An artificial intelligence communication method, device and storage medium

Abstract

The present disclosure relates to an artificial intelligence communication method, device and storage medium. The artificial intelligence communication method comprises: determining a first time, the first time being used to represent a processing time of processing an AI task based on an AI model; and performing AI communication processing based on the AI model based on the first time. The present disclosure determines the time for communication processing based on the AI model through the determination of the first time.

Description

Technical Field

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

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

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

[0004] To overcome the problems existing in related technologies, this disclosure provides an artificial intelligence communication method, device and storage medium.

[0005] According to a first aspect of the present disclosure, an artificial intelligence (AI) communication method is provided, executed by a first communication device, comprising determining a first time, the first time being used to represent the processing time of processing an AI task based on an AI model; and performing AI communication processing based on the first time.

[0006] In one implementation, the first time is represented based on at least one of the following: absolute time; communication time unit; AI time unit, wherein the AI ​​time unit is determined based on a preset AI task.

[0007] In another embodiment, the AI ​​time unit includes processing time for processing a preset AI task based on an AI model; or the AI ​​time unit includes computing resources for processing a preset AI task based on an AI model.

[0008] In another implementation, the step of performing AI communication processing based on the AI ​​model based on the first time includes:

[0009] Send a processing time based on the first time to a second communication device that communicates with the first communication device; 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; and perform AI communication processing of the AI ​​model with the second communication device based on the second time.

[0010] In another implementation, the step of performing AI model-based AI communication based on the first time includes:

[0011] Based on the processing time represented by the first time, a second time is determined, which is the time for performing AI communication processing; based on the second time, AI communication processing of the AI ​​model is performed.

[0012] 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, the processing time being based on the first time representation; or a processing time selected from a set of processing times, the set of processing times including processing times based on the first time representation.

[0013] In another embodiment, the AI ​​communication processing based on the AI ​​model includes at least one of the following: AI model inference, AI model activation, and AI model switching.

[0014] In another embodiment, the AI ​​model includes at least one of an AI function and a model corresponding to the AI ​​function.

[0015] In 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.

[0016] According to a second aspect of the present disclosure, an AI communication method is provided, executed by a second device, the method comprising:

[0017] Receive a first time sent by a first communication device, wherein the first time is used to represent the processing time for processing AI tasks based on an AI model;

[0018] Based on the first time frame, AI communication processing based on the AI ​​model is performed.

[0019] In one implementation, the first time is represented based on at least one of the following: absolute time; communication time unit; AI time unit, wherein the AI ​​time unit is determined based on a preset AI task.

[0020] In another embodiment, the AI ​​time unit includes processing time for processing a preset AI task based on an AI model; or the AI ​​time unit includes computing resources for processing a preset AI task based on an AI model.

[0021] In another implementation, the step of performing AI model-based AI communication based on the first time includes:

[0022] Based on the processing time represented by the first time, a second time is determined, which is the time for performing AI communication processing; the second time is sent to the first communication device; and AI communication processing of the AI ​​model is performed with the first communication device based on the second time.

[0023] In another implementation, the step of performing AI communication based on the first time includes:

[0024] Based on the processing time represented by the first time, a second time is determined, which is the time for performing AI communication processing; based on the second time, AI communication processing of the AI ​​model is performed.

[0025] In another embodiment, the processing time represented by the first time includes at least one of the following:

[0026] The processing time corresponding to the AI ​​model supported by the first communication device is based on the first time representation; or

[0027] The processing time selected from the set of processing times, which includes processing times represented based on the first time.

[0028] In another implementation, the step of performing AI communication based on the first time includes:

[0029] Based on the processing time represented by the first time, a second time is determined, wherein the second time is the communication time represented by the communication time unit; based on the second time, AI communication processing of the AI ​​model is performed.

[0030] In another embodiment, the AI ​​communication processing based on the AI ​​model includes at least one of the following:

[0031] AI model inference, AI model activation, and AI model switching.

[0032] In another embodiment, the AI ​​model includes at least one of an AI function and a model corresponding to the AI ​​function.

[0033] In 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.

[0034] According to a third aspect of the present disclosure, an AI communication device is provided, executed by a first communication device, the device comprising:

[0035] The processing unit is configured to determine a first time, which represents 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.

[0036] In one implementation, the first time is represented based on at least one of the following: absolute time; communication time unit; AI time unit, wherein the AI ​​time unit is determined based on a preset AI task.

[0037] In another embodiment, the AI ​​time unit includes processing time for processing a preset AI task based on an AI model; or the AI ​​time unit includes computing resources for processing a preset AI task based on an AI model.

[0038] 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 to a second communication device that communicates with the first communication device. The receiving unit is used to acquire 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.

[0039] In another embodiment, the processing unit performs AI communication based on the AI ​​model in the following manner based on the first time: determining a second time based on the processing time represented by the first time, wherein the second time is the time for performing AI communication processing; and performing AI communication processing based on the AI ​​model based on the second time.

[0040] In another embodiment, the processing time of 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, wherein the processing time is based on the first time representation; or

[0041] The processing time selected from the set of processing times, which includes processing times represented based on the first time.

[0042] In another embodiment, the AI ​​communication processing based on the AI ​​model includes at least one of the following:

[0043] AI model inference, AI model activation, and AI model switching.

[0044] In another embodiment, the AI ​​model includes at least one of an AI function and a model corresponding to the AI ​​function.

[0045] In 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.

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

[0047] The processing unit is configured to receive a first time transmitted by a first communication device, the first time representing the processing time of an AI task based on an AI model; and to perform AI communication processing based on the first time.

[0048] In one implementation, the first time is represented based on at least one of the following: absolute time; communication time unit; AI time unit, wherein the AI ​​time unit is determined based on a preset AI task.

[0049] In another embodiment, the AI ​​time unit includes processing time for processing a preset AI task based on an AI model; or the AI ​​time unit includes computing resources for processing a preset AI task based on an AI model.

[0050] In another embodiment, the processing unit determines a second time based on the processing time represented by the first time, the second time being the time for performing AI communication processing; the AI ​​communication device further 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.

[0051] In another embodiment, the processing unit performs AI communication based on the first time in the following manner:

[0052] Based on the processing time represented by the first time, a second time is determined, which is the time for performing AI communication processing; based on the second time, AI communication processing of the AI ​​model is performed.

[0053] 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, the processing time being based on the first time representation; and the processing time selected from a set of processing times, the set of processing times including processing times based on the first time representation.

[0054] In another embodiment, the AI ​​communication processing based on the AI ​​model includes at least one of the following: AI model inference, AI model activation, and AI model switching.

[0055] In another embodiment, the AI ​​model includes at least one of an AI function and a model corresponding to the AI ​​function.

[0056] In 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.

[0057] According to a fifth aspect 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 AI ​​communication method described in the first aspect or any embodiment of the first aspect.

[0058] According to a sixth aspect 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 AI ​​communication method described in the second aspect or any embodiment of the second aspect.

[0059] According to a seventh aspect of the present disclosure, a storage medium is provided, the storage medium storing instructions that, when executed by a processor of a first communication device, enable the first communication device to execute the AI ​​communication method described in the first aspect or any embodiment of the first aspect.

[0060] According to an eighth aspect of the present disclosure, a storage medium is provided that stores instructions, which, when executed by a processor of a second communication device, enable the second communication device to perform the AI ​​communication method described in the second aspect or any embodiment of the second aspect.

[0061] According to a ninth aspect of the present disclosure, an artificial intelligence communication system is provided, the system comprising: a first communication device for performing the method described in the first aspect or any embodiment thereof; and a second communication device for performing the method described in the second aspect or any embodiment thereof.

[0062] The technical solutions provided by the embodiments of this disclosure may include the following beneficial effects: determining the first time for processing AI tasks based on the AI ​​model, and performing subsequent communication processing based on the determined first time, can determine the processing time representation method corresponding to the subsequent communication processing, thereby reducing the complexity of the subsequent communication processing process.

[0063] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure. Attached Figure Description

[0064] The accompanying drawings, which are incorporated in and form a part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure.

[0065] Figure 1 This is a schematic diagram illustrating a wireless communication system according to an exemplary embodiment.

[0066] Figure 2a This is a flowchart illustrating an AI communication method according to an exemplary embodiment.

[0067] Figure 2b This is a flowchart illustrating another AI communication method according to an exemplary embodiment.

[0068] Figure 2c This is a flowchart illustrating yet another AI communication method according to an exemplary embodiment.

[0069] Figure 3 This is a flowchart illustrating an AI communication method according to an exemplary embodiment.

[0070] Figure 4 This is a schematic diagram of the architecture of an AI communication system according to an exemplary embodiment.

[0071] Figure 5a This is a structural block diagram of an AI communication device according to an exemplary embodiment.

[0072] Figure 5b This is a structural block diagram of an AI communication device according to an exemplary embodiment.

[0073] Figure 6 This is a block diagram of an apparatus for AI communication according to an exemplary embodiment.

[0074] Figure 7 This is a block diagram of an apparatus for AI communication according to an exemplary embodiment. Detailed Implementation

[0075] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this disclosure.

[0076] The communication method disclosed herein can be applied to... Figure 1 The wireless communication system shown. (See attached image) Figure 1 As shown, this wireless communication system includes network equipment and terminals. The terminals connect to the network equipment via wireless resources and transmit data.

[0077] Understandable, Figure 1 The wireless communication system shown is for illustrative purposes only. A wireless communication system may also include other network devices, such as core network equipment, wireless relay equipment, and wireless backhaul equipment. Figure 1 Not shown in the diagram. This disclosure does not limit the number of network devices and terminals included in the wireless communication system.

[0078] It is further understood that the wireless communication system of this disclosure is a network providing wireless communication functionality. The wireless communication system can employ 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), and carrier sense multiple access with collision avoidance. Based on factors such as capacity, speed, and latency, networks can be categorized as 2G networks, 3G networks, 4G networks, or future evolution networks, such as 5G networks. 5G networks can also be referred to as New Radio (NR). For ease of description, this disclosure may sometimes simply refer to the wireless communication network as a network.

[0079] Furthermore, the network device involved in this disclosure can also be referred to as a wireless access network device. This wireless access network device can be: a base station, an evolved Node B (eBY), 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 can also be a gNB in ​​an NR system, or a component or part of a base station. It should be understood that the specific technology and specific device form used in the embodiments of this disclosure are not limited. In this disclosure, the network device can provide communication coverage for a specific geographical area and can communicate with terminals located within that coverage area (cell). Furthermore, when it is a vehicle-to-everything (V2X) communication system, the network device can also be an in-vehicle device.

[0080] Furthermore, the terminal involved in this disclosure can 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 a user. For example, the terminal can be a handheld device with wireless connectivity, an in-vehicle device, etc. Currently, some examples of terminals include: smartphones, customer premise equipment (CPE), pocket personal computers (PPCs), handheld computers, personal digital assistants (PDAs), laptops, tablets, wearable devices, or in-vehicle devices, etc. In addition, when it is a vehicle-to-everything (V2X) communication system, the terminal device can also be an in-vehicle device. It should be understood that the embodiments of this disclosure do not limit the specific technology or specific device form adopted by the terminal.

[0081] In recent years, artificial intelligence (AI) technology has made continuous breakthroughs in many fields, and AI technology is gradually intersecting and penetrating with other disciplines, providing new directions and methods for the development of different disciplines.

[0082] Among related technologies, the 3rd Generation Partnership Project (3GPP) has established a research project on the application of artificial intelligence (AI) technology in wireless air interfaces. This project aims to study the introduction of AI technology into wireless air interfaces and explore how AI technology can assist in improving wireless air interface transmission technology.

[0083] In research on AI communication, AI use cases may include: AI-based beam management and AI-based positioning, etc.

[0084] Understandably, AI use cases can also be called AI features, which are communication scenarios where AI is used to perform a specific communication operation to achieve a certain purpose. Examples include using AI to predict channel information in the time domain or using AI for beam management in the spatial domain. Typically, an AI feature is defined within a protocol.

[0085] Understandably, in the above use cases, each AI use case involves the process of an AI model processing AI tasks, and due to different application cases, the AI ​​tasks processed by the AI ​​model also differ. Therefore, the processing time descriptions of the corresponding AI models for different AI tasks are not entirely the same.

[0086] In related technologies, there is no clear description of how the processing time of the AI ​​model is described in order to conduct AI communication.

[0087] Based on this, this disclosure proposes an AI communication method that clarifies the processing time for AI tasks based on AI models, so that subsequent AI communication processing based on AI models can be performed based on this processing time.

[0088] It should be noted that the AI ​​model involved in the embodiments of this disclosure can be at least one of AI function and AI function corresponding model. Furthermore, the AI ​​model involved in the following embodiments of this disclosure can be replaced with an AI model or an AI function.

[0089] It's important to note that for a single AI use case, multiple AI functions may be defined. For example, for the AI-based Channel State Information (CSI) enhancement use case, AI function #1 supports predicting the ID of the optimal beam, while AI function #2 supports predicting the optimal beam and the corresponding beam measurement results. The implementation of these AI functions relies on AI models. Different AI functions may be implemented using different AI models, or even different AI models can be used to implement different functions. In other words, an AI function can correspond to one or more AI models.

[0090] In one embodiment of this disclosure, the AI ​​model processing AI tasks involved in the following embodiments can be understood as executing the AI ​​model on AI use cases.

[0091] For example, AI models can handle AI tasks including AI-based CSI enhancement, AI-based beam management, and AI-based localization.

[0092] For example, the AI ​​communication method provided in this disclosure has a processing time for AI tasks based on AI models, including at least one of the following: processing time for AI-based CSI enhancement tasks, processing time for AI-based beam management tasks, and processing time for AI-based positioning tasks.

[0093] In the AI ​​communication method provided in this embodiment, the first communication device performs AI communication processing based on an AI model based on a first time.

[0094] In one embodiment of this disclosure, AI communication processing based on an AI model includes at least one of the following:

[0095] AI model inference, AI model activation, and AI model switching.

[0096] It should be further noted that the AI ​​communication processing based on AI models involved in the following embodiments of this disclosure includes one or more of the following: AI model inference, AI model activation, and AI model switching.

[0097] In the AI ​​communication method provided in this embodiment, the AI ​​model inference time can be determined, the AI ​​model activation time can be determined, or the AI ​​model switching time can be determined.

[0098] Figure 2a This is a flowchart illustrating an AI communication method according to an exemplary embodiment, such as... Figure 2a As shown, the AI ​​communication method is executed by a first communication device, which can be a terminal or a network device. The AI ​​communication method includes the following steps:

[0099] In step S11, a first time is determined, which represents the processing time for processing AI tasks based on the AI ​​model.

[0100] In step S12, AI communication processing based on the AI ​​model is performed based on the first time.

[0101] In this embodiment of the disclosure, a processing time for representing AI tasks based on an AI model is determined, and the time representation for processing AI tasks based on an AI model is clarified.

[0102] The term "first time" is used to represent the processing time of an AI model in handling AI tasks. It can be understood as the first time used to measure the time it takes for an AI model to process an AI task.

[0103] In one embodiment of this disclosure, the first time is the time for processing AI tasks based on the AI ​​model, which can be understood as duration.

[0104] In one embodiment of this disclosure, the first time is a time unit for measuring the processing of AI tasks based on an AI model; this time unit can also be understood as a time unit.

[0105] In the AI ​​communication method provided in this embodiment, the first time is a time unit for measuring AI tasks based on an AI model, and is determined based on at least one of the following: AI model inference time, AI model activation time, and AI model switching time.

[0106] For example, for terminals or network devices, the processing time of AI tasks by the AI ​​models deployed at their respective locations can be determined, that is, the first moment.

[0107] In one embodiment of the AI ​​communication method provided in this disclosure, the first time can be represented by a unit used to describe time.

[0108] For example, in conventional physical space, the physical quantity used to describe time is absolute time, and the units of absolute time include: second, millisecond, microsecond, etc.

[0109] In communication systems, the physical unit used to describe time is called the communication time unit. The units of the communication time unit include: Orthogonal Frequency Division Multiplexing (OFDM) symbols, slots, subslots, and the sampling interval of OFDM symbols.

[0110] In some scenarios, the time unit used to describe AI communication, defined through a specific definition, is referred to hereafter as the AI ​​time unit. It can be understood that the AI ​​time unit, defined through a specific definition, is the basic time unit used to measure AI processing tasks.

[0111] In this embodiment of the disclosure, the AI ​​time unit can be determined based on a preset AI task.

[0112] For example, since the AI ​​time unit is a unit that describes the AI ​​processing time through definition, the determination of the AI ​​time unit can be based on the AI ​​task.

[0113] In one implementation scheme, the AI ​​time unit is determined based on the AI ​​task and the corresponding processing time. For example, task A is defined as a pre-set AI task, and the time required to complete task A is defined as Y absolute times. The AI ​​time unit includes the Y absolute times used to complete task A.

[0114] The processing time for an AI task is determined based on the complexity of the model executing the AI ​​task.

[0115] In another implementation, the AI ​​time unit is determined based on the AI ​​task and the corresponding computing resources. For example, task A is defined as a pre-set AI task, and the computing resources required to complete task A are Y FLOPS. The AI ​​time unit includes the Y FLOPS of computing resources used to complete task A.

[0116] The computing resources corresponding to an AI task can be understood as the amount of computing power or resources used to execute a basic AI task. Alternatively, the computing resources corresponding to an AI task can be understood as the processing unit capability for handling the AI ​​task.

[0117] In one embodiment provided by this disclosure, the first time is based on at least one of the following representations: absolute time; communication time unit; and AI time unit.

[0118] In an exemplary embodiment of the AI ​​communication method provided in this disclosure, the first time is based on absolute time representation.

[0119] The first time is based on a unit of measurement for absolute time, such as seconds (s), milliseconds (ms), microseconds (us), etc.

[0120] Taking the inference of an AI model as an example, the first communication device (e.g., a terminal) can report the first processing time corresponding to each of the supported AI model #1 and AI model #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).

[0121] In another implementation, when the first time is expressed based on a unit that measures absolute time, the first communication device may also report in the following ways.

[0122] Select the corresponding processing time from the processing time set, which includes processing times represented based on the first time.

[0123] When the elements in the processing time set have units that measure absolute time, such as 1ms, 2ms, 3ms, etc., the first communication device selects the first processing time corresponding to the AI ​​model from the processing time set. For example, the processing time for AI model #1 is selected as 1ms, and the processing time for AI model #2 is selected as 2ms.

[0124] The AI ​​communication method provided in this disclosure is based on communication time units in the first instance.

[0125] The first time is represented by OFDM symbols, slots, subslots, and the sampling interval of OFDM symbols.

[0126] Taking the inference of an AI model as an example, the first communication device (e.g., a terminal) can report the first processing time corresponding to each of the supported AI model #1 and AI model #2. For example, the first processing time corresponding to AI model #1 (e.g., 1 OFDM symbol) and the first processing time corresponding to AI model #2 (e.g., 2 slots).

[0127] In another implementation, the first communication device may also report the time of first communication based on the measurement of the communication time unit representation in the following manner.

[0128] Select the corresponding processing time from the processing time set, which includes processing times represented based on the first time.

[0129] When the elements in the processing time set have units that measure absolute time, such as 1 OFDM symbol, 2 slots, 3 OFDM symbol sampling intervals, etc., the first communication device selects the first processing time corresponding to the AI ​​model from the processing time set. For example, the processing time for AI model #1 is selected as 1 OFDM symbol, and the processing time for AI model #2 is selected as 2 slots.

[0130] Understandably, the absolute time corresponding to each communication time unit differs under different subcarriers. For example, under subcarrier a, one OFDM symbol sampling interval corresponds to 0.5ms, while under subcarrier b (subcarrier a and subcarrier b are different), one OFDM symbol sampling interval corresponds to 0.3ms.

[0131] In this communication system, communication processing is measured in basic communication time units. In this embodiment, the first time is represented based on communication time units, which makes the I processing time of task A more compatible with the communication system. It also simplifies subsequent communication processing.

[0132] The AI ​​communication method provided in this disclosure is based on AI time unit representation in the first time.

[0133] The first time is represented based on AI time units. For example, task A is defined as a pre-set AI task, and the time required to complete task A is Y absolute time units. The AI ​​time unit includes task A and Y absolute time units; or task A is defined as a pre-set AI task, and the computing resources required to complete task A are Y FLOPS. The AI ​​time unit includes task A and Y FLOPS.

[0134] In this embodiment of the disclosure, the AI ​​time unit can be determined in the following two ways:

[0135] (i) Determine the processing time of the preset AI task and the AI ​​model for processing the preset task.

[0136] For example, let's define a preset AI task as A, where task A can be called the base task, or in some scenarios, a subtask A' of task A can be used as the base task. Taking task A as the base task as an example, the processing time used by the model that processes task A can be considered as one AI time unit. If the processing time used by the model that processes task A is a milliseconds, where a is greater than zero, then a milliseconds in absolute time corresponds to one AI time unit; if the processing time used by the model that processes task A is b slots, where b is greater than zero, then b slots in communication time units correspond to one AI time unit.

[0137] Furthermore, the determination of the processing time for the preset AI task based on the preset AI task and the AI ​​model processing the preset AI task can be: determined based on the complexity of the AI ​​task and the processing time for the AI ​​model processing the preset task.

[0138] For example, the complexity of a preset AI task can be determined in a predefined way. For instance, if the preset task is Channel State Information (CSI) compression, then the complexity of compressing a Physical Resource Block (PRB) can be defined as the complexity of the preset AI task, which is also the complexity of the basic task.

[0139] It is understandable that if there is a linear relationship between the complexity of the preset AI task and the AI ​​time unit corresponding to the model's processing of the basic task (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, the processing time corresponding to the currently processed AI task can be expressed as N AI time units.

[0140] Furthermore, if one AI time unit represents a millisecond, 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.

[0141] For example, the protocol predefines a basic AI processing task. The terminal reports the time it takes to process this basic AI task, using this time as the unit to measure the processing time of the AI ​​models or functions supported by the terminal. For instance, if an 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 ​​models or functions supported by the terminal are measured in units of Y. For example, if the processing time for model A is N AI processing time units, that is, N*Y milliseconds.

[0142] (ii) Determination of computing resources for processing preset AI tasks and AI models based on preset AI tasks.

[0143] For example, let's define a preset AI task as A, which can also be called a basic task. Let's define the maximum computing power of the model processing task A as m, and the computing power used when processing task A as n, where m is greater than or equal to n. Then, the time taken for the model to process task A with computing power n corresponds to one time unit.

[0144] It is understandable that the time taken by the model to process task A with computing power n can be either absolute time or a communication time unit. For example, if the time taken by the model to process task A with computing power n is a milliseconds, then when the model processes 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 processes task A with computing power n, one time unit corresponds to b slots in communication time unit, two time units correspond to 2b slots in communication time unit, and so on.

[0145] For example, the protocol predefines a basic AI processing task and the processing unit capabilities for processing this task. The terminal uses the predefined processing unit configuration to process the defined basic AI processing task, obtaining a basic processing time unit. This time is then used as the unit to measure the processing time of the AI ​​models or AI functions supported by the terminal. For example, an AI processing task A is defined, and the predefined processing unit configuration 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. Then, the AI ​​models or AI functions supported by the terminal are reported in units of Y, and the processing time for model A is N AI processing time units, which is N*Y milliseconds.

[0146] In the AI ​​communication method provided in this embodiment, by determining the AI ​​time unit based on the processing time or computing power resources used by the model to process the preset task, it is possible to simultaneously report information such as the task complexity of the communication device and the computing power of the model during the AI ​​communication process using the AI ​​time unit as the first time.

[0147] For example, the first time can be represented based on absolute time and communication time units.

[0148] For example, the first time can be represented based on absolute time and AI time units.

[0149] For example, the first time can be represented based on communication time and AI time unit.

[0150] For example, the first time can be represented based on absolute time, communication time unit, and AI time unit.

[0151] It should be understood that the foregoing embodiments have already provided a more detailed list of AI communication processing and the corresponding first timeframes. Therefore, only the representation of the first timeframe is given here as an example, and all listed items will not be described in detail.

[0152] The AI ​​communication method provided in this disclosure performs AI model-based AI communication processing based on a first moment used to represent processing AI tasks based on an AI model.

[0153] Figure 2b This is a flowchart illustrating an AI communication method according to an exemplary embodiment. Figure 2b The AI ​​communication method shown is executed by a first communication device, which is a terminal or a network device.

[0154] exist Figure 2b In one embodiment shown, AI communication is performed based on the first moment, including the following steps:

[0155] In step S21, a processing time based on a first time representation is sent to a second communication device that communicates with the first communication device. The processing time represented by the first time representation is the time for processing the AI ​​task.

[0156] In this embodiment of the disclosure, the first communication device sends a processing time based on a 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.

[0157] For ease of description, the AI ​​communication processing time determined based on the first time will be referred to as the second time.

[0158] It is understood that the second time can be a time represented based on communication time units, or it can be represented based on other forms, and this disclosure does not limit this. The representation of the second time satisfies the requirement of aligning 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.

[0159] Furthermore, the time unit used in the second time can be the same as the time unit represented by the first time, or it can be a different time unit than the time unit used in the first time.

[0160] In this embodiment of the disclosure, the processing time of the AI ​​task, which is sent to the second communication device communicating with the first communication device, is based on a first time representation. This includes sending the first time in the following form: absolute time, communication time unit, and AI time unit.

[0161] In this embodiment of the disclosure, the first communication device can be a terminal, and the second communication device can be a network device such as a base station. Alternatively, the first communication device can be a network device such as a base station, and the second communication device can be a terminal.

[0162] For example, taking the first communication device as the terminal and the second communication device as the base station, the terminal sends the AI ​​task processing time, expressed in absolute time, to the base station. For example, the processing time is sent as 'a' milliseconds. The base station determines that the processing time represented in the communication time unit is 1 slot based on 'a' milliseconds.

[0163] Furthermore, if the terminal sends the AI ​​task processing time in communication time units to the base station, the base station directly uses the received AI task processing time in communication time units as the communication time, without needing to perform any other conversion processing. For example, if the processing time is sent as one OFDM symbol, then the communication time determined by the base station is one OFDM symbol.

[0164] Furthermore, if the terminal sends the AI ​​task processing time to the base station in the form of AI time units, for example, sending a processing time of 1 AI time unit, since the AI ​​time unit can be predefined based on a preset AI task (the specific predefinition steps have been described in detail in the above embodiments 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.

[0165] In step S22, a second time is obtained, which is determined by the second communication device based on the processing time represented by the first time.

[0166] In this embodiment of the disclosure, the second communication device determines the second time based on the first time sent by the first communication device.

[0167] In one embodiment of this disclosure, a second communication device sends a determined second time to a first communication device. 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 and second communication devices.

[0168] In step S23, AI communication processing of the AI ​​model is performed with the second communication device based on the second time.

[0169] In the AI ​​communication method provided in this embodiment, a first time representing the AI ​​task processing time is determined by a first communication device and sent to a second communication device. The second communication device determines a second time representing the AI ​​communication processing time based on the first time. The first and second communication devices align the second time.

[0170] For example, representing the second time as a communication time unit can make the AI ​​processing time more compatible with the communication system and reduce the complexity of subsequent communication processing.

[0171] In the AI ​​communication method provided in this embodiment, the second time for AI communication processing can also be determined by the first communication device.

[0172] like Figure 2c As shown, Figure 2c This is a flowchart illustrating yet another AI communication method according to an exemplary embodiment. Figure 2c In one embodiment shown, AI communication is performed based on the first moment, including the following steps:

[0173] In step S31, a second time is determined based on the processing time represented by the first time, where the second time represents the time of AI communication processing.

[0174] In this embodiment of the disclosure, the first communication device may determine the second time based on the processing time represented by the first time.

[0175] For example, the processing time represented by the first time and the related implementation scheme for the second time are the same as those in the above embodiments, and will not be repeated here. It should be noted that in the embodiments of this disclosure, the second time is determined by the first communication device.

[0176] In step S32, AI communication of the AI ​​model is performed based on the second time.

[0177] In the AI ​​communication method provided in this embodiment, a first communication device determines a first time representing the AI ​​task processing time, and determines a second time representing the AI ​​communication processing time based on the first time.

[0178] It is understood that the second time can be a time represented based on a communication time unit, or it can be represented based on other forms, and this disclosure does not limit it.

[0179] In one embodiment of the AI ​​communication method provided in this disclosure, the processing time of the AI ​​task based on the first time representation can 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.

[0180] In this embodiment of the disclosure, different first-time representation methods are selected for different AI communication processing contents based on AI models.

[0181] For example, when the communication processing content of an AI model is the activation of the AI ​​model, the corresponding processing time can be represented by either absolute time or by communication time units.

[0182] For example, when the communication processing content of an AI model is the switching of the AI ​​model, the corresponding processing time can be represented by either absolute time or by communication time units.

[0183] For example, when the communication processing content of an AI model is the inference of the AI ​​model, the corresponding processing time can be represented by an AI time unit.

[0184] In another embodiment of the AI ​​communication method provided in this disclosure, the processing time for processing AI tasks based on the first time representation can be a processing time selected from a set of processing times, which includes processing times based on the first time representation.

[0185] In this embodiment of the disclosure, the processing time set may include: an absolute time set, a communication time unit set, and an AI time unit set.

[0186] For example, the elements in the absolute time set are first times expressed in absolute time form, such as: 1 millisecond, 2 milliseconds, 3 milliseconds... a millisecond.

[0187] For example, the elements in the communication time unit set are the first time represented in the form of communication time units, such as: 1 slot, 2 slots, 3 slots... b slots.

[0188] For example, the elements in the AI ​​time unit set are the first time represented in the form of AI time units, such as: 1 AI time unit, 2 AI time units, 3 AI time units... N AI time units.

[0189] In this embodiment of the disclosure, different first-time representation methods are selected for different AI communication processing contents based on AI models.

[0190] For example, when the communication processing content of an AI model is the activation of the AI ​​model, the corresponding processing time set can be an absolute time set or a communication time unit set.

[0191] When the communication processing content of an 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.

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

[0193] In this embodiment of the disclosure, for the inference of AI models or AI functions, an inference time set can be predefined by a protocol. The inference time in the set is an element corresponding to the unit of absolute time. The first communication device can select the corresponding element from the preset time set for reporting.

[0194] In this embodiment of the disclosure, for the inference of AI models or AI functions, an inference time set can be predefined by the protocol. The inference time in the set is an element of the unit corresponding to the communication time unit. The first communication device can select the corresponding element from the preset time set for reporting.

[0195] In this embodiment of the disclosure, when selecting a processing time from the set of processing times, the selection is based on the processing capability of the first communication device. For example, the faster the AI ​​task processing time is due to the processing capability, the smaller the selected processing time value will be. Specifically, in the case where the first time includes an AI time unit, the value of the processing time selected from the set of processing times is based on the basic AI processing task (preset AI task) and the processing capability of the first communication device.

[0196] It is understood that the above embodiments provide a detailed description 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 function is activated or switched and uses communication time unit as the first time, or AI time unit as the first time, the corresponding embodiments are similar to the above embodiments, and will not be described in detail here.

[0197] It should be noted that those skilled in the art will understand that the various implementation methods / embodiments described above in this disclosure can be used in conjunction with the foregoing embodiments, or they can be used independently. Whether used alone or in conjunction with the foregoing embodiments, the implementation principle is similar. In this disclosure, some embodiments are described as implementations used together. Of course, those skilled in the art will understand that such illustrative examples are not intended to limit the embodiments of this disclosure.

[0198] Based on the same concept, this disclosure also provides an AI communication method.

[0199] Figure 3 This is a flowchart illustrating an AI communication method according to an exemplary embodiment, such as... Figure 3 As shown, the AI ​​communication method is executed by a second communication device, which can be a network device or a terminal device. The AI ​​communication method includes the following steps:

[0200] In step S41, a first time is received from the first communication device, which represents the processing time of the AI ​​task based on the AI ​​model.

[0201] In step S42, AI communication processing based on the AI ​​model is performed based on the first time.

[0202] In one implementation, the first time is represented based on at least one of the following: absolute time; communication time unit; AI time unit, wherein the AI ​​time unit is determined based on a preset AI task.

[0203] In one embodiment of this disclosure, AI communication processing based on an AI model includes at least one of the following:

[0204] AI model inference, AI model activation, and AI model switching.

[0205] It should be further noted that the AI ​​communication processing based on AI models involved in the following embodiments of this disclosure includes one or more of the following: AI model inference, AI model activation, and AI model switching.

[0206] In the AI ​​communication method provided in this embodiment, the AI ​​model inference time can be determined, the AI ​​model activation time can be determined, or the AI ​​model switching time can be determined.

[0207] In this embodiment, 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. This embodiment will not be repeated here.

[0208] In one implementation, the AI ​​time unit is the processing time for processing a preset AI task based on an AI model; or the AI ​​time unit includes computing resources for processing a preset AI task based on an AI model.

[0209] In one implementation, AI communication based on an AI model is performed based on a first-time event, including:

[0210] Receive the processing time of the AI ​​task from the first communication device communicating with the second communication device, based on a first time representation; determine a second time based on a communication time unit representation, the second time being determined by the processing time of the second communication device based on the first time representation; and perform AI communication processing of the AI ​​model with the first communication device based on the second time.

[0211] In one implementation, the processing time for processing an AI task based on a first-time representation includes at least one of the following:

[0212] The processing time corresponding to the AI ​​model supported by the first communication device is based on the first time representation; or the processing time is selected from a set of processing times, which includes processing times based on the first time representation.

[0213] In one implementation, AI communication is performed based on a first time, including: determining a second time based on the processing time represented by the first time, wherein the second time is a communication time represented by a communication time unit; and performing AI communication processing of the AI ​​model based on the second time.

[0214] In one implementation, AI communication processing based on an AI model includes at least one of the following: AI model inference, AI model activation, and AI model switching.

[0215] In one implementation, the AI ​​model includes at least one of an AI function and a model corresponding to the AI ​​function.

[0216] In one 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.

[0217] It is understood that the implementation process of the AI ​​communication method executed by the second communication device in this embodiment is similar to that of the AI ​​communication method executed by the first communication device. The similarities will not be repeated here, but can be found in the implementation process of the AI ​​communication method executed by the first communication device described above. For example, for the first time, relevant embodiments concerning the processing time involved in the terminal executing the AI ​​communication method can be referred to.

[0218] Based on the same concept, this disclosure also 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 the AI ​​communication method.

[0219] Figure 4 This is a schematic diagram illustrating a method interaction of an AI communication system according to an exemplary embodiment of this disclosure. Figure 4 As shown, this disclosure relates to an AI communication system, and the method includes:

[0220] Step S51: The first communication device determines the first time.

[0221] In one implementation, the first time is used to represent the processing time of AI tasks based on AI models.

[0222] In one implementation, the first time is based on at least one of the following representations: absolute time; communication time unit; AI time unit.

[0223] Furthermore, the AI ​​time unit is determined based on a preset AI task.

[0224] 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 resources for processing a preset AI task based on the AI ​​model.

[0225] Step S52: Perform AI communication processing based on the AI ​​model in real time.

[0226] In one implementation, AI communication includes:

[0227] Send the processing time of the AI ​​task based on the first time representation to the second communication device that communicates with the first communication device; obtain the second time based on the communication time unit representation, 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 second communication device based on the second time.

[0228] In one implementation, the processing time for processing an AI task based on a first-time representation includes at least one of the following:

[0229] The processing time corresponding to the AI ​​model supported by the first communication device is based on the first time representation; or the processing time is selected from a set of processing times, which includes processing times based on the first time representation.

[0230] In one embodiment, AI communication is performed based on the first time, including: determining a second time based on a communication time unit based on the processing time represented by the first time, wherein the second time is determined by the first communication device based on the processing time represented by the first time;

[0231] Based on the second time, AI communication processing of the AI ​​model is performed.

[0232] In one implementation, AI model-based AI communication processing includes at least one of the following: AI model inference, AI model activation, and AI model switching.

[0233] In one implementation, the AI ​​model includes at least one of an AI function and a model corresponding to the AI ​​function.

[0234] In this embodiment of the disclosure, in the interaction scenario between the first communication device and the second communication device, the first communication device can be a terminal or a network device, and the second communication device can be a network device or a terminal. The relevant information processing procedures of the second communication device in the interaction scenario are the same as or similar to those of the first communication device in the interaction scenario. Therefore, for the relevant information processing procedures of the second communication device in the interaction scenario, please refer to the relevant embodiments of the first communication device described above; these embodiments will not be repeated here.

[0235] Based on the same concept, this disclosure also provides an AI communication device.

[0236] Figure 5a This is a structural block diagram illustrating an AI communication device according to an exemplary embodiment. The AI ​​communication device is executed by a first communication device, which can be a terminal or a network device.

[0237] like Figure 5a As shown, this disclosure provides an AI communication device, including: a processing unit 501, configured to determine a first time, the first time representing the processing time of processing an AI task based on an AI model; and to perform AI communication processing based on the first time.

[0238] In one implementation, the first time is based on at least one of the following representations: absolute time; communication time unit; AI time unit, wherein the AI ​​time unit is determined based on a preset AI task.

[0239] In one embodiment, the AI ​​time unit includes processing time for processing a preset AI task based on an AI model; or the AI ​​time unit includes computing resources for processing a preset AI task based on an AI model.

[0240] In one 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 a first time to a second communication device that communicates with the first communication device. The receiving unit is used to acquire 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.

[0241] In one embodiment, the processing unit performs AI communication based on an AI model in the following manner based on a first time: a second time is determined based on the processing time represented by the first time, and the second time is the time for performing AI communication processing; AI communication processing of the AI ​​model is performed based on the second time.

[0242] In one implementation, the processing time for processing the AI ​​task, expressed as a first time, includes at least one of the following:

[0243] The processing time corresponding to the AI ​​model supported by the first communication device is based on the first time representation; or

[0244] The processing time selected from the processing time set, which includes processing times represented based on the first time.

[0245] In one implementation, AI communication processing based on an AI model includes at least one of the following:

[0246] AI model inference, AI model activation, and AI model switching.

[0247] In one implementation, the AI ​​model includes at least one of an AI function and a model corresponding to the AI ​​function.

[0248] In one 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.

[0249] Understandably, the second time refers to the communication processing time.

[0250] Furthermore, the time unit used in the second time can be the same as the time unit represented by the first time, or it can be a different time unit than the time unit used in the first time.

[0251] Based on the same concept, this disclosure also provides an AI communication device.

[0252] Figure 5b This is a structural block diagram illustrating an AI communication device according to an exemplary embodiment. The AI ​​communication device is executed by a second communication device, which can be a network device or a terminal.

[0253] like Figure 5b As shown in the figure, this disclosure provides an AI communication device, including:

[0254] The processing unit 502 is configured to receive a first time sent by the first communication device, the first time representing the processing time of processing an AI task based on an AI model; and to perform AI communication processing based on the first time.

[0255] In one implementation, the first time is represented based on at least one of the following: absolute time; communication time unit; AI time unit, wherein the AI ​​time unit is determined based on a preset AI task.

[0256] In one embodiment, the AI ​​time unit includes processing time for processing a preset AI task based on an AI model; or the AI ​​time unit includes computing resources for processing a preset AI task based on an AI model.

[0257] In one embodiment, the processing unit 502 determines a second time based on a first time (representing the processing time), where the second time is the time for performing AI communication processing. The AI ​​communication device further includes a sending unit that sends the second time to a 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.

[0258] In one embodiment, the processing unit 502 performs AI communication based on a first time in the following manner:

[0259] Based on the processing time represented by the first time, a second time is determined, which is the time for AI communication processing; based on the second time, AI communication processing of the AI ​​model is performed.

[0260] 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, the processing time being based on the first time representation; and the processing time selected from a set of processing times, the set of processing times including the processing time based on the first time representation.

[0261] In one implementation, AI communication processing based on an AI model includes at least one of the following: AI model inference, AI model activation, and AI model switching.

[0262] In one implementation, the AI ​​model includes at least one of an AI function and a model corresponding to the AI ​​function.

[0263] In one 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.

[0264] Regarding the apparatus in the above embodiments, the specific manner in which each module performs its operation has been described in detail in the embodiments related to the method, and will not be elaborated upon here.

[0265] Figure 6 This is a block diagram illustrating a communication device 600 according to an exemplary embodiment. For example, device 600 may be a mobile phone, computer, digital broadcasting terminal, messaging device, game console, tablet device, medical device, fitness equipment, personal digital assistant, etc.

[0266] Reference Figure 6 The device 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.

[0267] Processing component 602 typically controls the overall operation of device 600, such as operations associated with display, telephone calls, data communication, camera operation, and recording. Processing component 602 may include one or more processors 620 to execute instructions to perform all or part of the steps of the methods described above. Furthermore, processing component 602 may include one or more modules to facilitate interaction between processing component 602 and other components. For example, processing component 602 may include a multimedia module to facilitate interaction between multimedia component 608 and processing component 602.

[0268] Memory 604 is configured to store various types of data to support the operation of device 600. Examples of such data include instructions for any application or method operating on device 600, contact data, phonebook data, messages, pictures, videos, etc. 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 storage, flash memory, magnetic disk, or optical disk.

[0269] The power supply component 606 provides power to the various components of the device 600. The power supply component 606 may include a power management system, one or more power sources, and other components associated with generating, managing, and distributing power to the device 600.

[0270] 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 may be implemented as a touchscreen to receive input signals from the user. The touch panel includes one or more touch sensors to sense touches, swipes, and gestures on the touch panel. The touch sensors may sense not only the boundaries of the touch or swipe action but also the duration and pressure associated with the touch or swipe operation. In some embodiments, multimedia component 608 includes a front-facing camera and / or a rear-facing camera. When the device 600 is in an operating mode, such as a shooting mode or a video mode, the front-facing camera and / or the rear-facing camera may receive external multimedia data. Each front-facing camera and rear-facing camera may be a fixed optical lens system or have focal length and optical zoom capabilities.

[0271] Audio component 610 is configured to output and / or input audio signals. For example, audio component 610 includes a microphone (MIC) configured to receive external audio signals when device 600 is in an operating mode, such as call mode, recording mode, and voice recognition mode. The received audio signals may be further stored in memory 604 or transmitted via communication component 616. In some embodiments, audio component 610 also includes a speaker for outputting audio signals.

[0272] I / O interface 612 provides an interface between processing component 602 and peripheral interface modules, such as keyboards, click wheels, buttons, etc. These buttons may include, but are not limited to, home buttons, volume buttons, power buttons, and lock buttons.

[0273] Sensor assembly 614 includes one or more sensors for providing status assessments of various aspects of device 600. For example, sensor assembly 614 may detect the on / off state of device 600, the relative positioning of components such as the display and keypad of device 600, changes in the position of device 600 or a component of device 600, the presence or absence of user contact with device 600, the orientation or acceleration / deceleration of device 600, and temperature changes of device 600. Sensor assembly 614 may include a proximity sensor configured to detect the presence of nearby objects without any physical contact. Sensor assembly 614 may also include a light sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, sensor assembly 614 may also include an accelerometer, a gyroscope, a magnetometer, a pressure sensor, or a temperature sensor.

[0274] Communication component 616 is configured to facilitate wired or wireless communication between device 600 and other devices. Device 600 can access wireless networks based on communication standards, such as WiFi, 2G, or 3G, or combinations thereof. In one exemplary embodiment, communication component 616 receives broadcast signals or broadcast-related information from an external broadcast management system via a broadcast channel. In one exemplary embodiment, communication component 616 also includes a near-field communication (NFC) module to facilitate short-range communication. For example, the NFC module may be implemented based on radio frequency identification (RFID) technology, Infrared Data Association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology, and other technologies.

[0275] 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 methods described above.

[0276] 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 a processor 620 of the device 600 to perform the above-described method. For example, the non-transitory computer-readable storage medium may be a ROM, random access memory (RAM), CD-ROM, magnetic tape, floppy disk, and optical data storage device, etc.

[0277] Figure 7 This is a block diagram illustrating a communication apparatus 700 according to an exemplary embodiment. For example, apparatus 700 may be provided as a network device. (Refer to...) Figure 7The 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 application programs, that can be executed by the processing component 722. The application programs stored in memory 732 may include one or more modules, each corresponding to a set of instructions. Furthermore, the processing component 722 is configured to execute instructions to perform the methods described above.

[0278] Device 700 may also include a power supply component 726 configured to perform power management of device 700, a wired or wireless network interface 750 configured to connect device 700 to a network, and an input / output (I / O) interface 758. Device 700 may operate on an operating system stored in memory 732, such as Windows Server™, Mac OS X™, Unix™, Linux™, FreeBSD™, or similar.

[0279] 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 a processing component 722 of the apparatus 700 to perform the above-described method. For example, the non-transitory computer-readable storage medium may be a ROM, random access memory (RAM), CD-ROM, magnetic tape, floppy disk, and optical data storage device, etc.

[0280] This disclosure provides an artificial intelligence communication method, apparatus, and storage medium. In some embodiments, the terms "communication method" and "information processing method" can be used interchangeably, as can the terms "communication apparatus" and "information processing apparatus," and the terms "information processing system" and "communication system."

[0281] This disclosure is not exhaustive, but merely illustrative of some embodiments, and is not intended to limit the scope of protection of this disclosure. Unless otherwise specified, each step in a particular 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 particular embodiment can also be implemented as an independent embodiment, and the order of the steps in a particular embodiment can be arbitrarily interchanged. Furthermore, the optional implementation methods in a particular embodiment can be arbitrarily combined; moreover, the embodiments can be arbitrarily combined, for example, some or all steps of different embodiments can be arbitrarily combined, and a particular embodiment can be arbitrarily combined with the optional implementation methods of other embodiments.

[0282] In all embodiments disclosed herein, unless otherwise specified or logically conflicting, the terminology and / or descriptions are consistent across embodiments and can be referenced interchangeably. Technical features from different embodiments can be combined to form new embodiments based on their inherent logical relationships. The terminology used in the embodiments of this disclosure is for the purpose of describing specific embodiments only and is not intended to limit the scope of this disclosure.

[0283] It can be further understood that in this disclosure, "multiple" refers to two or more, and other quantifiers are similar. "And / or" describes the relationship between related objects, indicating that three relationships can exist; for example, A and / or B can represent: A alone, A and B simultaneously, and B alone. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. The singular forms "a," "the," and "the" are also intended to include the plural forms unless the context clearly indicates otherwise.

[0284] It is further understood that the meaning of words such as “in response to” and “if” used in this disclosure depends on the context and the actual usage scenario. For example, the word “in response to” as used herein can be interpreted as “when”, “when”, or “if”.

[0285] It is further understood that the terms "first," "second," etc., are used to describe various types of information, but this information should not be limited to these terms. These terms are only used to distinguish information of the same type from one another, and do not indicate a specific order or degree of importance. In fact, the expressions "first," "second," etc., are completely interchangeable. For example, without departing from the scope of this disclosure, first information can also be referred to as second information, and similarly, second information can also be referred to as first information.

[0286] It is further understood that although operations are described in a specific order in the accompanying drawings in the embodiments of this disclosure, this should not be construed as requiring these operations to be performed in the specific order or serial order shown, or requiring all of the shown operations to be performed to obtain the desired result. In certain environments, multitasking and parallel processing may be advantageous.

[0287] Other embodiments of this disclosure will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not disclosed herein.

[0288] It should be understood that this disclosure is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this disclosure is limited only by the appended claims.

Claims

1. An artificial intelligence (AI) communication method, characterized in that, Performed by a first communication device, the method includes: The first time is determined, which represents the processing time for processing AI tasks based on AI models; Based on the first time frame, AI communication processing based on the AI ​​model is performed; The AI ​​communication based on the AI ​​model includes: Based on the processing time represented by the first time, a second time is determined, which is the time for performing AI communication processing; Based on the second time, AI communication processing of the AI ​​model is performed.

2. The method according to claim 1, characterized in that, The first time is based on at least one of the following representations: Absolute time; Communication time unit; AI time units are determined based on preset AI tasks.

3. The method according to claim 2, characterized in that, 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 computing resources for processing preset AI tasks based on AI models.

4. The method according to claim 1, 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 is based on the first time representation; or The processing time selected from the set of processing times, which includes processing times represented based on the first time.

5. 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: AI model inference, AI model activation, and AI model switching.

6. 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.

7. An AI communication device, characterized in that, Performed by a first communication device, the apparatus includes: The processing unit is configured to determine a first time, which represents the processing time for processing AI tasks based on an AI model; and to determine a second time based on the processing time represented by the first time, which is the time for performing AI communication processing. Based on the second time, AI communication processing of the AI ​​model is performed.

8. The AI ​​communication device according to claim 7, characterized in that, The first time is based on at least one of the following representations: Absolute time; Communication time unit; AI time units are determined based on preset AI tasks.

9. An AI communication device, characterized in that, include: processor; Memory used to store processor-executable instructions; The processor is configured to execute the AI ​​communication method according to any one of claims 1 to 6.

10. A storage medium, characterized in that, The storage medium stores instructions that, when executed by the terminal's processor, enable the terminal to perform the AI ​​communication method according to any one of claims 1 to 6.

Images