI ​​model.

[0051] In another embodiment, the processing unit determines a second time based on the processing time represented by the first time, and the second time is the time for performing AI communication processing; the AI ​​communication device also includes a sending unit, which sends the second time to the first communication device; the processing unit and the first communication device perform AI communication processing of the AI ​​model based on the second time.

[0052] In another embodiment, the processing unit performs AI communication based on the first time in the following manner:

[0053] Based on the processing time represented by the first time, a second time is determined, where the second time is the time for performing AI communication processing; based on the second time, AI communication processing of the AI ​​model is performed.

[0054] In another embodiment, the processing time represented by the first time includes at least one of the following: the processing time corresponding to the AI ​​model supported by the first communication device, and the processing time is based on the first time representation; the processing time selected from the processing time set, and the processing time set includes the processing time based on the first time representation.

[0055] In yet another embodiment, the AI ​​model-based AI communication processing includes at least one of the following: reasoning of the AI ​​model, activation of the AI ​​model, and switching of the AI ​​model.

[0056] In another embodiment, the AI ​​model includes at least one of an AI function and a model corresponding to the AI ​​function.

[0057] In yet another embodiment, the first communication device is a terminal, and the second communication device is a network device; or the first communication device is a network device, and the second communication device is a terminal.

[0058] 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 AI ​​communication method described in the first aspect or any one of the implementations of the first aspect.

[0059] According to a sixth 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 AI ​​communication method described in the second aspect or any one of the implementations of the second aspect.

[0060] According to a seventh aspect of an embodiment of the present disclosure, a storage medium is provided, in which instructions are stored. When the instructions in the storage medium are executed by a processor of a first communication device, the first communication device is enabled to execute the AI ​​communication method described in the first aspect or any one of the embodiments of the first aspect.

[0061] According to an eighth aspect of an embodiment of the present disclosure, a storage medium is provided, in which instructions are stored. When the instructions in the storage medium are executed by a processor of a second communication device, the second communication device is enabled to execute the AI ​​communication method described in the second aspect or any one of the embodiments of the second aspect.

[0062] According to a ninth aspect of an embodiment of the present disclosure, an artificial intelligence communication system is provided, the system comprising: a first communication device for executing the method described in the first aspect or any one of the embodiments of the first aspect; and a second communication device for executing the method described in the second aspect or any one of the embodiments of the second aspect.

[0063] The technical solution provided by the embodiments of the present disclosure may include the following beneficial effects: determining the first time based on the processing time of the AI ​​model for processing the AI ​​task, performing subsequent communication processing based on the determined first time, and determining the processing time representation method corresponding to the subsequent communication processing, thereby reducing the complexity of the subsequent communication processing process.

[0064] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0065] 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.

[0066] Fig. 1 is a schematic diagram showing a wireless communication system according to an exemplary embodiment.

[0067] Fig. 2a is a flow chart showing an AI communication method according to an exemplary embodiment.

[0068] Fig. 2b is a flow chart showing another AI communication method according to an exemplary embodiment.

[0069] Fig. 2c is a flowchart showing yet another AI communication method according to an exemplary embodiment.

[0070] Fig. 3 is a flowchart showing an AI communication method according to an exemplary embodiment.

[0071] FIG4 is a schematic diagram showing the architecture of an AI communication system according to an exemplary embodiment

[0072] FIG5 a is a structural block diagram of an AI communication device according to an exemplary embodiment.

[0073] FIG5 b is a structural block diagram of an AI communication device according to an exemplary embodiment.

[0074] Fig. 6 is a block diagram of a device for AI communication according to an exemplary embodiment.

[0075] Fig. 7 is a block diagram of a device for AI communication according to an exemplary embodiment. DETAILED DESCRIPTION

[0076] 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.

[0077] The communication method of the embodiment of the present disclosure can be applied to the wireless communication system shown in Figure 1. Referring to Figure 1, the wireless communication system includes a network device and a terminal. The terminal is connected to the network device through wireless resources and performs data transmission.

[0078] It should be understood that the wireless communication system shown in Figure 1 is for illustrative purposes only, and the wireless communication system may also include other network devices, such as core network devices, wireless relay devices, and wireless backhaul devices, which are not shown in Figure 1. The embodiments of the present disclosure do not limit the number of network devices and terminals included in the wireless communication system.

[0079] It can be further understood that the wireless communication system of the embodiment of the present disclosure is a network that provides wireless communication functions. The wireless communication system can adopt different communication technologies, such as code division multiple access (CDMA), wideband code division multiple access (WCDMA), time division multiple access (TDMA), frequency division multiple access (FDMA), orthogonal frequency-division multiple access (OFDMA), single carrier frequency division multiple access (SC-FDMA), carrier sense multiple access / collision avoidance (Carrier Sense Multiple Access with Collision Avoidance). According to the capacity, rate, delay and other factors of different networks, the network can be divided into 2G (English: generation) network, 3G network, 4G network or future evolution network, such as 5G network, 5G network can also be called new radio network (New Radio, NR). For the convenience of description, the present disclosure sometimes refers to the wireless communication network as simply a network.

[0080] Furthermore, the network devices involved in the present disclosure may also be referred to as wireless access network devices. The wireless access network device may be: a base station, an evolved node B (base station), a home base station, an access point (AP) in a wireless fidelity (WIFI) system, a wireless relay node, a wireless backhaul node, a transmission point (TP) or a transmission and reception point (TRP), etc. It may also be a gNB in ​​an NR system, or it may also be a component or part of a base station. It should be understood that in the embodiments of the present disclosure, the specific technology and specific device form adopted by the network device are not limited. In the present disclosure, the network device can provide communication coverage for a specific geographical area and can communicate with terminals located in the coverage area (cell). In addition, when it is a vehicle-to-everything (V2X) communication system, the network device may also be a vehicle-mounted device.

[0081] Furthermore, the terminal involved in the present disclosure may also be referred to as a terminal device, user equipment (UE), mobile station (MS), mobile terminal (MT), etc., which is a device that provides voice and / or data connectivity to users. For example, the terminal can be a handheld device with wireless connection function, a vehicle-mounted device, etc. At present, some examples of terminals are: smart phones (Mobile Phones), customer premises equipment (Customer Premise Equipment, CPE), pocket computers (Pocket Personal Computers, PPCs), handheld computers, personal digital assistants (Personal Digital Assistants, PDAs), laptops, tablet computers, wearable devices, or vehicle-mounted devices, etc. In addition, when it is a vehicle-to-everything (V2X) communication system, the terminal device can also be a vehicle-mounted device. It should be understood that the embodiments of the present disclosure do not limit the specific technology and specific device form adopted by the terminal.

[0082] In recent years, artificial intelligence (AI) technology has made continuous breakthroughs in many fields. AI technology is gradually cross-penetrating into other disciplines, providing new directions and methods for the development of different disciplines.

[0083] In related technologies, the 3rd Generation Partnership Project (3GPP) has established a research project on artificial intelligence technology in wireless air interfaces. This project aims to study the introduction of AI technology in wireless air interfaces and explore how AI technology can assist in improving wireless air interface transmission technology.

[0084] In the research on AI communications, AI use cases may include: AI-based beam management and AI-based positioning, etc.

[0085] It's understandable that AI use cases can also be called AI features. These are communication scenarios where AI-based communication operations are performed to achieve a specific purpose. For example, AI can be used to predict channel information in the time domain or to manage beams in the air domain. An AI feature is typically defined in the protocol.

[0086] It's understandable that each of the above use cases involves the AI ​​model processing an AI task, and because the AI ​​models handle different AI tasks, the AI ​​tasks they handle also vary. Consequently, the processing time descriptions for different AI tasks by the corresponding AI models are not exactly the same.

[0087] In the related art, in the process of AI communication processing based on the AI ​​model, there is no clear method for describing the processing time of the AI ​​model to perform AI communication.

[0088] Based on this, the present disclosure proposes an AI communication method to clarify the processing time of processing AI tasks based on an AI model, so that AI communication processing based on the AI ​​model can be performed subsequently based on the processing time.

[0089] It should be noted that the AI ​​model involved in the embodiments of the present disclosure may include at least one of an AI function and a model corresponding to the AI ​​function. Among them, the AI ​​model involved in the following embodiments of the present disclosure may be replaced by an AI model or an AI function.

[0090] It should be noted that for one AI use case, multiple AI functions will be defined. For example, for the AI-based Channel State Information (CSI) enhancement use case, AI function #1 supports predicting the ID of the best beam, and AI function #2 supports predicting the best beam and the measurement results of the corresponding beam. The implementation of AI functions relies on AI models. Different AI functions can be implemented by different AI models, or they can be implemented by different AI models. That is, an AI function can correspond to one or more AI models.

[0091] In one implementation of the embodiments of the present disclosure, the AI ​​model processing AI tasks involved in the following embodiments of the present disclosure can be understood as executing the AI ​​model on the AI ​​use case.

[0092] Exemplarily, the AI ​​model processes AI tasks including AI-based CSI enhancement, AI-based beam management, and AI-based positioning.

[0093] Exemplarily, in the AI ​​communication method provided by the embodiment of the present disclosure, the processing time of processing AI tasks based on the AI ​​model includes at least one of the following: the processing time of the AI-based CSI enhancement task, the processing time of the AI-based beam management task, and the processing time of the AI-based positioning task.

[0094] In the AI ​​communication method provided by the embodiment of the present disclosure, the first communication device performs AI communication processing based on the AI ​​model based on the first time.

[0095] In one implementation of the present disclosure, AI communication processing based on the AI ​​model includes at least one of the following:

[0096] AI model reasoning, AI model activation, and AI model switching.

[0097] It should be further explained that the AI ​​communication processing based on the AI ​​model involved in the following embodiments of the present disclosure includes one or more of the reasoning of the AI ​​model, the activation of the AI ​​model, and the switching of the AI ​​model.

[0098] In the AI ​​communication method provided by the embodiments of the present disclosure, the AI ​​model inference time may be determined, the AI ​​model activation time may be determined, and the AI ​​model switching time may be determined.

[0099] Figure 2a is a flowchart of an AI communication method according to an exemplary embodiment. As shown in Figure 2a, the AI ​​communication method is executed by a first communication device, which may be a terminal or a network device. The AI ​​communication method includes the following steps:

[0100] In step S11, a first time is determined, where the first time is used to represent a processing time for processing an AI task based on an AI model.

[0101] In step S12, AI communication processing based on the AI ​​model is performed based on the first time.

[0102] In the embodiments of the present disclosure, a processing time for representing the processing of an AI task based on an AI model is determined, and the time representation for processing an AI task based on an AI model is clarified.

[0103] Among them, the first time is used to represent the processing time of the AI ​​model to process the AI ​​task, which can be understood as the first time used to measure the time for processing the AI ​​task based on the AI ​​model.

[0104] In one implementation of the embodiment of the present disclosure, the first time is the time for processing the AI ​​task based on the AI ​​model, which can be understood as duration.

[0105] In one implementation of the disclosed embodiment, the first time is a time unit for measuring the processing of AI tasks based on an AI model, and the time unit can also be understood as a time unit.

[0106] In the AI ​​communication method provided by the embodiments of the present disclosure, the first time is a time unit for measuring the processing of AI tasks based on the AI ​​model, and at least one of the AI ​​model inference time, the AI ​​model activation time, and the AI ​​model switching time is determined based on the first time.

[0107] For example, for a terminal or a network device, the processing time of the AI ​​model deployed at the respective corresponding location to process the AI ​​task can be determined, that is, the first time.

[0108] In one implementation of the AI ​​communication method provided by the embodiment of the present disclosure, the first time may be represented by a unit used to describe time.

[0109] For example, the physical unit used to describe time in conventional physical space is absolute time, and the units of absolute time include seconds, milliseconds, microseconds, etc.

[0110] The physical unit used to describe time in a communication system is a communication time unit. The units of the communication time unit include: Orthogonal Frequency Division Multiplexing (OFDM) symbol, slot, subslot, and OFDM symbol sampling interval.

[0111] The time unit used to describe AI communication in some scenarios is defined and is subsequently referred to as the AI ​​time unit. It is understood that the AI ​​time unit is defined and is the basic time unit used to measure AI processing tasks.

[0112] In the embodiment of the present disclosure, the AI ​​time unit may be determined based on a preset AI task.

[0113] Exemplarily, since the AI ​​time unit is a unit obtained by definition for describing AI processing time, the AI ​​time unit can be determined based on the AI ​​task.

[0114] In one embodiment, the AI ​​time unit is determined based on the AI ​​task and the processing time corresponding to the AI ​​task. For example, let's define Task A as a pre-defined AI task, and the time required to complete Task A as Y absolute times. The AI ​​time unit includes the Y absolute times required to complete Task A.

[0115] Among them, the processing time corresponding to the AI ​​task is determined based on the complexity of the model that executes the AI ​​task.

[0116] In another implementation, the AI ​​time unit is determined based on the AI ​​task and the corresponding computing resources. For example, let's define Task A as a pre-defined AI task, and the computing resources required to complete Task A as Y FLOPS. The AI ​​time unit includes the Y FLOPS of computing resources required to complete Task A.

[0117] The computing power resources corresponding to AI tasks can be understood as the amount of computing power or resources used to perform basic AI tasks. The computing power resources corresponding to AI tasks can also be understood as the processing unit capabilities required to handle AI tasks.

[0118] In an implementation manner provided by an embodiment of the present disclosure, the first time is represented based on at least one of the following: absolute time; a communication time unit and an AI time unit.

[0119] In an exemplary embodiment of the AI ​​communication method provided by the embodiments of the present disclosure, the first time is expressed based on absolute time.

[0120] The first time is expressed based on a unit for measuring absolute time, such as seconds (s), milliseconds (ms), microseconds (us), etc.

[0121] Taking AI model reasoning as an example, a first communication device (e.g., a terminal) can report the first processing time corresponding to supported AI models #1 and #2. For example, the first processing time corresponding to AI model #1 (e.g., 1ms) and the first processing time corresponding to AI model #2 (e.g., 2ms) can be reported.

[0122] In another implementation, when the first time is expressed based on a unit for measuring absolute time, the first communication device may also report in the following manner.

[0123] A corresponding processing time is selected from a processing time set, where the processing time set includes the processing time represented based on the first time.

[0124] When the elements in the processing time set have units for measuring absolute time, for example, 1ms, 2ms, 3ms, etc., the first communications device selects a first processing time corresponding to the AI ​​model from the processing time set, for example, selecting the processing time of AI model #1 as 1ms and the processing time of AI model #2 as 2ms.

[0125] In the AI ​​communication method provided by the embodiment of the present disclosure, the first time is represented based on a communication time unit.

[0126] The first time is represented based on an OFDM symbol, a slot, a subslot, and a sampling interval of an OFDM symbol.

[0127] Taking AI model reasoning as an example, a first communication device (e.g., a terminal) can report the first processing time corresponding to supported AI models #1 and #2. For example, the first processing time corresponding to AI model #1 (e.g., one OFDM symbol) and the first processing time corresponding to AI model #2 (e.g., two slots) can be reported.

[0128] In another implementation, when the first time is expressed based on a measured communication time unit, the first communication device may also report in the following manner.

[0129] A corresponding processing time is selected from a processing time set, where the processing time set includes the processing time represented based on the first time.

[0130] When the elements in the processing time set have units that measure absolute time, for example, 1 OFDM symbol, 2 slots, 3 OFDM symbol sampling intervals, etc., the first communications device selects a first processing time corresponding to the AI ​​model from the processing time set, for example, selecting the processing time of AI model #1 as 1 OFDM symbol and selecting the processing time of AI model #2 as 2 slots.

[0131] It is understandable that the absolute time corresponding to each communication time unit is different under different subcarriers. For example, under subcarrier a, the sampling interval of one OFDM symbol corresponds to 0.5ms, and under subcarrier b (subcarrier a and subcarrier b are different), the sampling interval of one OFDM symbol corresponds to 0.3ms.

[0132] In a communication system, communication processing is measured in basic communication time units. In the embodiment of the present disclosure, the first time is expressed based on the communication time unit, which can make the I processing time of task A more compatible with the communication system. It also simplifies subsequent communication processing.

[0133] In the AI ​​communication method provided by the embodiment of the present disclosure, the first time is represented based on the AI ​​time unit.

[0134] The first time is expressed based on AI time units. For example, if Task A is defined as a pre-set AI task, and the time required to complete Task A is Y absolute time, then the AI ​​time unit includes Task A and Y absolute time. Alternatively, if Task A is defined as a pre-set AI task, and the computing power required to complete Task A is Y FLOPS, then the AI ​​time unit includes Task A and Y FLOPS.

[0135] In the embodiment of the present disclosure, the AI ​​time unit can be determined in the following two ways:

[0136] (1) Determined based on the preset AI task and the processing time of the AI ​​model to process the preset task.

[0137] For example, the preset AI task is defined as A, where task A can be called a basic task, or in some scenarios, subtask A' of task A can be used as a basic task. Taking task A as an example, the processing time used to call the model corresponding to task A can be regarded as one AI time unit. If the processing time used by the model corresponding to task A is a milliseconds, where a is greater than zero, then a millisecond in absolute time corresponds to one AI time unit; if the processing time used by the model corresponding to task A is b slots, where b is greater than zero, then b slots in the communication time unit correspond to one AI time unit.

[0138] Furthermore, the processing time for processing the preset AI task based on the preset AI task and the AI ​​model can be determined based on the complexity of the AI ​​task and the processing time for processing the preset task by the AI ​​model.

[0139] Exemplarily, the complexity of the preset AI task can be determined in a predefined manner. For example, if the preset task is a channel state information (CSI) compression task, the complexity of compressing a physical resource block (PRB) can be defined as the complexity of the preset AI task, that is, the complexity of the basic task.

[0140] It can be understood that if there is a linear characteristic relationship between the complexity of the preset AI task and the AI ​​time unit corresponding to the basic task processed by the model (for example, when the complexity of processing the AI ​​task is m, it corresponds to one AI time unit, when the complexity of processing the AI ​​task is 2m, it corresponds to two AI time units, etc.), then, when the complexity of the currently processed AI task is N times the complexity of the preset AI task, where N is a rational number greater than zero, then the processing time corresponding to the currently processed AI task can be expressed as N AI time units.

[0141] Furthermore, if one AI time unit represents a milliseconds, then N AI time units can represent N*a milliseconds; if one AI time unit represents b slots, then N time units can represent N*b slots.

[0142] For example, the protocol predefines a basic AI processing task. The terminal reports the time it takes to process this basic AI processing task, and this time is used as a unit to measure the processing time of the AI ​​model or AI function supported by the terminal. For example, if AI processing task A is defined, where the model complexity of A is X and the time required for the terminal to process model A is Y milliseconds, then the AI ​​model or AI function supported by the corresponding terminal will be measured in units of Y. For example, the processing time for model A is N AI processing time units, that is, N*Y milliseconds.

[0143] (2) Determine the computing power resources required to process the preset AI tasks based on the preset AI tasks and the AI ​​model.

[0144] For example, let's define a predefined AI task as A, which can also be called a basic task. The maximum computing power of the model corresponding to task A is defined as m, and the computing power required to process task A is defined as n, where m is numerically greater than or equal to n. The time it takes for the model to process task A with computing power n corresponds to one time unit.

[0145] It is understood that the time taken by the model to process Task A with computing power n can be either absolute time or communication time units. For example, if the time taken by the model to process Task A with computing power n is a milliseconds, then when the model is defined to process Task A with computing power n, one time unit corresponds to a milliseconds in absolute time, two time units correspond to 2a milliseconds in absolute time, and so on. If the time taken by the model to process Task A with computing power n is b slots, then when the model is defined to process Task A with computing power n, one time unit corresponds to b slots in communication time units, two time units correspond to 2b slots in communication time units, and so on.

[0146] Exemplarily, the protocol predefines a basic AI processing task and predefines the processing unit capabilities when processing this AI task. The terminal uses the predefined processing unit configuration to process the defined basic AI processing task to obtain a basic processing time unit. This time unit is then used to measure the processing time of the AI ​​model or AI function supported by the terminal. For example, an AI processing task A is defined, and the predefined configuration of the processing unit used is Z. The model complexity of A is X, and the time required for the terminal to process model A based on the preset processing unit is Y milliseconds. At this time, the corresponding terminal reports that the AI ​​model or AI function it supports is measured in units of Y. The processing time for model A is N AI processing time units, that is, N*Y milliseconds.

[0147] In the AI ​​communication method provided in this embodiment, by determining the AI ​​time unit based on the processing time used by the model to process the preset task or the computing power resources used to process the preset task, it is possible to simultaneously report information such as the task complexity of the communication device and the model processing computing power while using the AI ​​time unit as the first time for AI communication.

[0148] Exemplarily, the first time may be expressed based on absolute time and communication time units.

[0149] Exemplarily, the first time may be expressed based on absolute time and AI time units.

[0150] Exemplarily, the first time may be expressed based on the communication time and the AI ​​time unit.

[0151] Exemplarily, the first time may be expressed based on absolute time, communication time units, and AI time units.

[0152] It should be understood that the aforementioned embodiments have provided more detailed examples of AI communication processing and the first time corresponding to the AI. Based on this, only the representation of the first time corresponding to the AI ​​is given here as an example, and all the listed items are not described one by one.

[0153] The AI ​​communication method provided by the embodiment of the present disclosure performs AI communication processing based on the AI ​​model based on the first time for representing processing an AI task based on the AI ​​model.

[0154] Figure 2b is a flow chart showing an AI communication method according to an exemplary embodiment. The AI ​​communication method shown in Figure 2b is executed by a first communication device, which is a terminal or a network device.

[0155] In an embodiment shown in FIG2b , performing AI communication based on the first time includes the following steps:

[0156] In step S21, a processing time represented by a first time is sent to a second communication device communicating with the first communication device. The processing time represented by the first time is the time for processing the AI ​​task.

[0157] In the embodiment of the present disclosure, the first communication device sends the processing time based on the first time representation to the second communication device, so that the second communication device determines the AI ​​communication processing time based on the processing time represented by the first time representation.

[0158] For convenience of description below, the AI ​​communication processing time determined based on the first time is referred to as the second time.

[0159] It is understood that the second time can be a time expressed in communication time units or in other forms, and this disclosure is not limited thereto. The second time is expressed in a form that aligns the first communication device and the second communication device. It is understood that both the first time and the second time represent communication processing time.

[0160] Furthermore, the time unit used for the second time may be the same as the time unit used for the first time, or may be another time unit different from the time unit used for the first time.

[0161] In the embodiment of the present disclosure, the processing time of the AI ​​task based on the first time representation sent to the second communication device communicating with the first communication device includes sending the first time represented in the following form: absolute time, communication time unit and AI time unit.

[0162] In the embodiment of the present disclosure, the first communication device may be a terminal, and the second communication device may be a network device such as a base station. Alternatively, the first communication device may be a network device such as a base station, and the second communication device may be a terminal.

[0163] For example, the first communication device is a terminal and the second communication device is a base station. The terminal sends the AI ​​task processing time expressed in absolute time to the base station. For example, if the processing time is a milliseconds, the base station determines that the corresponding processing time expressed in the communication time unit is 1 slot based on a millisecond.

[0164] Furthermore, if the terminal sends the AI ​​task processing time expressed in communication time units to the base station, the base station directly uses the received AI task processing time expressed in communication time units as the communication time without performing any other conversion processing. For example, if the sending processing time is one OFDM symbol, the communication time determined by the base station is one OFDM symbol.

[0165] Furthermore, if the terminal sends the AI ​​task processing time expressed in AI time units to the base station, for example, the sent processing time is 1 AI time unit. Since the AI ​​time unit can be predefined based on the preset AI task (the specific predefinition steps have been described in detail in the above embodiment and will not be repeated here), the base station can determine that the communication time corresponds to b slots based on the AI ​​time unit.

[0166] In step S22, a second time is acquired, where the second time is determined by the second communication device based on the processing time represented by the first time.

[0167] In the embodiment of the present disclosure, the second communication device determines the second time based on the first time sent by the first communication device.

[0168] In one embodiment of the present disclosure, the second communication device sends the determined second time to the first communication device, and the first communication device can obtain the second time by receiving the second time sent by the second communication device, thereby aligning the second time between the first communication device and the second communication device.

[0169] In step S23, AI communication processing of the AI ​​model is performed with the second communication device based on the second time.

[0170] In the AI ​​communication method provided in the embodiments of the present disclosure, a first communication device determines a first time representing AI task processing time and transmits the first time to a second communication device. The second communication device determines a second time representing AI communication processing based on the first time. The first and second communication devices align the second time.

[0171] For example, the second time is expressed in communication time units, which can make the AI ​​processing time more compatible with the communication system and reduce the complexity of subsequent communication processing.

[0172] In the AI ​​communication method provided by the embodiment of the present disclosure, the second time for AI communication processing may also be determined by the first communication device.

[0173] As shown in Figure 2c, Figure 2c is a flowchart of another AI communication method according to an exemplary embodiment. In one embodiment shown in Figure 2c, based on the first time, AI communication is performed, including the following steps:

[0174] In step S31 , a second time is determined based on the processing time indicated by the first time, the second time indicating the time of the AI ​​communication processing.

[0175] In the embodiment of the present disclosure, the first communication device may determine the second time based on the processing time represented by the first time.

[0176] For example, the processing time represented by the first time and the implementation scheme of the second time are the same as those in the above embodiment, and are not described in detail here. It should be noted that in the embodiment of the present disclosure, the second time is determined by the first communication device.

[0177] In step S32 , AI communication of the AI ​​model is performed based on the second time.

[0178] In the AI ​​communication method provided by the embodiment of the present disclosure, the first communication device determines a first time representing an AI task processing time, and determines a second time representing an AI communication process based on the first time.

[0179] It is understandable that the second time may be a time expressed based on a communication time unit, or may be expressed based on other forms, and the embodiment of the present disclosure does not limit this.

[0180] In one implementation of the AI ​​communication method provided by the embodiments of the present disclosure, the processing time of processing the AI ​​task based on the first time representation may be the processing time corresponding to the AI ​​model supported by the first communication device. The processing time corresponding to the AI ​​model supported by the first communication device is based on the first time representation.

[0181] In the embodiment of the present disclosure, for different AI communication processing contents based on the AI ​​model, a corresponding first time representation method is selected.

[0182] Exemplarily, when the communication processing content of the AI ​​model is the activation of the AI ​​model, the corresponding processing time can be expressed based on absolute time or by communication time units.

[0183] Exemplarily, when the communication processing content of the AI ​​model is the switching of the AI ​​model, the corresponding processing time can be expressed based on absolute time or by communication time units.

[0184] Exemplarily, when the communication processing content of the AI ​​model is the reasoning of the AI ​​model, the corresponding processing time can be represented by an AI time unit.

[0185] In another implementation of the AI ​​communication method provided by an embodiment of the present disclosure, the processing time for processing the AI ​​task based on the first time representation may be a processing time selected from a processing time set, and the processing time set includes the processing time based on the first time representation.

[0186] In the embodiment of the present disclosure, the processing time set may include: an absolute time set, a communication time unit set, and an AI time unit set.

[0187] Exemplarily, the elements in the absolute time set are the first time expressed in the form of absolute time, for example: 1 millisecond, 2 milliseconds, 3 milliseconds...a millisecond.

[0188] Exemplarily, the elements in the communication time unit set are first times expressed in the form of communication time units, for example: 1 slot, 2 slots, 3 slots . . . b slots.

[0189] Exemplarily, the elements in the AI ​​time unit set are first times expressed in the form of AI time units, for example: 1 AI time unit, 2 AI time units, 3 AI time units...N AI time units.

[0190] In the embodiment of the present disclosure, for different AI communication processing contents based on the AI ​​model, a corresponding first time representation method is selected.

[0191] Exemplarily, when the communication processing content of the AI ​​model is the activation of the AI ​​model, the corresponding processing time set may be an absolute time set or a communication time unit set.

[0192] When the communication processing content of the AI ​​model is the switching of the AI ​​model, the corresponding processing time set can be an absolute time set or a communication time unit set.

[0193] When the communication processing content of the AI ​​model is the reasoning of the AI ​​model, the corresponding processing time set can be an AI time unit set.

[0194] In an embodiment of the present disclosure, for the reasoning of an AI model or AI function, an inference time set can be predefined through a protocol. The inference time in the set is an element of a unit corresponding to absolute time. The first communication device can select the corresponding element from the preset time set for reporting.

[0195] In an embodiment of the present disclosure, for the reasoning of an AI model or AI function, an inference time set can be predefined through a protocol. The inference time in the set is an element of a unit corresponding to a communication time unit. The first communication device can select a corresponding element from the preset time set for reporting.

[0196] In the disclosed embodiments, when selecting a processing time from a processing time set, the selection is made based on the processing capability of the first communication device. For example, the faster the AI ​​task processing time is, the smaller the selected processing time value is. Specifically, in the case where the first time includes an AI time unit, the processing time value selected from the processing time set is selected based on the basic AI processing task (pre-set AI task) and the processing capability of the first communication device.

[0197] It will be appreciated that the above embodiments provide detailed descriptions of the case where the AI ​​model or AI model function uses absolute time as the first time for model inference. When the AI ​​model or AI model function uses communication time units or AI time units as the first time for model activation or switching, the corresponding embodiments are similar to the above embodiments and will not be further described here.

[0198] 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.

[0199] Based on the same concept, the embodiment of the present disclosure also provides an AI communication method.

[0200] FIG3 is a flow chart of an AI communication method according to an exemplary embodiment. As shown in FIG3 , the AI ​​communication method is executed by a second communication device, which may be a network device or a terminal device. The AI ​​communication method includes the following steps:

[0201] In step S41, a first time sent by a first communication device is received, where the first time is used to represent a processing time for processing an AI task based on an AI model.

[0202] In step S42, AI communication processing based on the AI ​​model is performed based on the first time.

[0203] In one embodiment, the first time is represented based on at least one of the following: absolute time; communication time unit; AI time unit, where the AI ​​time unit is determined based on a preset AI task.

[0204] In one implementation of the present disclosure, AI communication processing based on the AI ​​model includes at least one of the following:

[0205] AI model reasoning, AI model activation, and AI model switching.

[0206] It should be further explained that the AI ​​communication processing based on the AI ​​model involved in the following embodiments of the present disclosure includes one or more of the reasoning of the AI ​​model, the activation of the AI ​​model, and the switching of the AI ​​model.

[0207] In the AI ​​communication method provided by the embodiments of the present disclosure, the AI ​​model inference time may be determined, the AI ​​model activation time may be determined, and the AI ​​model switching time may be determined.

[0208] In the embodiment of the present disclosure, the first time received by the second communication device is the same as or similar to the first time sent by the first communication device in the above embodiment. Therefore, for the relationship between the first time received by the second communication device, the processing time, and the AI ​​communication processing based on the AI ​​model based on the first time, please refer to the relevant description in the embodiment of the first communication device above, and the embodiment of the present disclosure will not be repeated here one by one.

[0209] In one embodiment, the AI ​​time unit is the processing time for processing a preset AI task based on the AI ​​model; or the AI ​​time unit includes computing power resources for processing a preset AI task based on the AI ​​model.

[0210] In one embodiment, performing AI communication based on an AI model at a first time includes:

[0211] Receive the processing time of an AI task based on the first time represented by a first communication device that communicates with a second communication device; determine a second time represented by a communication time unit, the second time being determined by the second communication device based on the processing time represented by the first time; and perform AI communication processing of the AI ​​model with the first communication device based on the second time.

[0212] In one embodiment, the processing time of the AI ​​task represented based on the first time includes at least one of the following:

[0213] The processing time corresponding to the AI ​​model supported by the first communication device, the processing time is based on the first time representation; or the processing time selected in the processing time set, the processing time set includes the processing time based on the first time representation.

[0214] In one embodiment, AI communication is performed based on a first time, including: determining a second time based on a processing time represented by the first time, where the second time is a communication time represented by a communication time unit; and performing AI communication processing of an AI model based on the second time.

[0215] In one embodiment, AI communication processing based on the AI ​​model includes at least one of the following: reasoning of the AI ​​model, activation of the AI ​​model, and switching of the AI ​​model.

[0216] In one embodiment, the AI ​​model includes at least one of an AI function and a model corresponding to the AI ​​function.

[0217] In one implementation, the first communication device is a terminal, and the second communication device is a network device; or the first communication device is a network device, and the second communication device is a terminal.

[0218] It is understood that the implementation process of the AI ​​communication method executed by the second communication device in the embodiment of the present disclosure is similar to that of the AI ​​communication method executed by the first communication device. The similarities will not be repeated here, and reference may be made to the implementation process of the AI ​​communication method executed by the first communication device. For example, for the first time, reference may be made to the relevant embodiments regarding the processing time involved in the terminal executing the AI ​​communication method.

[0219] Based on the same concept, an embodiment of the present disclosure further provides an AI communication system. The AI ​​communication system includes a first communication device and a second communication device. The first communication device and the second communication device interact to implement an AI communication method.

[0220] Figure 4 is a schematic diagram of a method interaction of an AI communication system shown in an exemplary embodiment of the present disclosure. As shown in Figure 4, the embodiment of the present disclosure relates to an AI communication system, and the above method includes:

[0221] Step S51: The first communication device determines a first time.

[0222] In one embodiment, the first time is used to represent the processing time of processing the AI ​​task based on the AI ​​model.

[0223] In one embodiment, the first time is expressed based on at least one of the following: absolute time; communication time unit; AI time unit.

[0224] Furthermore, the AI ​​time unit is determined based on a preset AI task.

[0225] Furthermore, the AI ​​time unit includes the processing time for processing a preset AI task based on the AI ​​model; or the AI ​​time unit includes the computing power resources for processing a preset AI task based on the AI ​​model.

[0226] Step S52: Perform AI communication processing based on the AI ​​model based on the first time.

[0227] In one embodiment, performing AI communication includes:

[0228] Sending a processing time of an AI task represented by a first time to a second communication device that communicates with the first communication device; obtaining a second time represented by a communication time unit, where the second time is determined by the second communication device based on the processing time represented by the first time; and performing AI communication processing of an AI model with the second communication device based on the second time.

[0229] In one embodiment, the processing time of the AI ​​task represented based on the first time includes at least one of the following:

[0230] The processing time corresponding to the AI ​​model supported by the first communication device, the processing time is based on the first time representation; or the processing time selected in the processing time set, the processing time set includes the processing time based on the first time representation.

[0231] In one embodiment, performing AI communication based on the first time includes: determining a second time represented by a communication time unit based on a processing time represented by the first time, the second time being determined by the first communication device based on the processing time represented by the first time;

[0232] Based on the second time, AI communication processing of the AI ​​model is performed.

[0233] In one embodiment, AI communication processing based on the AI ​​model includes at least one of the following: reasoning of the AI ​​model, activation of the AI ​​model, and switching of the AI ​​model.

[0234] In one embodiment, the AI ​​model includes at least one of an AI function and a model corresponding to the AI ​​function.

[0235] 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.

[0236] Based on the same concept, an embodiment of the present disclosure also provides an AI communication device.

[0237] Figure 5a is a structural block diagram of an AI communication apparatus according to an exemplary embodiment, wherein the AI ​​communication apparatus is executed by a first communication device, which may be a terminal or a network device.

[0238] As shown in Figure 5a, an embodiment of the present disclosure provides an AI communication device, including: a processing unit 501, used to determine a first time, the first time is used to represent the processing time of processing an AI task based on an AI model; and based on the first time, perform AI communication processing based on the AI ​​model.

[0239] In one embodiment, the first time is represented based on at least one of the following: absolute time; communication time unit; AI time unit, where the AI ​​time unit is determined based on a preset AI task.

[0240] In one embodiment, the AI ​​time unit includes the processing time for processing a preset AI task based on the AI ​​model; or the AI ​​time unit includes the computing power resources for processing a preset AI task based on the AI ​​model.

[0241] In one embodiment, the AI ​​communication device further includes a sending unit and a receiving unit, the sending unit being used to send a processing time based on a first time representation to a second communication device communicating with the first communication device; the receiving unit being used to obtain a second time, which is the time for performing AI communication processing and is determined by the second communication device based on the first time; the processing unit and the second communication device perform AI communication processing of the AI ​​model based on the second time.

[0242] In one embodiment, the processing unit performs AI communication based on the AI ​​model based on the first time in the following manner: based on the processing time represented by the first time, determining a second time, the second time being the time for performing AI communication processing; and performing AI communication processing of the AI ​​model based on the second time.

[0243] In one embodiment, the processing time of the AI ​​task represented by the first time includes at least one of the following:

[0244] a processing time corresponding to an AI model supported by the first communication device, the processing time being represented based on the first time; or

[0245] The processing time selected from the processing time set includes the processing time represented based on the first time.

[0246] In one embodiment, AI communication processing based on the AI ​​model includes at least one of the following:

[0247] AI model reasoning, AI model activation, and AI model switching.

[0248] In one embodiment, the AI ​​model includes at least one of an AI function and a model corresponding to the AI ​​function.

[0249] In one implementation, the first communication device is a terminal, and the second communication device is a network device; or the first communication device is a network device, and the second communication device is a terminal.

[0250] It can be understood that the second time represents the communication processing time.

[0251] Furthermore, the time unit used for the second time may be the same as the time unit used for the first time, or may be another time unit different from the time unit used for the first time.

[0252] Based on the same concept, an embodiment of the present disclosure also provides an AI communication device.

[0253] FIG5 b is a structural block diagram of an AI communication apparatus according to an exemplary embodiment, wherein the AI ​​communication apparatus is executed by a second communication device, which may be a network device or a terminal.

[0254] As shown in FIG5b , an embodiment of the present disclosure provides an AI communication device, including:

[0255] The processing unit 502 is used to receive a first time sent by a first communication device, where the first time is used to represent the processing time of processing an AI task based on an AI model; and to perform AI communication processing based on the AI ​​model based on the first time.

[0256] In one embodiment, the first time is represented based on at least one of the following: absolute time; communication time unit; AI time unit, where the AI ​​time unit is determined based on a preset AI task.

[0257] In one embodiment, the AI ​​time unit includes the processing time for processing a preset AI task based on the AI ​​model; or the AI ​​time unit includes the computing power resources for processing a preset AI task based on the AI ​​model.

[0258] In one embodiment, the processing unit 502 determines a second time based on the first time (representing the processing time), where the second time is the time for performing AI communication processing. The AI ​​communication apparatus further includes a sending unit that sends the second time to the first communication device. The processing unit 502 and the first communication device perform AI communication processing of the AI ​​model based on the second time.

[0259] In one embodiment, the processing unit 502 performs AI communication based on the first time in the following manner:

[0260] Based on the processing time represented by the first time, a second time is determined, where the second time is the time for performing AI communication processing; based on the second time, AI communication processing of the AI ​​model is performed.

[0261] In one embodiment, the processing time represented by the first time includes at least one of the following: the processing time corresponding to the AI ​​model supported by the first communication device, and the processing time is based on the first time representation; the processing time selected in the processing time set, and the processing time set includes the processing time based on the first time representation.

[0262] In one embodiment, AI communication processing based on the AI ​​model includes at least one of the following: reasoning of the AI ​​model, activation of the AI ​​model, and switching of the AI ​​model.

[0263] In one embodiment, the AI ​​model includes at least one of an AI function and a model corresponding to the AI ​​function.

[0264] In one implementation, the first communication device is a terminal, and the second communication device is a network device; or the first communication device is a network device, and the second communication device is a terminal.

[0265] 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.

[0266] Figure 6 is a block diagram of a communication apparatus 600 according to an exemplary embodiment. For example, the apparatus 600 may be a mobile phone, a computer, a digital broadcast terminal, a messaging device, a game console, a tablet device, a medical device, a fitness device, a personal digital assistant, etc.

[0267] 6 , apparatus 600 may include one or more of the following components: a processing component 602 , a memory 604 , a power component 606 , a multimedia component 608 , an audio component 610 , an input / output (I / O) interface 612 , a sensor component 614 , and a communication component 616 .

[0268] The processing component 602 generally controls the overall operation of the device 600, such as operations associated with display, phone calls, data communications, camera operation, and recording operations. The processing component 602 may include one or more processors 620 to execute instructions to perform all or part of the steps of the above-described method. In addition, the processing component 602 may include one or more modules to facilitate interaction between the processing component 602 and other components. For example, the processing component 602 may include a multimedia module to facilitate interaction between the multimedia component 608 and the processing component 602.

[0269] The memory 604 is configured to store various types of data to support operations on the device 600. Examples of such data include instructions for any application or method operating on the device 600, contact data, phone book data, messages, pictures, videos, etc. The memory 604 can be implemented by any type of volatile or non-volatile storage device, or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk, or optical disk.

[0270] The power component 606 provides power to the various components of the device 600. The power component 606 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power to the device 600.

[0271] The multimedia component 608 includes a screen that provides an output interface between the device 600 and the user. In some embodiments, the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen can be implemented as a touch screen to receive input signals from the user. The touch panel includes one or more touch sensors to sense touches, slides, and gestures on the touch panel. The touch sensor can not only sense the boundaries of the touch or slide action, but also detect the duration and pressure associated with the touch or slide operation. In some embodiments, the multimedia component 608 includes a front camera and / or a rear camera. When the device 600 is in an operating mode, such as a shooting mode or a video mode, the front camera and / or the rear camera can receive external multimedia data. Each front camera and rear camera can be a fixed optical lens system or have focal length and optical zoom capabilities.

[0272] The audio component 610 is configured to output and / or input audio signals. For example, the audio component 610 includes a microphone (MIC), which is configured to receive external audio signals when the device 600 is in an operating mode, such as a call mode, a recording mode, and a voice recognition mode. The received audio signal can be further stored in the memory 604 or transmitted via the communication component 616. In some embodiments, the audio component 610 also includes a speaker for outputting audio signals.

[0273] I / O interface 612 provides an interface between processing component 602 and peripheral interface modules, such as a keyboard, click wheel, buttons, etc. These buttons may include but are not limited to: a home button, volume buttons, a start button, and a lock button.

[0274] The sensor assembly 614 includes one or more sensors for providing various aspects of the status assessment of the device 600. For example, the sensor assembly 614 can detect the open / closed state of the device 600, the relative positioning of components, such as the display and keypad of the device 600. The sensor assembly 614 can also detect changes in the position of the device 600 or a component of the device 600, the presence or absence of user contact with the device 600, the orientation or acceleration / deceleration of the device 600, and temperature changes of the device 600. The sensor assembly 614 may include a proximity sensor configured to detect the presence of nearby objects without any physical contact. The sensor assembly 614 may also include an optical sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor assembly 614 may also include an accelerometer, a gyroscope, a magnetic sensor, a pressure sensor, or a temperature sensor.

[0275] The communication component 616 is configured to facilitate wired or wireless communication between the device 600 and other devices. The device 600 can access a wireless network based on a communication standard, such as WiFi, 2G or 3G, or a combination thereof. In an exemplary embodiment, the communication component 616 receives a broadcast signal or broadcast-related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 616 also includes a near field communication (NFC) module to facilitate short-range communication. For example, the NFC module can be implemented based on radio frequency identification (RFID) technology, infrared data association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology and other technologies.

[0276] In an exemplary embodiment, the apparatus 600 may be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the above-described method.

[0277] In an exemplary embodiment, a non-transitory computer-readable storage medium including instructions is also provided, such as a memory 604 including instructions, which can be executed by the processor 620 of the apparatus 600 to perform the above method. For example, the non-transitory computer-readable storage medium can be a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, etc.

[0278] Figure 7 is a block diagram illustrating an apparatus 700 for communication, according to an exemplary embodiment. For example, apparatus 700 may be provided as a network device. Referring to Figure 7 , apparatus 700 includes a processing component 722, which further includes one or more processors, and memory resources represented by memory 732 for storing instructions, such as applications, executable by processing component 722. The applications stored in memory 732 may include one or more modules, each corresponding to a set of instructions. Furthermore, processing component 722 is configured to execute the instructions to perform the aforementioned method.

[0279] The device 700 may also include a power supply component 726 configured to perform power management of the device 700, a wired or wireless network interface 750 configured to connect the device 700 to a network, and an input / output (I / O) interface 758. The device 700 may operate based on an operating system stored in the memory 732, such as Windows Server™, Mac OS X™, Unix™, Linux™, FreeBSD™, or the like.

[0280] In an exemplary embodiment, a non-transitory computer-readable storage medium including instructions is also provided, such as a memory 732 including instructions, which can be executed by the processing component 722 of the apparatus 700 to perform the above method. For example, the non-transitory computer-readable storage medium can be a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, etc.

[0281] The present disclosure provides an artificial intelligence communication method, device, and storage medium. In some embodiments, the terms "communication method," "information processing method," and "communication method" are interchangeable; the terms "communication device," "information processing device," and "information processing system" are interchangeable; and the terms "information processing system," "communication system," and "communication system" are interchangeable.

[0282] The embodiments of the present disclosure are not exhaustive and are merely illustrative of some embodiments, and are not intended to be a specific limitation on the scope of protection of the present disclosure. In the absence of contradiction, each step in a certain embodiment can be implemented as an independent embodiment, and the steps can be arbitrarily combined. For example, a solution after removing some steps in a certain embodiment can also be implemented as an independent embodiment, and the order of the steps in a certain embodiment can be arbitrarily exchanged. In addition, the optional implementation methods in a certain embodiment can be arbitrarily combined; in addition, the embodiments can be arbitrarily combined. For example, some or all steps of different embodiments can be arbitrarily combined, and a certain embodiment can be arbitrarily combined with the optional implementation methods of other embodiments.

[0283] In the various embodiments of the present disclosure, unless otherwise specified or logically conflicting, the terms and / or descriptions between the various embodiments are consistent and can be referenced from each other. The technical features of different embodiments can be combined to form new embodiments based on their inherent logical relationships. The terms used in the embodiments of the present disclosure are only for the purpose of describing specific embodiments and are not intended to limit the present disclosure.

[0284] It is further understood that in the present disclosure, "plurality" refers to two or more than two, and other quantifiers are similar. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. The character " / " generally indicates that the related objects before and after are in an "or" relationship. The singular forms "a", "the" and "the" are also intended to include the plural forms, unless the context clearly indicates otherwise.

[0285] It is further understood that the meanings of words such as "in response to" and "if" involved in this disclosure depend on the context and the actual usage scenario. For example, the word "in response to" used herein can be interpreted as "at..." or "when..." or "if".

[0286] 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.

[0287] 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.

[0288] 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.

[0289] It should be understood that the present disclosure is not limited to the exact structures described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the scope of the appended claims.

Claims

1. An artificial intelligence (AI) communication method, characterized in that: Executed by a first communication device, the method includes: Determining a first time, where the first time is used to represent a processing time of processing the AI ​​task based on the AI ​​model; Based on the first time, AI communication processing based on the AI ​​model is performed.

2. The method according to claim 1, characterized in that The first time is represented based on at least one of the following: Absolute time; Communication time unit; The AI ​​time unit is determined based on a preset AI task.

3. The method according to claim 2, characterized in that The AI ​​time unit includes the processing time of processing a preset AI task based on the AI ​​model; or The AI ​​time unit includes computing resources for processing preset AI tasks based on the AI ​​model.

4. The method according to any one of claims 1 to 3, characterized in that The performing AI communication based on the AI ​​model based on the first time includes: sending a processing time based on the first time representation to a second communication device communicating with the first communication device; Acquire a second time, where the second time is a time for performing AI communication processing and is determined by the second communication device based on the first time; Perform AI communication processing of the AI ​​model with the second communication device based on the second time.

5. The method according to any one of claims 1 to 3, characterized in that: The performing AI communication based on the AI ​​model based on the first time includes: Determine a second time based on the processing time represented by the first time, where the second time is the time for performing AI communication processing; Based on the second time, AI communication processing of the AI ​​model is performed.

6. The method according to claim 4 or 5, characterized in that: The processing time represented by the first time includes at least one of the following: a processing time corresponding to an AI model supported by the first communication device, the processing time being represented based on the first time; or A processing time selected from a set of processing times, the set of processing times including a processing time represented based on the first time.

7. The method according to claim 1, characterized in that The AI ​​communication processing based on the AI ​​model includes at least one of the following: Reasoning of AI models, activation of AI models, and switching of AI models.

8. The method according to claim 1, characterized in that The AI ​​model includes at least one of an AI function and a model corresponding to the AI ​​function.

9. The method according to any one of claims 1 to 8, characterized in that: The first communication device is a terminal, and the second communication device is a network device; or The first communication device is a network device, and the second communication device is a terminal.

10. An artificial intelligence AI communication method, characterized in that: Executed by a second communication device, the method includes: Receiving a first time sent by a first communication device, where the first time is used to indicate a processing time of processing an AI task based on an AI model; Based on the first time, AI communication processing based on the AI ​​model is performed.

11. The method according to claim 10, characterized in that The first time is represented based on at least one of the following: Absolute time; Communication time unit; The AI ​​time unit is determined based on a preset AI task.

12. The method according to claim 11, characterized in that The AI ​​time unit includes the processing time of processing a preset AI task based on the AI ​​model; or The AI ​​time unit includes computing resources for processing preset AI tasks based on the AI ​​model.

13. The method according to any one of claims 10 to 12, characterized in that The performing AI communication based on the AI ​​model based on the first time includes: Determine a second time based on the processing time represented by the first time, where the second time is the time for performing AI communication processing; sending the second time to the first communication device; Perform AI communication processing of the AI ​​model with the first communication device based on the second time.

14. The method according to any one of claims 10 to 12, characterized in that The performing AI communication based on the first time includes: Determine a second time based on the processing time represented by the first time, where the second time is the time for performing AI communication processing; Based on the second time, AI communication processing of the AI ​​model is performed.

15. The method according to claim 13 or 14, characterized in that The processing time represented by the first time includes at least one of the following: The processing time corresponding to the AI ​​model supported by the first communication device, the processing time being based on the first time indicates; or A processing time selected from a set of processing times, the set of processing times including a processing time represented based on the first time.

16. The method according to claim 10, characterized in that The AI ​​communication processing based on the AI ​​model includes at least one of the following: Reasoning of AI models, activation of AI models, and switching of AI models.

17. The method according to claim 10, characterized in that The AI ​​model includes at least one of an AI function and a model corresponding to the AI ​​function.

18. The method according to any one of claims 10 to 17, characterized in that: The first communication device is a terminal, and the second communication device is a network device; or The first communication device is a network device, and the second communication device is a terminal.

19. An AI communication device, characterized in that: The method is performed by a first communication device, and the apparatus includes: A processing unit is used to determine a first time, where the first time is used to represent the processing time of processing an AI task based on an AI model; and based on the first time, perform AI communication processing based on the AI ​​model.

20. The AI ​​communication device according to claim 19, characterized in that: The first time is represented based on at least one of the following: Absolute time; Communication time unit; The AI ​​time unit is determined based on a preset AI task.

21. An AI communication device, characterized in that: The method is performed by a second communication device, and the apparatus includes: a processing unit, configured to receive a first time sent by a first communication device, where the first time is used to indicate a processing time for processing an AI task based on an AI model; and Based on the first time, AI communication processing based on the AI ​​model is performed.

22. The AI ​​communication device according to claim 21, characterized in that: The first time is represented based on at least one of the following: Absolute time; Communication time unit; The AI ​​time unit is determined based on a preset AI task.

23. An AI communication device, characterized in that: include: processor; a memory for storing processor-executable instructions; The processor is configured to: execute the AI ​​communication method described in any one of claims 1 to 9, or execute the AI ​​communication method described in any one of claims 10 to 18.

24. A storage medium, characterized in that: The storage medium stores instructions. When the instructions in the storage medium are executed by the processor of the terminal, the terminal is enabled to execute the AI ​​communication method described in any one of claims 1 to 9, or execute the AI ​​communication method described in any one of claims 10 to 18.

Images