Artificial intelligence communication method and apparatus, and storage medium

By deploying a one-sided AI model or AI function on the terminal side and using data sets for AI operations, the problem of selecting and switching of AI models or AI functions in wireless air interfaces is solved, and the efficiency and quality of AI communication is improved.

WO2024234257A1PCT designated stage expired Publication Date: 2024-11-21BEIJING XIAOMI MOBILE SOFTWARE CO LTD
View PDF 5 Cites 0 Cited by

Patent Information

Application Number
PCT/CN2023/094333
Authority / Receiving Office
WO · WO
Patent Type
Applications
Current Assignee / Owner
Filing Date
2023-05-15
Publication Date
2024-11-21

AI Technical Summary

Technical Problem

In wireless air ports, how the terminal can effectively select and switch suitable AI models or AI functions to improve AI communication efficiency, especially when application scenarios change, it is a challenge to determine the AI ​​model or AI functions that need to be activated.

Method used

By deploying a one-sided AI model or AI function on the terminal side, using the data set to perform AI operations, the results of AI operations are obtained to determine whether to perform activation, deactivate or switch operations, and ensure that the appropriate AI model or AI function is selected for communication processing.

Benefits of technology

It improves the communication efficiency and quality of AI communication, ensures that terminals or network devices can choose the correct AI model or AI functions to operate, and adapt to different application scenarios.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN2023094333_21112024_PF_FP_ABST
    Figure CN2023094333_21112024_PF_FP_ABST
Patent Text Reader

Abstract

The present disclosure relates to an AI communication method and apparatus, and a storage medium, which are used for improving the communication efficiency of AI communication. The method comprises: using a first AI model or a first AI function to perform an AI operation on the basis of a data set, so as to obtain an AI operation result, wherein the AI operation result is used for determining whether to perform a first operation on the first AI model or the first AI function; the first AI model is a unilateral model and is deployed on a terminal side; and an AI model corresponding to the first AI function is a unilateral model and is deployed on the terminal side.
Need to check novelty before this filing date? Find Prior Art

Description

Artificial intelligence communication method, device and storage medium Technical Field

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

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

[0003] Summary of the Invention

[0004] The present disclosure provides an artificial intelligence (AI) communication method, device, and storage medium.

[0005] According to a first aspect of an embodiment of the present disclosure, an AI communication method is provided, which is executed by a terminal. The method includes: using a first AI model or a first AI function to perform an AI operation based on a data set to obtain an AI operation result; the AI ​​operation result is used to determine whether to perform a first operation on the first AI model or the first AI function; the first AI model is a unilateral model and is deployed on the terminal side; the AI ​​model corresponding to the first AI function is a unilateral model and is deployed on the terminal side.

[0006] According to a second aspect of an embodiment of the present disclosure, an AI communication method is provided, which is executed by a network device. The method includes: determining whether a terminal performs a first operation on a first AI model or a first AI function; the first AI model is a unilateral model and is deployed on the terminal side; the AI ​​model corresponding to the first AI function is a unilateral model and is deployed on the terminal side.

[0007] According to a third aspect of an embodiment of the present disclosure, an AI communication device is provided, comprising: a processing module for performing an AI operation based on a data set using a first AI model or a first AI function to obtain an AI operation result; the AI ​​operation result is used to determine whether to perform a first operation on the first AI model or the first AI function; the first AI model is a unilateral model and is deployed on the terminal side; the AI ​​model corresponding to the first AI function is a unilateral model and is deployed on the terminal side.

[0008] According to a fourth aspect of an embodiment of the present disclosure, an AI communication device is provided, comprising: a processing module for determining whether a terminal performs a first operation on a first AI model or a first AI function; the first AI model is a unilateral model and is deployed on the terminal side; the AI ​​model corresponding to the first AI function is a unilateral model and is deployed on the terminal side.

[0009] According to a fifth aspect of an embodiment of the present disclosure, an AI communication device is provided, comprising: a processor; and a memory for storing processor-executable instructions; wherein the processor is configured to: execute the AI ​​communication method in the above-mentioned first aspect and its embodiments.

[0010] 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 in the above-mentioned second aspect and its embodiments.

[0011] 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 terminal, the terminal is enabled to execute the AI ​​communication method in the above-mentioned first aspect and its implementation methods.

[0012] 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 network device, the network device is enabled to execute the AI ​​communication method in the above-mentioned second aspect and its implementation methods.

[0013] The technical solution provided by the embodiments of the present disclosure may include the following beneficial effects: a terminal performs an AI operation based on a data set by using a first AI model or a first AI function to obtain an AI operation result, wherein the AI ​​operation result is used to determine whether to perform a first operation on the first AI model or the first AI function, thereby ensuring that the terminal or network device can select a suitable AI model or AI function to perform the first operation, thereby improving the communication efficiency of AI communication.

[0014] 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

[0015] 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.

[0016] Fig. 1 is a schematic diagram of a wireless communication system according to an exemplary embodiment.

[0017] Fig. 2 is a flowchart showing an AI communication method according to an exemplary embodiment.

[0018] Fig. 3 is a flowchart showing an AI communication method according to an exemplary embodiment.

[0019] Fig. 4 is a flowchart showing an AI communication method according to an exemplary embodiment.

[0020] Fig. 5 is a flowchart showing an AI communication method according to an exemplary embodiment.

[0021] Fig. 6 is a flowchart showing an AI communication method according to an exemplary embodiment.

[0022] Fig. 7 is a flowchart showing a communication method according to an exemplary embodiment.

[0023] Fig. 8 is a flowchart showing an AI communication method according to an exemplary embodiment.

[0024] Fig. 9 is a flowchart showing an AI communication method according to an exemplary embodiment.

[0025] Fig. 10 is a flowchart showing an AI communication method according to an exemplary embodiment.

[0026] FIG11 is a flowchart showing an AI communication method according to an exemplary embodiment.

[0027] Fig. 12 is a flowchart showing an AI communication method according to an exemplary embodiment.

[0028] Fig. 13 is a flowchart showing an AI communication method according to an exemplary embodiment.

[0029] Fig. 14 is a block diagram showing an AI communication device according to an exemplary embodiment.

[0030] FIG15 is a block diagram showing an AI communication device according to an exemplary embodiment.

[0031] FIG16 is a block diagram showing a device for AI communication according to an exemplary embodiment.

[0032] FIG17 is a block diagram showing a device for AI communication according to an exemplary embodiment. DETAILED DESCRIPTION

[0033] 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.

[0034] The AI ​​communication method provided in the embodiments 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 via wireless resources and performs data transmission.

[0035] 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.

[0036] 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.

[0037] Furthermore, the network devices involved in this disclosure may also be referred to as wireless access network devices. The wireless access network devices may be: base stations, evolved node Bs (base stations), home base stations, access points (APs) in wireless fidelity (WIFI) systems, wireless relay nodes, wireless backhaul nodes, transmission points (TPs), or transmission and reception points (TRPs), etc. They may also be gNBs in NR systems, or they may be components or parts of base stations. It should be understood that in the embodiments of this disclosure, the specific technologies and specific device forms used by the network devices are not limited. In this disclosure, the network devices can provide communication coverage for a specific geographical area and can communicate with terminals located within the coverage area (cell). In addition, when it comes to vehicle-to-everything (V2X) communication systems, the network devices may also be vehicle-mounted devices.

[0038] 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, pocket personal computers (PPCs), handheld computers, 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.

[0039] In recent years, artificial intelligence (AI) technology has achieved continuous breakthroughs in numerous fields. The continued development of fields such as intelligent voice and computer vision has not only brought a rich variety of applications to smart terminals, but has also found widespread application in education, transportation, home living, healthcare, retail, security, and other fields. This has brought convenience to people's lives while also promoting industrial upgrading across various industries. AI technology is also rapidly interpenetrating with other disciplines, integrating knowledge from different disciplines while also providing new directions and methods for their development.

[0040] In related technologies, a research project on AI technology in the radio access network (RAN) has been established to introduce artificial intelligence technology into the wireless air interface to assist in improving wireless air interface transmission technology. Furthermore, the application of AI technology in the wireless air interface for communication processing, including AI model training and model inference applications, is currently supported.

[0041] In AI model-based deployment solutions, AI models may be deployed on the terminal side, and multiple AI models can be deployed on the terminal side. Among them, an AI model may correspond to one or more AI functions, and an AI function may also correspond to one or more AI models.

[0042] The application scenarios of multiple AI models or multiple AI functions may be different. For example, some AI models or AI functions are applied in macro cells, and some AI models or AI functions are applied in micro cells. At this time, the network device will only instruct the terminal to activate one AI model or AI function, that is, the AI ​​model or AI function used by the terminal in the actual communication process.

[0043] Then, when the application scenario of the terminal changes, the terminal needs to switch the AI ​​model or AI function. At this time, how the terminal and network equipment determine the AI ​​model that needs to be activated is a problem that needs to be solved.

[0044] Based on this, an embodiment of the present disclosure proposes an AI communication method, in which the terminal performs an AI operation based on a data set using an AI model or AI function to obtain an AI operation result, wherein the AI ​​operation result is used to determine whether to perform a first operation on the AI ​​model or AI function, thereby ensuring that the terminal or network device can select a suitable AI model or AI function to perform the first operation, thereby improving the communication efficiency of AI communication.

[0045] FIG1 is a flow chart showing an AI communication method according to an exemplary embodiment. As shown in FIG1 , the AI ​​communication method is used in a terminal and includes the following steps.

[0046] In step S11 , an AI operation is performed based on a data set using a first AI model or a first AI function to obtain an AI operation result.

[0047] In some embodiments, the first AI model or the AI ​​model corresponding to the first AI function is a unilateral model and is deployed on the terminal side. In some embodiments, the first AI model is a unilateral model and is deployed on the terminal side.

[0048] In some embodiments, the first AI model or the first AI function is an AI-based beam prediction function.

[0049] In some embodiments, the AI ​​model corresponding to the first AI function is a unilateral model and is deployed on the terminal side.

[0050] In some embodiments, the terminal is deployed with one or more first AI models, or the terminal is deployed with one or more AI functions.

[0051] In some embodiments, the terminal uses each of all first AI models to perform an AI operation based on the data set.

[0052] In some embodiments, the terminal uses each of all first AI functions to perform an AI operation based on the data set.

[0053] In some embodiments, the terminal uses each of all first AI models to perform an AI operation based on the data set, and uses each of all first AI functions to perform an AI operation based on the data set.

[0054] In some embodiments, different first AI models or different first AI functions have different data sets, and the data sets for different first AI models or different first AI functions are determined based on AI use cases. It should be understood that the data included in the data set should be data that the terminal can use the first AI model or first AI function to perform AI operations and obtain AI operation results.

[0055] The data set is a data set used to test the first AI model or the first AI function.

[0056] For example, if the AI ​​use case is compression based on Channel State Information (CSI), the dataset may include some information about the measured channel. For another example, if the AI ​​use case is positioning, the dataset may include information used for positioning, such as radius and azimuth.

[0057] In some embodiments, one first AI model or one first AI function corresponds to one AI operation result, and different first AI models or different first AI functions may correspond to multiple different AI operation results.

[0058] Exemplarily, if the first AI function is an AI-based beam prediction, the AI ​​operation result is the predicted optimal beam or the channel measurement result corresponding to the optimal beam. In another exemplary embodiment, if the first AI function is an AI-based positioning function, the AI ​​operation result can be positioning accuracy.

[0059] In some embodiments, the AI ​​operation result is used to determine whether the terminal performs a first operation on the first AI model or the first AI function.

[0060] In an embodiment of the present disclosure, a terminal performs an AI operation based on a data set by using a first AI model or a first AI function to obtain an AI operation result, wherein the AI ​​operation result is used to determine whether to perform a first operation on the first AI model or the first AI function, thereby ensuring that the terminal or network device can select a suitable AI model or AI function to perform the first operation, thereby improving the communication efficiency of AI communication.

[0061] In an AI communication method provided in an embodiment of the present disclosure, the first operation includes at least one of the following:

[0062] Activate the operation;

[0063] Deactivation operation;

[0064] Switching AI models or AI functions.

[0065] In some embodiments, the first operation includes an activation operation, wherein the activation operation indicates activating an AI model or an AI function, and the terminal uses the activated AI model or AI function to perform AI communication.

[0066] Exemplarily, if the terminal performs AI communication based on AI model 1, when AI model 2 performs an activation operation, the terminal performs AI communication based on AI model 2.

[0067] In some embodiments, the first operation includes a deactivation operation, wherein the deactivation operation deactivates an AI model or AI function that is currently performing AI communication on the terminal, and the terminal is unable to use the deactivated AI model or AI function for AI communication.

[0068] Exemplarily, the terminal currently actually uses AI model 1 for AI communication. If the AI ​​model 1 performs a deactivation operation, the terminal no longer uses AI model 1 for AI communication.

[0069] In some embodiments, the first operation includes an AI model or AI function switching operation, wherein the switching operation represents switching the AI ​​function or AI model currently being used by the terminal for AI communication, and the terminal uses the switched AI model or AI function for AI communication.

[0070] Exemplarily, the terminal currently actually uses AI model 1 for AI communication. If AI model 2 performs a switching operation, the AI ​​model used by the terminal for communication is switched from AI model 1 to AI model 2.

[0071] In some embodiments, the first operation includes an activation operation and a switching operation.

[0072] Exemplarily, the AI ​​model currently used by the terminal for AI communication is AI model 1. If AI model 2 performs a switching operation and an activation operation, the terminal switches from AI model 1 to AI model 2 for AI communication.

[0073] In some embodiments, the terminal uses a first AI model or a first AI function to perform a first operation based on a data set, and determines an AI operation result, which is used to determine whether to activate, deactivate, or switch the first AI model or the first AI function.

[0074] For example, if the first AI model or the first AI function is currently in an activated state, the AI ​​operation result may be used to determine whether to perform a deactivation operation and / or a switching operation on the first AI model or the first AI function.

[0075] For another example, if the first AI model or the first AI function is currently in an inactive state, the AI ​​operation result may be used to determine whether to perform an activation operation and / or a switching operation on the first AI model or the first AI function.

[0076] In the embodiment of the present disclosure, by performing a first operation on a first AI model or a first AI function, the terminal can determine the AI ​​model or AI function for AI communication, thereby improving the efficiency of AI communication.

[0077] In an AI communication method provided by an embodiment of the present disclosure, whether to perform a first operation on a first AI model or a first AI function is determined based on an AI operation result.

[0078] In one implementation, the terminal determines whether to perform the first operation on the first AI model or the first AI function based on the AI ​​operation result.

[0079] In another implementation, the terminal reports the AI ​​operation result to the network device, and the network device determines whether to perform the first operation on the first AI model or the first AI function based on the AI ​​operation result.

[0080] In some embodiments, the terminal or network device determines whether to perform a first operation on the first AI model or the first AI function based on the AI ​​operation result and the output result of the AI ​​model currently running on the terminal.

[0081] Exemplarily, if the AI ​​operation result indicates that the communication quality of the first AI model or the first AI function is higher than the communication quality of the AI ​​model or AI function currently allowed by the terminal, it is determined to perform the first operation on the first AI model or the first AI function.

[0082] In an embodiment of the present disclosure, whether to perform the first operation on the first AI model or the first AI function is determined based on the AI ​​operation result, so that the terminal or network device determines the correct first AI model or first AI function to perform the first operation, thereby improving the quality of AI communication.

[0083] In an AI communication method provided by an embodiment of the present disclosure, whether to perform a first operation on a first AI model or a first AI function is determined based on a first result.

[0084] In some embodiments, the first result includes whether the AI ​​operation result satisfies the first condition.

[0085] In some embodiments, the first condition is determined based on an AI use case corresponding to the first AI model or the first AI function.

[0086] For example, if the AI ​​use case is positioning, the first condition may be a preset positioning accuracy threshold. For another example, if the AI ​​use case is beam prediction, the first condition may be a preset beam quality threshold.

[0087] In some embodiments, the first conditions corresponding to AI operation results of different AI models or different AI functions are different.

[0088] In some embodiments, whether to perform the first operation on the first AI model or the first AI function is determined based on the first result, that is, based on whether the AI ​​operation result satisfies the first condition.

[0089] In one implementation, if the first result indicates that the AI ​​operation result of the first AI model or the first AI function meets the first condition, a first operation is performed on the first AI model or the first AI function.

[0090] In another embodiment, if the first result indicates that the AI ​​operation result of the first AI model or the first AI function does not meet the first condition, the first operation is performed on the first AI model or the first AI function. In some embodiments, the terminal determines whether to perform the first operation on the first AI model or the first AI function based on the AI ​​operation result and the first condition.

[0091] In one implementation, the first condition may be configured by the network device.

[0092] In other embodiments, the network device determines whether to perform the first operation on the first AI model or the first AI function based on the AI ​​operation result and the first condition.

[0093] In the implementation of the present disclosure, whether to perform the first operation on the first AI model or the first AI function is determined based on the AI ​​operation result and the first condition, so that the terminal or network device determines the correct first AI model or first AI function to perform the first operation, thereby improving the quality of AI communication.

[0094] In an AI communication method provided by an embodiment of the present disclosure, a network device determines whether a terminal performs a first operation on a first AI model or a first AI function.

[0095] FIG3 is a flow chart of an AI communication method according to an exemplary embodiment. As shown in FIG3 , the method includes the following steps:

[0096] In step S21 , the AI ​​operation result or the first result is sent to the network device.

[0097] In some embodiments, the network device determines whether to perform a first operation on the first AI model or the first AI function based on the AI ​​operation result.

[0098] In one implementation, the network device determines whether to perform a first operation on the first AI model or the first AI function based on the AI ​​operation result and the output result of the AI ​​model currently running on the terminal.

[0099] In some embodiments, the network device determines whether to perform a first operation on the first AI model or the first AI function based on the first result.

[0100] Exemplarily, the network device determines that the first condition is met based on the AI ​​operation result, and then determines that the terminal needs to perform a first operation on the first AI model or the first AI function.

[0101] It is worth noting that step S21 can be implemented independently, and the terminal sends the AI ​​operation result or the first result to the network device. As for how the terminal determines the AI ​​operation result or the first result, there is no limitation. Step S21 and step S11 can also be implemented in combination, and the terminal performs an AI operation based on the data set using the first AI model or the first AI function to obtain the AI ​​operation result or the first result, and further sends the AI ​​operation result or the first result to the terminal. This is not limited in the present embodiment.

[0102] In an embodiment of the present disclosure, the terminal sends an AI operation result or a first result to a network device, and the network device determines whether the terminal performs a first operation on a first AI model or a first AI function based on the AI ​​operation result or the first result, thereby enabling the terminal or the network device to determine the correct first AI model or first AI function to perform the first operation, thereby improving the quality of AI communication.

[0103] FIG4 is a flow chart of an AI communication method according to an exemplary embodiment. As shown in FIG4 , the method includes the following steps:

[0104] In step S31 , in response to the terminal determining to perform a first operation on the first AI model or the first AI function based on the AI ​​operation result or the first result, first information is sent to the network device.

[0105] In some embodiments, the first information is used to request the network device to instruct the terminal to perform a first operation on the first AI model or the first AI function.

[0106] In some embodiments, in response to the terminal determining to perform a first operation on the first AI model or the first AI function based on the AI ​​operation result, the first information is sent to the network device.

[0107] For example, the terminal determines whether to perform a first operation on a first AI model or a first AI function based on the AI ​​operation result and the operation result of the AI ​​model or AI function currently running on the terminal.

[0108] In some embodiments, in response to the terminal determining to perform a first operation on the first AI model or the first AI function based on the first result, first information is sent to the network device.

[0109] For example, the terminal determines that the AI ​​operation result of the first AI model or the first AI function meets the first condition, and determines to perform the first operation on the first AI model or the first AI function, then sends first information to the network device, requesting the network device to instruct the terminal to perform the first operation on the first AI model or the first AI function.

[0110] It is worth noting that step S31 can be implemented independently. The terminal determines to perform a first operation on the first AI model or the first AI function based on the AI ​​operation result or the first result, and sends a first message to the network device, requesting the network device to instruct the terminal to perform the first operation. As for how the terminal determines the AI ​​operation result or the first result, there is no limitation. Step S31 and step S11 can also be implemented in combination. The terminal performs an AI operation based on a data set using the first AI model or the first AI function to obtain the AI ​​operation result or the first result. Based on the AI ​​operation result or the first result, the terminal determines whether to perform the first operation on the first AI model or the first AI function. When it is determined to perform the first operation on the first AI model or the first AI function, the terminal sends a first message to the network device, requesting the network device to instruct the terminal to perform the first operation on the first AI model or the first AI function. The embodiments of the present disclosure are not limited thereto.

[0111] In an embodiment of the present disclosure, after the terminal determines to perform a first operation on the first AI model or the first AI function, the network device instructs the terminal to perform the first operation on the first AI model or the first AI function, so that the terminal or the network device determines the correct first AI model or first AI function to perform the first operation, thereby improving the quality of AI communication.

[0112] FIG5 is a flow chart of an AI communication method according to an exemplary embodiment. As shown in FIG5 , the method includes the following steps:

[0113] In step S41, second information sent by the network device is received.

[0114] In some embodiments, the second information is used to instruct the terminal to perform a first operation on the first AI model or the first AI function.

[0115] In some embodiments, step S41 can be implemented separately, where the terminal receives second information sent by the network device and determines to perform a first operation on the first AI model or the first AI function based on the second information.

[0116] Exemplarily, the second information is an activation instruction or a deactivation instruction.

[0117] In some implementations, step S41 may be implemented in combination with any of the above implementations. For example, the terminal uses the first AI model or the first AI function to perform an AI operation based on the data set to obtain an AI operation result. The terminal sends the AI ​​operation result to the network device, and the network device determines whether to send the second information based on whether the AI ​​operation result meets the first condition. If the network device determines to send the second information, the terminal determines to perform the first operation on the first AI model or the first AI function based on the second information.

[0118] In an embodiment of the present disclosure, by receiving the second information sent by the network device, the terminal can determine to perform a first operation on the first AI model or the first AI function, thereby improving the quality of AI communication.

[0119] In an AI communication method provided by an embodiment of the present disclosure, a terminal determines whether to perform a first operation on a first AI model or a first AI function.

[0120] In some embodiments, the terminal determines whether to perform a first operation on the first AI model or the first AI function based on the AI ​​operation result.

[0121] For example, the terminal determines whether to perform a first operation on a first AI model or a first AI function based on the AI ​​operation result and the operation result of the AI ​​model or AI function currently running on the terminal.

[0122] In some embodiments, the terminal determines whether to perform a first operation on the first AI model or the first AI function based on the first result.

[0123] In one embodiment, in response to the first result indicating that the AI ​​operation result meets the first condition, a first operation is performed on the first AI model or the first AI function.

[0124] In another embodiment, in response to the first result indicating that the AI ​​operation result does not meet the first condition, the first operation is not performed on the first AI model or the first AI function.

[0125] In the embodiment of the present disclosure, the terminal itself determines whether to perform the first operation on the first AI model or the first AI function, so that the terminal can accurately perform the first operation on the first AI model or the first AI function, thereby improving the quality of AI communication.

[0126] FIG6 is a flow chart of an AI communication method according to an exemplary embodiment. As shown in FIG6 , the method includes the following steps:

[0127] In step S51, third information is sent to the network device.

[0128] In some embodiments, the third information is used to instruct the terminal to determine to perform a first operation on the first AI model or the first AI function.

[0129] Exemplarily, the third information is an activation confirmation or a deactivation confirmation.

[0130] In some embodiments, in response to the terminal determining to perform a first operation on the first AI model or the first AI function based on the AI ​​operation result or the first result, third information is sent to the network device, and the network device decides whether the terminal performs the first operation on the first AI model or the first AI function.

[0131] For example, the terminal determines to perform a first operation on a first AI model or a first AI function, but because the terminal's computing power resources do not support the terminal's first operation on the first AI model or the first AI function, the network device can issue an indication message to instruct the terminal that the first operation cannot be performed on the first AI model or the first AI function, even if the terminal determines to perform the first operation on the first AI model or the first AI function.

[0132] In the implementation of the present disclosure, when the terminal determines to perform the first operation on the first AI model or the first AI function, it sends third information to the network device, and the network device determines whether the terminal can perform the first operation on the first AI model or the first AI function, thereby enabling the terminal to accurately determine whether the first AI model or the first AI function can perform the first operation, thereby improving the quality of AI communication.

[0133] FIG7 is a flow chart of an AI communication method according to an exemplary embodiment. As shown in FIG7 , the method includes the following steps:

[0134] In step S61, fourth information sent by the network device is received.

[0135] In some embodiments, the fourth information is used to instruct the terminal to perform an AI operation based on the data set using the first AI model or the first AI function.

[0136] In which, exemplarily, the fourth information is an AI operation instruction.

[0137] It is worth noting that step S61 can be implemented alone or in combination with any embodiment of the present disclosure, and the embodiment of the present disclosure is not limited thereto.

[0138] In an embodiment of the present disclosure, the terminal determines, based on the fourth information sent by the network device, to use the first AI model or the first AI function to perform an AI operation based on the data set to obtain an AI operation result, thereby enabling the terminal to accurately determine whether to perform the first operation on the first AI model or the first AI function based on the AI ​​operation result, thereby improving the quality of AI communication.

[0139] In an AI communication method provided by an embodiment of the present disclosure, a data set is collected in a cell to which a terminal belongs; or the data set is a data set with a distribution similar to that of data in the cell to which the terminal belongs.

[0140] For example, for AI use cases based on AI beam prediction, corresponding AI models A and AI models B are set for macro cells and micro cells respectively. When the terminal enters a cell, it can obtain the corresponding data set of the cell and use AI model A and AI model B to perform corresponding AI operations respectively. The results of the AI ​​operation can be used to determine whether AI model A or AI model B is to be used in the cell.

[0141] In an AI communication method provided by an embodiment of the present disclosure, a data set is sent by a network device to a terminal based on a request from the terminal to the network device; or the data set is obtained by the terminal based on a broadcast from the network device.

[0142] In which, exemplarily, the fourth information is an AI operation instruction.

[0143] In an embodiment of the present disclosure, the terminal obtains a data set so that the terminal can use an AI model or AI function to perform AI operations based on the data set, thereby improving the quality of AI communication.

[0144] Based on the same concept, an embodiment of the present disclosure also provides an AI communication method performed by a network device.

[0145] FIG8 is a flowchart showing an AI communication method according to an exemplary embodiment. As shown in FIG8 , the AI ​​communication method is used in a network device and includes the following steps.

[0146] In step S71 , it is determined whether the terminal performs a first operation on a first AI model or a first AI function.

[0147] In some embodiments, the first AI model is a unilateral model and is deployed on the terminal side.

[0148] In some embodiments, the AI ​​model corresponding to the first AI function is a unilateral model and is deployed on the terminal side.

[0149] In an embodiment of the present disclosure, the network device determines whether the terminal performs a first operation on a first AI model or a first AI function, so that the terminal can perform the first operation on an appropriate AI model or AI function, thereby improving the communication efficiency of AI communication.

[0150] In an AI communication method provided in an embodiment of the present disclosure, the first operation includes at least one of the following:

[0151] Activate the operation;

[0152] Deactivation operation;

[0153] Switching AI models or AI functions.

[0154] The specific implementation method of the first operation can refer to the relevant implementation method of the first operation on the terminal side, and will not be explained here in the embodiment of the present disclosure.

[0155] In an AI communication method provided by an embodiment of the present disclosure, whether a terminal performs a first operation on a first AI model or a first AI function is determined based on an AI operation result.

[0156] In some embodiments, the AI ​​operation result is obtained by the terminal performing an AI operation based on a data set using a first AI model or a first AI function.

[0157] In some embodiments, different first AI models or different first AI functions have different data sets, and the data sets for different first AI models or different first AI functions are determined based on AI use cases. It should be understood that the data included in the data set should be data that the terminal can use the first AI model or first AI function to perform AI operations and obtain AI operation results.

[0158] For example, if the AI ​​use case is compression based on Channel State Information (CSI), the dataset may include some information about the measured channel. For another example, if the AI ​​use case is positioning, the dataset may include information used for positioning, such as radius and azimuth.

[0159] In some embodiments, one first AI model or one first AI function corresponds to one AI operation result, and different first AI models or different first AI functions may correspond to multiple different AI operation results.

[0160] Exemplarily, if the first AI function is an AI-based beam prediction, the AI ​​operation result is the predicted optimal beam or the channel measurement result corresponding to the optimal beam. In another exemplary embodiment, if the first AI function is an AI-based positioning function, the AI ​​operation result can be positioning accuracy.

[0161] In some embodiments, the terminal determines whether to perform the first operation on the first AI model or the first AI function based on the AI ​​operation result.

[0162] In some embodiments, the network device receives the AI ​​operation result sent by the terminal, and determines whether to perform the first operation on the first AI model or the first AI function based on the AI ​​operation result.

[0163] In some embodiments, the terminal or network device determines whether to perform a first operation on the first AI model or the first AI function based on the AI ​​operation result and the output result of the AI ​​model currently running on the terminal.

[0164] Exemplarily, if the AI ​​operation result indicates that the communication quality of the first AI model or the first AI function is higher than the communication quality of the AI ​​model or AI function currently allowed by the terminal, it is determined to perform the first operation on the first AI model or the first AI function.

[0165] In an embodiment of the present disclosure, whether to perform the first operation on the first AI model or the first AI function is determined based on the AI ​​operation result, so that the terminal or network device determines the correct first AI model or first AI function to perform the first operation, thereby improving the quality of AI communication.

[0166] In an AI communication method provided by an embodiment of the present disclosure, whether a terminal performs a first operation on a first AI model or a first AI function is determined based on a first result.

[0167] In some embodiments, the first result includes whether the AI ​​operation result satisfies the first condition.

[0168] In some embodiments, the first condition is determined based on an AI use case corresponding to the first AI model or the first AI function.

[0169] For example, if the AI ​​use case is positioning, the first condition may be a preset positioning accuracy threshold. For another example, if the AI ​​use case is beam prediction, the first condition may be a preset beam quality threshold.

[0170] In some embodiments, the first conditions corresponding to AI operation results of different AI models or different AI functions are different.

[0171] In some embodiments, whether to perform the first operation on the first AI model or the first AI function is determined based on the first result, that is, based on whether the AI ​​operation result satisfies the first condition.

[0172] In one implementation, if the first result indicates that the AI ​​operation result of the first AI model or the first AI function meets the first condition, a first operation is performed on the first AI model or the first AI function.

[0173] In another embodiment, if the first result indicates that the AI ​​operation result of the first AI model or the first AI function does not meet the first condition, a first operation is performed on the first AI model or the first AI function.

[0174] In some embodiments, the terminal determines whether to perform the first operation on the first AI model or the first AI function based on the AI ​​operation result and the first condition.

[0175] In one implementation, the first condition may be configured by the network device.

[0176] In other embodiments, the network device determines whether to perform the first operation on the first AI model or the first AI function based on the AI ​​operation result and the first condition.

[0177] In the implementation of the present disclosure, whether to perform the first operation on the first AI model or the first AI function is determined based on the AI ​​operation result and the first condition, so that the terminal or network device determines the correct first AI model or first AI function to perform the first operation, thereby improving the quality of AI communication.

[0178] FIG9 is a flow chart of an AI communication method according to an exemplary embodiment. As shown in FIG9 , the method includes the following steps:

[0179] In step S81 , an AI operation result or a first result is received.

[0180] The specific implementation of step S81 can refer to the specific implementation involved in step S21, and will not be further explained in this embodiment of the present disclosure.

[0181] In step S82 , it is determined whether the terminal performs a first operation on the first AI model or the first AI function based on the AI ​​operation result or the first result.

[0182] In some embodiments, the network device determines whether to perform a first operation on the first AI model or the first AI function based on the AI ​​operation result.

[0183] In one implementation, the network device determines whether to perform a first operation on the first AI model or the first AI function based on the AI ​​operation result and the output result of the AI ​​model currently running on the terminal.

[0184] In some embodiments, the network device determines, based on the first result, that the AI ​​operation result satisfies a first condition, and determines that the terminal performs a first operation on the first AI model or the first AI function.

[0185] In some embodiments, the network device determines, based on the first result, that the AI ​​operation result does not meet the first condition, and determines that the terminal does not perform the first operation on the first AI model or the first AI function.

[0186] In an embodiment of the present disclosure, a network device receives an AI operation result or a first result, and determines by the network device whether a terminal performs a first operation on a first AI model or a first AI function based on the AI ​​operation result or the first result, thereby enabling the terminal or the network device to determine the correct first AI model or first AI function to perform the first operation, thereby improving the quality of AI communication.

[0187] FIG10 is a flow chart of an AI communication method according to an exemplary embodiment. As shown in FIG10 , the method includes the following steps:

[0188] In step S91, first information is received.

[0189] In some embodiments, the first information is used to request the network device to instruct the terminal to perform a first operation on the first AI model or the first AI function.

[0190] Exemplarily, the first information is an activation request or a deactivation request.

[0191] In some embodiments, the terminal determines that the terminal performs a first operation on the first AI model or the first AI function based on the AI ​​operation result of the first AI model or the first AI function, and the terminal sends first information to the network device.

[0192] In some embodiments, the terminal determines that the AI ​​operation result meets the first condition based on the AI ​​operation result of the first AI model or the first AI function, the terminal determines to perform a first operation on the first AI model or the first AI function, and the terminal sends first information to the network device.

[0193] In an embodiment of the present disclosure, the network device instructs the terminal whether to perform the first operation on the first AI model or the first AI function based on the first information, so that the terminal or the network device determines the correct first AI model or first AI function to perform the first operation, thereby improving the quality of AI communication.

[0194] FIG11 is a flow chart of an AI communication method according to an exemplary embodiment. As shown in FIG11 , the method includes the following steps:

[0195] In step S1001, the second information is sent.

[0196] The specific implementation of step S1001 can refer to the specific implementation of step S41, and will not be further explained in this embodiment of the present disclosure.

[0197] FIG12 is a flow chart of an AI communication method according to an exemplary embodiment. As shown in FIG12 , the method includes the following steps:

[0198] In step S1101, third information is received.

[0199] In some embodiments, the third information is used to instruct the terminal to determine to perform a first operation on the first AI model or the first AI function.

[0200] In step S1102 , based on the third information, it is determined whether the terminal performs a first operation on the first AI model or the first AI function.

[0201] For example, the terminal determines to perform a first operation on a first AI model or a first AI function, but because the terminal's computing power resources do not support the terminal's first operation on the first AI model or the first AI function, the network device can issue an indication message to instruct the terminal that the first operation cannot be performed on the first AI model or the first AI function, even if the terminal determines to perform the first operation on the first AI model or the first AI function.

[0202] In the implementation of the present disclosure, when the terminal determines to perform the first operation on the first AI model or the first AI function, it sends third information to the network device, and the network device determines whether the terminal can perform the first operation on the first AI model or the first AI function, thereby enabling the terminal to accurately determine whether the first AI model or the first AI function can perform the first operation, thereby improving the quality of AI communication.

[0203] FIG13 is a flow chart of an AI communication method according to an exemplary embodiment. As shown in FIG13 , the method includes the following steps:

[0204] In step S1201, the fourth information is sent.

[0205] In some embodiments, the fourth information is used to instruct the terminal to perform an AI operation based on the data set using the first AI model or the first AI function.

[0206] It is worth noting that step S1201 can be implemented alone or in combination with any embodiment of the present disclosure, and the embodiment of the present disclosure is not limited thereto.

[0207] In an embodiment of the present disclosure, the network device sends the fourth information to enable the terminal to perform an AI operation based on a data set using the first AI model or the first AI function to obtain an AI operation result, so that the terminal can accurately determine whether to perform the first operation on the first AI model or the first AI function based on the AI ​​operation result, thereby improving the quality of AI communication.

[0208] In an AI communication method provided by an embodiment of the present disclosure, a data set is collected in a cell to which a terminal belongs; or the data set is a data set with a distribution similar to that of data in the cell to which the terminal belongs.

[0209] For example, for AI use cases based on AI beam prediction, corresponding AI models A and AI models B are set for macro cells and micro cells respectively. When the terminal enters a cell, it can obtain the corresponding data set of the cell and use AI model A and AI model B to perform corresponding AI operations respectively. The results of the AI ​​operation can be used to determine whether AI model A or AI model B is to be used in the cell.

[0210] In an AI communication method provided by an embodiment of the present disclosure, a data set is sent by a network device to a terminal based on a request from the terminal to the network device; or the data set is obtained by the terminal based on a broadcast from the network device.

[0211] In an embodiment of the present disclosure, the terminal obtains a data set so that the terminal can use an AI model or AI function to perform AI operations based on the data set, thereby improving the quality of AI communication.

[0212] 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.

[0213] Based on the same concept, an embodiment of the present disclosure also provides an AI communication device.

[0214] It is understandable that the AI ​​communication device provided in the embodiment of the present disclosure includes hardware structures and / or software modules corresponding to the execution of each function in order to realize the above functions. In combination with the units and algorithm steps of the various examples disclosed in the embodiment of the present disclosure, the embodiment of the present disclosure can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the technical solution of the embodiment of the present disclosure.

[0215] FIG14 is a block diagram of an AI communication device according to an exemplary embodiment. Referring to FIG14 , the device includes a processing module 101 .

[0216] Processing module 101 is configured to perform an AI operation based on a data set using a first AI model or a first AI function to obtain an AI operation result; the AI ​​operation result is used to determine whether to perform a first operation on the first AI model or the first AI function; the first AI model is a unilateral model and is deployed on the terminal side; the AI ​​model corresponding to the first AI function is also a unilateral model and is deployed on the terminal side.

[0217] In one embodiment, whether to perform the first operation on the first AI model or the first AI function is determined based on a first result, wherein the first result includes whether the AI ​​operation result satisfies a first condition.

[0218] In one embodiment, the apparatus further includes a sending module 102. The sending module 102 is configured to send the AI ​​operation result to a network device, and the network device determines whether to perform a first operation on the first AI model or the first AI function based on the AI ​​operation result or the first result.

[0219] In one embodiment, the sending module 102 is used to send first information to the network device in response to the terminal determining to perform a first operation on the first AI model or the first AI function based on the AI ​​operation result or the first result; the first information is used to request the network device to instruct the terminal to perform the first operation on the first AI model or the first AI function.

[0220] In one embodiment, the apparatus further includes a receiving module 103. The receiving module 103 is configured to receive second information sent by the network device, where the second information is configured to instruct the terminal to perform a first operation on the first AI model or the first AI function.

[0221] In this embodiment, the processing module 101 is used to determine whether to perform a first operation on the first AI model or the first AI function based on the AI ​​operation result or the first result.

[0222] In one embodiment, the processing module 101 is configured to determine, in response to the AI ​​operation result satisfying the first condition, to perform a first operation on the first AI model or the first AI function; or, in response to the AI ​​operation result not satisfying the first condition, to determine not to perform the first operation on the first AI model or the first AI function.

[0223] In one implementation, the sending module 102 is configured to send third information to the network device, where the third information is used to instruct the terminal to determine to perform a first operation on the first AI model or the first AI function.

[0224] In one embodiment, the first operation includes at least one of the following: an activation operation; a deactivation operation; an AI model or AI function switching operation.

[0225] In one implementation, the receiving module 103 receives fourth information sent by the network device, where the fourth information is used to instruct the terminal to perform an AI operation based on a data set using the first AI model or the first AI function.

[0226] In one implementation, the data set is collected in a cell to which the terminal belongs; or the data set is a data set with a distribution similar to that of data in the cell to which the terminal belongs.

[0227] In one implementation, the data set is sent by the network device to the terminal based on a request from the terminal to the network device; or the data set is acquired by the terminal based on a broadcast from the network device.

[0228] FIG15 is a block diagram of an AI communication device according to an exemplary embodiment. Referring to FIG15 , the device includes a processing module 201 .

[0229] Processing module 201 is used to determine whether the terminal performs a first operation on a first AI model or a first AI function; the first AI model is a unilateral model and is deployed on the terminal side; the AI ​​model corresponding to the first AI function is a unilateral model and is deployed on the terminal side.

[0230] In one embodiment, whether the terminal performs a first operation on the first AI model or the first AI function is determined based on the AI ​​operation result or the first result, where the AI ​​operation result is obtained by the terminal performing an AI operation based on a data set using the first AI model or the first AI function, and the first result includes whether the AI ​​operation result satisfies the first condition.

[0231] In one embodiment, the apparatus further includes a receiving module 202. The receiving module 202 is configured to receive the AI ​​operation result or the first result; and determine whether the terminal performs a first operation on the first AI model or the first AI function based on the AI ​​operation result or the first result.

[0232] In one embodiment, the receiving module 202 is configured to receive first information, where the first information is used to request a network device to instruct the terminal to perform a first operation on the first AI model or the first AI function.

[0233] In one embodiment, the apparatus further includes a sending module 203. The sending module 203 is configured to send second information, where the second information is used to instruct the terminal to perform a first operation on the first AI model or the first AI function.

[0234] In one embodiment, the receiving module 202 is used to receive third information, where the third information is used to instruct the terminal to determine whether to perform a first operation on the first AI model or the first AI function; and based on the third information, determine whether the terminal performs the first operation on the first AI model or the first AI function.

[0235] In one embodiment, the first operation includes at least one of the following: an activation operation; a deactivation operation; an AI model or AI function switching operation.

[0236] In one implementation, the sending module 203 sends fourth information, where the fourth information is used to instruct the terminal to perform an AI operation based on a data set using the first AI model or the first AI function.

[0237] In one implementation, the data set is collected in a cell to which the terminal belongs; or the data set is a data set with a distribution similar to that of data in the cell to which the terminal belongs.

[0238] In one implementation, the data set is sent by the network device to the terminal based on a request from the terminal to the network device; or the data set is acquired by the terminal based on a broadcast from the network device.

[0239] 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.

[0240] Figure 16 is a block diagram of an AI communication device according to an exemplary embodiment. For example, the device 300 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.

[0241] 16 , apparatus 300 may include one or more of the following components: a processing component 302 , a memory 304 , a power component 306 , a multimedia component 308 , an audio component 310 , an input / output (I / O) interface 312 , a sensor component 314 , and a communication component 316 .

[0242] The processing component 302 generally controls the overall operation of the device 300, such as operations associated with display, phone calls, data communications, camera operation, and recording operations. The processing component 302 may include one or more processors 320 to execute instructions to perform all or part of the steps of the above-described method. In addition, the processing component 302 may include one or more modules to facilitate interaction between the processing component 302 and other components. For example, the processing component 302 may include a multimedia module to facilitate interaction between the multimedia component 308 and the processing component 302.

[0243] The memory 304 is configured to store various types of data to support operations on the device 300. Examples of such data include instructions for any application or method operating on the device 300, contact data, phone book data, messages, pictures, videos, etc. The memory 304 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.

[0244] The power component 306 provides power to the various components of the device 300. The power component 306 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power to the device 300.

[0245] The multimedia component 308 includes a screen that provides an output interface between the device 300 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 308 includes a front camera and / or a rear camera. When the device 300 is in an operating mode, such as a shooting mode or a video mode, the front camera and / or the rear camera can receive external multimedia data. Each front camera and rear camera can be a fixed optical lens system or have a focal length and optical zoom capability.

[0246] The audio component 310 is configured to output and / or input audio signals. For example, the audio component 310 includes a microphone (MIC) that is configured to receive external audio signals when the device 300 is in an operating mode, such as a call mode, a recording mode, and a voice recognition mode. The received audio signals may be further stored in the memory 304 or transmitted via the communication component 316. In some embodiments, the audio component 310 further includes a speaker for outputting audio signals.

[0247] I / O interface 312 provides an interface between processing component 302 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.

[0248] The sensor assembly 314 includes one or more sensors for providing various aspects of the status assessment of the device 300. For example, the sensor assembly 314 can detect the open / closed state of the device 300, the relative positioning of components, such as the display and keypad of the device 300. The sensor assembly 314 can also detect changes in the position of the device 300 or a component of the device 300, the presence or absence of user contact with the device 300, the orientation or acceleration / deceleration of the device 300, and temperature changes of the device 300. The sensor assembly 314 may include a proximity sensor configured to detect the presence of nearby objects without any physical contact. The sensor assembly 314 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 314 may also include an accelerometer, a gyroscope, a magnetic sensor, a pressure sensor, or a temperature sensor.

[0249] The communication component 316 is configured to facilitate wired or wireless communication between the device 300 and other devices. The device 300 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 316 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 316 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.

[0250] In an exemplary embodiment, the apparatus 300 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.

[0251] In an exemplary embodiment, a non-transitory computer-readable storage medium including instructions is also provided, such as a memory 304 including instructions, which can be executed by the processor 320 of the apparatus 300 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.

[0252] Figure 17 is a block diagram of an AI communication device according to an exemplary embodiment. For example, the device 400 can be provided as a network device. Referring to Figure 17, the device 400 includes a processing component 422, which further includes one or more processors, and a memory resource represented by a memory 432 for storing instructions that can be executed by the processing component 422, such as an application. The application stored in the memory 432 may include one or more modules, each of which corresponds to a set of instructions. In addition, the processing component 422 is configured to execute instructions to perform the above method.

[0253] The device 400 may also include a power supply component 426 configured to perform power management of the device 400, a wired or wireless network interface 450 configured to connect the device 400 to a network, and an input / output (I / O) interface 458. The device 400 may operate based on an operating system stored in the memory 432, such as Windows Server™, Mac OS X™, Unix™, Linux™, FreeBSD™, or the like.

[0254] In an exemplary embodiment, a non-transitory computer-readable storage medium including instructions is also provided, such as a memory 432 including instructions, which can be executed by the processing component 422 of the apparatus 400 to perform the above method. For example, the non-transitory computer-readable storage medium can be a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, etc.

[0255] 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.

[0256] 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.

[0257] 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.

[0258] 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.

[0259] It should be understood that the present disclosure is not limited to the exact structures described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the scope of the appended claims.

Claims

1. An artificial intelligence (AI) communication method, characterized in that: Executed by a terminal, the method includes: Perform an AI operation based on the data set using the first AI model or the first AI function to obtain an AI operation result; The AI ​​operation result is used to determine whether to perform a first operation on the first AI model or the first AI function; The first AI model is a unilateral model and is deployed on the terminal side; The AI ​​model corresponding to the first AI function is a unilateral model and is deployed on the terminal side.

2. The method according to claim 1, characterized in that Whether to perform a first operation on the first AI model or the first AI function is determined based on a first result; The first result includes whether the AI ​​operation result satisfies a first condition.

3. The method according to claim 1 or 2, characterized in that: The method further comprises: The AI ​​operation result is sent to a network device, and the network device determines whether to perform a first operation on the first AI model or the first AI function based on the AI ​​operation result or the first result.

4. The method according to claim 1 or 2, characterized in that: The method further comprises: In response to the terminal determining, based on the AI ​​operation result or the first result, to perform a first operation on the first AI model or the first AI function, sending first information to a network device; The first information is used to request the network device to instruct the terminal to perform a first operation on the first AI model or the first AI function.

5. The method according to claim 3 or 4, characterized in that: The method further comprises: Receive second information sent by the network device, where the second information is used to instruct the terminal to perform a first operation on the first AI model or the first AI function.

6. The method according to claim 1 or 2, characterized in that: The method further comprises: Based on the AI ​​operation result or the first result, it is determined whether to perform a first operation on the first AI model or the first AI function.

7. The method according to claim 6, characterized in that The determining, based on the first result, whether to perform a first operation on the first AI model or the first AI function includes: In response to the AI ​​operation result satisfying a first condition, determining to perform a first operation on the first AI model or the first AI function; or In response to the AI ​​operation result not satisfying a first condition, it is determined not to perform a first operation on the first AI model or the first AI function.

8. The method according to claim 6 or 7, characterized in that: In response to determining to perform a first operation on the first AI model or the first AI function, the method further includes: Sending third information to the network device, where the third information is used to instruct the terminal to determine to perform a first operation on the first AI model or the first AI function.

9. The method according to any one of claims 1 to 8, characterized in that The first operation includes at least one of the following: Activate the operation; Deactivate operation; AI model or AI function switching operation.

10. The method according to any one of claims 1 to 9, characterized in that The method further comprises: Receive fourth information sent by the network device, where the fourth information is used to instruct the terminal to use the first AI model or the first AI function to perform an AI operation based on a data set.

11. The method according to any one of claims 1 to 10, characterized in that The data set is collected in a cell to which the terminal belongs; or The data set is a data set with a distribution similar to that of data in a cell to which the terminal belongs.

12. The method according to any one of claims 1 to 11, characterized in that The data set is sent by the network device to the terminal based on a request from the terminal to the network device; or The data set is acquired by the terminal based on the broadcast of the network device.

13. An artificial intelligence (AI) communication method, characterized in that: Executed by a network device, the method includes: determining whether the terminal performs a first operation on the first AI model or the first AI function; The first AI model is a unilateral model and is deployed on the terminal side; The AI ​​model corresponding to the first AI function is a unilateral model and is deployed on the terminal side.

14. The method according to claim 13, characterized in that Whether the terminal performs a first operation on the first AI model or the first AI function is determined based on the AI ​​operation result or the first result, where the AI ​​operation result is obtained by the terminal performing an AI operation based on a data set using the first AI model or the first AI function, and the first result includes whether the AI ​​operation result satisfies a first condition.

15. The method according to claim 14, characterized in that The determining whether the terminal performs a first operation on the first AI model or the first AI function includes: Receiving the AI ​​operation result or the first result; Based on the AI ​​operation result or the first result, it is determined whether the terminal performs a first operation on the first AI model or the first AI function.

16. The method according to claim 14, characterized in that The determining whether the terminal performs a first operation on the first AI model or the first AI function includes: First information is received, where the first information is used to request a network device to instruct the terminal to perform a first operation on the first AI model or the first AI function.

17. The method according to claim 15 or 16, characterized in that The method further comprises: Send second information, where the second information is used to instruct the terminal to perform a first operation on the first AI model or the first AI function.

18. The method according to claim 14, characterized in that The determining whether the terminal performs a first operation on the first AI model or the first AI function includes: receiving third information, where the third information is used to instruct the terminal to determine to perform a first operation on the first AI model or the first AI function; Based on the third information, it is determined whether the terminal performs a first operation on a first AI model or a first AI function.

19. The method according to any one of claims 13 to 18, characterized in that The first operation includes at least one of the following: Activate the operation; Deactivate operation; AI model or AI function switching operation.

20. The method according to any one of claims 14 to 19, characterized in that The method further comprises: Send fourth information, where the fourth information is used to instruct the terminal to use the first AI model or the first AI function to perform an AI operation based on the data set.

21. The method according to any one of claims 13 to 20, characterized in that The data set is collected in a cell to which the terminal belongs; or The data set is a data set with a distribution similar to that of data in a cell to which the terminal belongs.

22. The method according to any one of claims 14 to 21, characterized in that The data set is sent by the network device to the terminal based on a request from the terminal to the network device; or The data set is acquired by the terminal based on the broadcast of the network device.

23. An artificial intelligence (AI) communication device, characterized in that: The device comprises: A processing module, configured to perform an AI operation based on a data set using a first AI model or a first AI function to obtain an AI operation result; The AI ​​operation result is used to determine whether to perform a first operation on the first AI model or the first AI function; The first AI model is a unilateral model and is deployed on the terminal side; The AI ​​model corresponding to the first AI function is a unilateral model and is deployed on the terminal side.

24. An artificial intelligence (AI) communication device, characterized in that: The device comprises: a processing module, configured to determine whether the terminal performs a first operation on a first AI model or a first AI function; The first AI model is a unilateral model and is deployed on the terminal side; The AI ​​model corresponding to the first AI function is a unilateral model and is deployed on the terminal side.

25. An artificial intelligence (AI) communication device, characterized in that: include: processor; a memory for storing processor-executable instructions; Wherein, the processor is configured to: execute the artificial intelligence AI communication method described in any one of claims 1 to 12.

26. An artificial intelligence (AI) communication device, characterized in that: include: processor; a memory for storing processor-executable instructions; Wherein, the processor is configured to: execute the artificial intelligence AI communication method described in any one of claims 13 to 22.

27. A storage medium, characterized in that: The storage medium stores instructions, and when the instructions in the storage medium are executed by the processor of the terminal, the terminal is enabled to execute the artificial intelligence AI communication method described in any one of claims 1 to 12.

28. 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 network device, the network device is enabled to execute the artificial intelligence AI communication method described in any one of claims 13 to 22.

Citation Information

Patent Citations

  • Cell reselection method, device and related equipment

    CN116017616A

  • Artificial intelligence communication method and device and storage medium

    CN116888937A

  • Machine learning model renewal

    WO2022161615A1

  • Model-based determination of feedback information concerning the channel state

    WO2022212253A1

  • Terminal, wireless communication method, and base station

    WO2023026413A1