Task processing method, communication device, and storage medium

Abstract

Embodiments of the present disclosure provide a task processing method, a communication device, and a storage medium. The task processing method executed by a UE may comprise: receiving first information sent by a second node, the first information being related to a terminal executing a first task, the first task being a task related to a first model, and the first model being an artificial intelligence (AI) model and / or a machine learning (ML) model.

Description

Task processing method, communication device, and storage medium TECHNICAL FIELD

[0001] The present disclosure relates to the technical field of communication, and in particular to a task processing method, a communication device, and a storage medium. BACKGROUND

[0002] With the development of information technology, Artificial Intelligence (AI) models and / or Machine Learning (ML) models emerge as the times require. After being trained, the AI models or ML models can complete corresponding functions.

[0003] SUMMARY

[0004] Embodiments of the present disclosure provide a task processing method, a communication device, and a storage medium.

[0005] According to a first aspect of embodiments of the present disclosure, a task processing method is provided, executed by a first node, and the method comprises: receiving first information sent by a second node, the first information being related to a terminal performing a first task; the first task being a task related to a first model; and the first model being an Artificial Intelligence (AI) model and / or a Machine Learning (ML) model.

[0006] According to a second aspect of embodiments of the present disclosure, a task processing method is provided, wherein,

[0007] The method is executed by a second node, and the method comprises:

[0008] sending first information to a first node; the first information being related to a terminal performing a first task; the first task being a task related to a first model; and the first model being an Artificial Intelligence (AI) model and / or a Machine Learning (ML) model.

[0009] According to a third aspect of embodiments of the present disclosure, a first node of a first cell is provided, and the first node comprises:

[0010] a sending module configured to send a first message to a User Equipment (UE); the first message comprising a first parameter, the first parameter being used by the UE to determine a second key for communicating with a second cell; the first parameter being protected by a first key; and the first key being a key used by the UE to communicate with the first cell.

[0011] According to a fourth aspect of embodiments of the present disclosure, a User Equipment (UE) is provided, and the UE comprises:

[0012] The receiving module is configured to receive a first message sent by a first node of a first cell, wherein the first message comprises a first parameter, the first parameter is used by the UE to determine a second key for communication with a second cell, and the first parameter is protected by a first key, and the first key is a key used by the UE to communicate with the first cell.

[0013] According to a fifth aspect of the embodiments of the present disclosure, a communication device is provided, and the communication device comprises one or more processors, wherein the processor is configured to invoke instructions to enable the communication device to perform the task processing method provided in any of the first aspect to the second aspect.

[0014] According to a sixth aspect of the embodiments of the present disclosure, a storage medium is provided, and the storage medium stores instructions, when the instructions are executed on a communication device, the instructions enable the communication device to perform the task processing method provided in any of the first aspect to the second aspect.

[0015] According to a seventh aspect of the embodiments of the present disclosure, a program product is provided, and the program product comprises a computer program, when the computer program is executed on a communication device, the computer program enables the communication device to implement the task processing method provided in any of the first aspect to the second aspect.

[0016] The technical means provided by the embodiments of the present disclosure is that the first node sends first information to the second node, the first information is related to the first task, so that the first node selects the terminal to participate in the execution of the first task, fully uses the computing resource and / or storage resource of the terminal, improves the effective utilization rate of the terminal resource, and the execution efficiency of the first task is higher with the help of the terminal resource.

[0017] It should be understood that the above general description and the following detailed description are only exemplary and explanatory, and cannot limit the embodiments of the present disclosure. BRIEF DESCRIPTION OF DRAWINGS

[0018] The drawings herein are incorporated into the specification and form a part of the specification, show embodiments consistent with the present disclosure, and together with the specification serve to explain the principles of the embodiments of the present disclosure.

[0019] FIG. 1 is a schematic diagram of an architecture of a communication system according to an exemplary embodiment;

[0020] FIG. 2 is a flow diagram of a task processing method according to an exemplary embodiment;

[0021] FIG. 3 is a flow diagram of a task processing method according to an exemplary embodiment;

[0022] FIG. 4 is a flow diagram of a task processing method according to an exemplary embodiment;

[0023] FIG. 5 is a flow diagram illustrating a task processing method according to an example embodiment;

[0024] FIG. 6A is a structural diagram illustrating a first node according to an example embodiment;

[0025] FIG. 6B is a structural diagram illustrating a second node according to an example embodiment;

[0026] FIG. 6C is a structural diagram illustrating a terminal according to an example embodiment;

[0027] FIG. 7A is a structural diagram illustrating a communication device according to an example embodiment;

[0028] FIG. 7B is a structural diagram illustrating a chip according to an example embodiment. DETAILED DESCRIPTION

[0029] Embodiments of the present disclosure provide a task processing method, a communication device, a communication system, and a storage medium.

[0030] The first aspect provides a task processing method, wherein the method is performed by a first node, and the method comprises: receiving first information sent by a second node, the first information being related to a terminal performing a first task; the first task being a task related to a first model; and the first model being an artificial intelligence (AI) model and / or a machine learning (ML) model.

[0031] Based on the above scheme, the first node sends first information to the second node, the first information being related to the first task, so that the first node can select a terminal to participate in the execution of the first task, fully use the computing power resources and / or storage resources of the terminal, improve the effective utilization rate of the resources of the terminal, and make the execution of the first task more efficient with the help of the resources of the terminal.

[0032] In some embodiments of the first aspect, the first information comprises at least one of: task information for executing the first task; first index information for indicating an ability index of the first model after training; second index information for indicating an index that an inference result of the first model needs to satisfy; model information for indicating the first model; and terminal information for the first node to determine a terminal capable of performing the first task.

[0033] Based on the above scheme, examples of the first information are given, and the implementation is not limited to the above examples.

[0034] In some embodiments of the first aspect, the task information comprises at least one of: a task identifier for identifying the first task; and a task time for indicating a start time and / or an end time of the first task.

[0035] The task information is carried in the first information, so that the terminal can know the parameters related to the execution of the first task according to the task information.

[0036] In some embodiments of the first aspect, the terminal information includes at least one of the following: capability information, used to indicate the terminal capability of the terminal performing the first task; terminal type, used to indicate the type of the terminal performing at least the first task; and terminal quantity, used to indicate the number of terminals performing the first task.

[0037] Based on the above scheme, the terminal information is carried in the first information, so that the first node can refer to the terminal performing the first task or select the terminal participating in the execution of the first task.

[0038] In some embodiments of the first aspect, the method further includes: sending second information to at least one first terminal according to the first information; and the second information is used to enable the at least one first terminal to perform the first task.

[0039] Based on the above scheme, the first node sends second information to at least one first terminal according to the first information, so that the first terminal can perform the first task according to the second information.

[0040] In some embodiments, the sending of the second information to the at least one terminal according to the first information includes: sending the second information to each of the at least one first terminal according to the first information; or sending the second information to a terminal group according to the first information; and the terminal group includes the at least one first terminal.

[0041] Based on the above scheme, the first node supports unicast of the second information to each of the first terminals, or groupcast of the second information to the terminal group, so that the sending mode of the second information is various, and can be flexibly selected in specific implementation.

[0042] In some embodiments of the first aspect, before the sending of the second information to the at least one first terminal, the method further includes: determining the first terminal from a second terminal according to third information related to the second terminal.

[0043] In some embodiments, the first node selects the first terminal according to the third information related to the second terminal. In specific implementation, the first node can also randomly select the first terminal, and is not limited to selecting the first terminal from the second terminal according to the third information related to the second terminal.

[0044] In an embodiment of the first aspect, the third information comprises at least one of: state information indicating a terminal state of the second terminal; capability information indicating a capability of the second terminal; willingness information indicating whether the second terminal is willing to participate in the execution of the first task; location information indicating a geographical location of the second terminal; channel information indicating a current channel state and / or an estimated channel state in a specified time period of the second terminal; mobility information indicating a mobility of the second terminal.

[0045] The above scheme gives an example of the third information, and the specific implementation is not limited to the above example. The third information can come from the second terminal itself, or be collected by the first node itself, or be received by the first node from other nodes.

[0046] In an embodiment of the first aspect, the terminal state comprises at least one of: a power state; a computing power state; a storage state; a temperature state.

[0047] Based on the above scheme, the terminal state limits the terminal participating in the execution of the first task, so that a suitable first terminal can be selected to participate in the execution of the first task, ensuring the smooth execution of the first task.

[0048] In some embodiments of the first aspect, before sending the second information to at least one first terminal, the method further comprises: sending fourth information to the second terminal; and receiving the third information sent by the second terminal based on the fourth information.

[0049] Based on the above scheme, the first node can instruct the second terminal to report the third information, so that the first node instructs the second terminal to report only when it needs the third information, thereby reducing unnecessary reporting of the third information by the second terminal.

[0050] In some embodiments of the first aspect, the fourth information comprises at least one of: requirement information indicating a terminal capability and / or a terminal state for executing the first task; and inquiry information inquiring about information related to the execution of the first task from the second terminal.

[0051] The above scheme illustrates the information content of the fourth information, and the specific implementation is not limited to the above example.

[0052] In some embodiments of the first aspect, the sending of the fourth information to the second terminal comprises: sending system information to the second terminal; and the system information comprises the fourth information.

[0053] Based on the above scheme, the fourth information is carried in the system information, so that the first node can broadcast the fourth information based on the system information, which can save wireless resources and / or signaling overhead compared to unicast transmission.

[0054] In some embodiments of the first aspect, before determining the first terminal from the second terminal according to third information related to the second terminal, the method further comprises: receiving the third information sent by the second terminal.

[0055] Based on the above scheme, the second terminal actively reports the third information, so that the first node does not need to be specially instructed by the fourth information, and the reporting process of the third information is simplified.

[0056] In some embodiments of the first aspect, the third information is included in auxiliary information sent by the second terminal.

[0057] Based on the above scheme, the third information is reported by being carried in the auxiliary information, so that an additional information element (IE) does not need to be set to send the third information.

[0058] In some embodiments of the first aspect, the method further comprises: sending fifth information to the second node; the fifth information is used by the second node to determine the execution information of the first task.

[0059] Based on the above scheme, the first node sends the fifth information to the second node, so that the second node can know the execution status of the first task through the sending of the fifth information, and better information interconnection and intercommunication between the first node and the second node is realized.

[0060] In some embodiments of the first aspect, the first task execution fails or the first task does not start execution, and the fifth information includes a failure reason.

[0061] Based on the above scheme, by carrying the failure reason in the fifth information, the second node can know the failure reason, so that adaptive adjustment can be made, such as replacing the first node assisting the execution of the first task, or changing the execution time period of the first task, etc.

[0062] In some embodiments, the failure reason includes at least one of the following: unable to obtain a terminal capable of executing the first task; unable to obtain a sufficient number of terminals for executing the first task.

[0063] In some embodiments of the first aspect, the method further comprises at least one of the following:

[0064] When the first condition is met, sixth information is sent to at least one third terminal; the sixth information is used to instruct the third terminal to stop executing the first task; the third terminal belongs to a terminal that is executing the first task; and / or,

[0065] When the first condition is met, the at least one fourth terminal is determined as a terminal participating in the execution of the first task.

[0066] Based on the above scheme, the first node dynamically adjusts the execution terminal of the first task in the execution process of the first task, thereby ensuring the smooth execution of the first task.

[0067] In some embodiments of the first aspect, the first condition comprises at least one of the following: the terminal state of the third terminal does not meet the requirement of executing the first task; the terminal state of the fourth terminal changes from not meeting the requirement of executing the first task to meeting the requirement of executing the first task; the terminal state of the fourth terminal is more suitable for executing the first task than the terminal state of the third terminal.

[0068] Based on the above scheme, the first node can select the most suitable terminal from the reachable terminals of the first node to participate in the execution of the first task, thereby ensuring the execution effect of the first task.

[0069] In some embodiments of the first aspect, before receiving the first information sent by the second node, the method further comprises: sending eighth information to the second node; the eighth information is used to indicate whether the first node supports executing the first task.

[0070] Based on the above scheme, the first node sends the eighth information to the second node, thereby facilitating the second node to select a suitable first node to participate in the execution of the first task.

[0071] In some embodiments of the first aspect, the sending, according to the first information, of the second information to the at least one first terminal comprises: sending, according to the first information, multicast and broadcast service (MBS) information to the at least one first terminal; the MBS information comprises the first information.

[0072] Based on the above scheme, the second information is sent to the first terminal as MBS information, which is equivalent to that the first task is set as a MBS task.

[0073] In some embodiments, the first node comprises at least one of the following: a radio resource management node; an application server.

[0074] Based on the above scheme, the first node is a radio resource management node and / or an application server, and both types of nodes are connected with a large number of terminals, so that the terminal resources can be fully used to achieve efficient and high-quality completion of the first task.

[0075] The second aspect provides a task processing method, wherein the method is executed by a second node, and the method comprises:

[0076] sending first information to a first node; the first information is related to a terminal performing a first task; the first task is a first model related task; the first model is an artificial intelligence AI model and / or a machine learning ML model.

[0077] In some embodiments of the second aspect, the first information comprises at least one of:

[0078] task information for performing the first task;

[0079] first index information for indicating an ability index of the trained first model;

[0080] second index information for indicating an index that an inference result of the first model needs to satisfy;

[0081] model information for indicating the first model;

[0082] terminal information for the first node to determine a terminal capable of performing the first task.

[0083] In some embodiments of the second aspect, the task information comprises at least one of:

[0084] task identification for identifying the first task;

[0085] task time for indicating a start time and / or an end time of the first task.

[0086] In some embodiments of the second aspect, the terminal information comprises at least one of:

[0087] ability information for indicating a terminal ability of a terminal performing the first task;

[0088] terminal type for a terminal type performing at least the first task;

[0089] terminal quantity for indicating a number of terminals performing the first task.

[0090] In some embodiments of the second aspect, the method further comprises:

[0091] receiving fifth information sent by the first node; the fifth information is used for the second node to determine execution information of the first task.

[0092] In some embodiments of the second aspect, the first task fails to be executed or the first task fails to be initiated for execution, and the fifth information comprises a failure cause.

[0093] In some embodiments of the second aspect, the failure cause comprises at least one of:

[0094] No terminal capable of performing the first task can be acquired;

[0095] No sufficient number of terminals capable of performing the first task can be acquired.

[0096] In some embodiments of the second aspect, the method further comprises:

[0097] receiving eighth information sent by the first node; the eighth information is used to indicate whether the first node supports performing the first task.

[0098] The third aspect provides a task processing method, wherein the method is performed by a terminal, and the method comprises: receiving second information sent by a first node; the second information is used to enable the terminal to perform a first task; the first task is a task of training a first model; the first model is an artificial intelligence (AI) model and / or a machine learning (ML) model.

[0099] In some embodiments of the third aspect, before receiving the second information sent by the first node, the method further comprises: sending third information to the first node; the third information is used by the first node to determine a terminal performing the first task.

[0100] In some embodiments of the third aspect, before sending the third information to the first node, the method further comprises: receiving fourth information sent by the first node; the fourth information is used by the terminal to send the third information to the first node.

[0101] In some embodiments of the third aspect, the fourth information comprises at least one of the following: requirement information used to indicate terminal capability and / or terminal state of performing the first task; inquiry information used to inquire information related to the terminal performing the first task.

[0102] In some embodiments of the third aspect, the sending of the third information to the first node comprises: sending auxiliary information containing the third information to the first node.

[0103] In some embodiments of the third aspect, the method further comprises: receiving sixth information sent by the first node; the sixth information is used to instruct a terminal performing the first task to stop performing the first task.

[0104] In some embodiments of the third aspect, the receiving of the second information sent by the first node further comprises: receiving the second information sent by the first node when a first condition is met.

[0105] In some embodiments of the third aspect, the first condition comprises at least one of: a terminal state of the third terminal does not meet a requirement for performing the first task; the third terminal is a terminal that is performing the first task; a terminal state of the fourth terminal changes from not meeting the requirement for performing the first task to meeting the requirement for performing the first task; the fourth terminal is a terminal that has not started performing the first task; and the terminal state of the fourth terminal is more in line with the requirement for performing the first task than the terminal state of the third terminal.

[0106] The fourth aspect provides a first node, wherein the first node comprises:

[0107] a receiving module configured to receive first information sent by a second node, the first information being related to a terminal performing a first task; the first task being a task related to a first model; and the first model being an artificial intelligence (AI) model and / or a machine learning (ML) model.

[0108] The fifth aspect provides a second node, wherein the second node comprises:

[0109] a sending module configured to send first information to a first node; the first information being related to a terminal performing a first task; the first task being a task related to a first model; and the first model being an artificial intelligence (AI) model and / or a machine learning (ML) model.

[0110] The sixth aspect provides a terminal, wherein the terminal comprises a receiving module configured to receive second information sent by a first node; the second information being used to cause the terminal to perform a first task; the first task being a task of training a first model; and the first model being an artificial intelligence (AI) model and / or a machine learning (ML) model.

[0111] The seventh aspect provides a communication system, wherein the communication system comprises a first node, a second node, and a terminal; the first node is configured to perform the task processing method of any of the technical solutions of the first aspect;

[0112] the second node is configured to perform the task processing method of any of the technical solutions of the second aspect;

[0113] the terminal is configured to perform the task processing method provided by any of the technical solutions of the third aspect.

[0114] The eighth aspect provides a program product, wherein the program product comprises a computer program, and the computer program is executed by a communication device to enable the communication device to implement the task processing method described in the optional implementation manners of the first aspect to the third aspect.

[0115] In a ninth aspect, the embodiments of the present disclosure provide a computer program which, when running on a computer, causes the computer to perform the task processing method described in the optional implementation manners of the first aspect to the third aspect.

[0116] It can be understood that the terminal (or UE), the network device, the communication system, the program product and the computer program are used to execute the method provided by the embodiments of the present disclosure. Therefore, the beneficial effects achieved by the above can refer to the beneficial effects in the corresponding method, which will not be described here.

[0117] The embodiments of the present disclosure provide a task processing method, a communication device, a communication system and a storage medium. The embodiments of the present disclosure are not exhaustive, but only illustrate some embodiments, and are not specific limitations on the protection scope of the present disclosure. In the case of no contradiction, each step in an embodiment can be implemented as an independent embodiment, and the steps can be combined arbitrarily, for example, the mode of removing some steps in an embodiment can also be implemented as an independent embodiment, and the order of the steps in an embodiment can be exchanged arbitrarily, in addition, the optional implementation manners in an embodiment can be combined arbitrarily; in addition, the embodiments can be combined arbitrarily, for example, some or all steps of different embodiments can be combined arbitrarily, an embodiment can be combined with the optional implementation manners of other embodiments.

[0118] In the embodiments of the present disclosure, the terms and / or descriptions of the embodiments are consistent and can be referred to each other if there is no special description and logical conflict, and the technical features in different embodiments can be combined to form new embodiments according to their inherent logical relationship.

[0119] The terms used in the embodiments of the present disclosure are only for the purpose of describing the specific embodiments, and not as a limitation on the present disclosure.

[0120] In the embodiments of the present disclosure, unless otherwise specified, the elements expressed in singular form, such as "one", "a", "the", "above", "preceding", "this", etc., can represent "one and only one", or "one or more", "at least one", etc. For example, in the case of using articles such as "a", "an", "the" in English, the noun after the article can be understood as singular expression, or as plural expression.

[0121] In the embodiments of the present disclosure, "a plurality of" means two or more.

[0122] In some embodiments, the terms "at least one of," "one or more of," "a plurality of," "multiple," and the like can be used interchangeably.

[0123] In some embodiments, the recitations "at least one of A, B," "A and / or B," "in one case A, in another case B," "one case A, another case B," and the like can include the following technical ways according to the situation: in some embodiments, A (A is executed regardless of B); in some embodiments, B (B is executed regardless of A); in some embodiments, A and B are selectively executed (A and B are selectively executed); in some embodiments, A and B (A and B are both executed). When there are more branches of A, B, C, and the like, the above is similar.

[0124] In some embodiments, the recitations "A or B" and the like can include the following technical ways according to the situation: in some embodiments, A (A is executed regardless of B); in some embodiments, B (B is executed regardless of A); in some embodiments, A and B are selectively executed (A and B are selectively executed). When there are more branches of A, B, C, and the like, the above is similar.

[0125] The prefix words "first," "second," and the like in the embodiments of the present disclosure are merely used to distinguish different description objects, and do not constitute a limitation on the position, order, priority, quantity, or content of the description objects. The description of the description objects should refer to the description in the claims or embodiments, and should not constitute an additional limitation because of the use of the prefix words. For example, the description objects are "fields," and the ordinal words before "fields" in "first field" and "second field" do not limit the positions or orders between "fields." "First" and "second" do not limit whether the "fields" they modify are in the same message, nor do they limit the order of "first field" and "second field." For another example, the description objects are "levels," and the ordinal words before "levels" in "first level" and "second level" do not limit the priorities between "levels." For another example, the quantity of the description objects is not limited by the ordinal words, and can be one or more. For example, "first device," where the quantity of "devices" can be one or more. In addition, the objects modified by different prefix words can be the same or different, for example, the description objects are "devices," and "first device" and "second device" can be the same device or different devices, and their types can be the same or different. For another example, the description objects are "information," and "first type of information" and "second type of information" can be the same information or different information, and their contents can be the same or different.

[0126] In some embodiments, "comprising", "including", "to indicate", "carrying", can be interpreted as directly carrying A, or indirectly indicating A.

[0127] In some embodiments, the terms "…", "determining …", "in the case of …", "when …", "when …", "if …", "if …", and the like can be replaced with each other.

[0128] In some embodiments, the terms "greater than", "greater than or equal to", "not less than", "more than", "more than or equal to", "not less than", "higher than", "higher than or equal to", "not lower than", "above", and the like can be replaced with each other, and the terms "less than", "less than or equal to", "not greater than", "less than", "less than or equal to", "not more than", "lower than", "lower than or equal to", "not higher than", "below", and the like can be replaced with each other.

[0129] In some embodiments, the device and the like can be interpreted as physical or virtual, and the name is not limited to the name recorded in the embodiments. The terms "device", "equipment", "device", "circuit", "network element", "node", "function", "unit", "section", "system", "network", "chip", "chip system", "entity", "subject", and the like can be replaced with each other.

[0130] In some embodiments, "network" can be interpreted as a device (for example, access network device, core network device, etc.) contained in the network.

[0131] In some embodiments, the terms “access network device (AN device),” “radio access network device (RAN device),” “base station (BS),” “radio base station,” “fixed station,” “node,” “access point,” “transmission point (TP),” “reception point (RP),” “transmission / reception point (TRP),” “panel,” “antenna panel,” “antenna array,” “cell,” “macro cell,” “small cell,” “femto cell,” “pico cell,” “sector,” “cell group,” “serving cell,” “carrier,” “component carrier,” “bandwidth part (BWP),” and the like can be used interchangeably.

[0132] In some embodiments, the terms "terminal," "terminal device," "user equipment (UE)," "user UE," "mobile station (MS)," "mobile UE (MT)," "subscriber station," "mobile unit," "subscriber unit," "wireless unit," "remote unit," "mobile device," "wireless device," "wireless communication device," "remote device," "mobile subscriber station," "access UE," "mobile terminal," "wireless terminal," "remote terminal," "handset," "user agent," "mobile client," "client," and so on can be replaced with each other.

[0133] In some embodiments, the access network device, the core network device, or the network device can be replaced with the UE. For example, the embodiments of the present disclosure can also be applied to a structure in which communication between the access network device, the core network device, or the network device and the UE is replaced with communication between a plurality of UEs (e.g., device-to-device (D2D), vehicle-to-everything (V2X), and so on). In this case, the structure in which the UE has all or part of the functions of the access network device can also be provided. In addition, the terms "uplink," "downlink," and so on can also be replaced with terms corresponding to the inter-UE communication (e.g., "side"). For example, the uplink channel, the downlink channel, and so on can be replaced with the side channel, and the uplink, the downlink, and so on can be replaced with the sidelink.

[0134] In some embodiments, the UE can be replaced with the access network device, the core network device, or the network device. In this case, the structure in which the access network device, the core network device, or the network device has all or part of the functions of the UE can also be provided.

[0135] In some embodiments, the data, information, etc. can be obtained in compliance with the laws and regulations of the country in which the location is situated.

[0136] In some embodiments, the data, information, etc. can be obtained after obtaining the consent of the user.

[0137] In addition, each element, each row, or each column in the table of the embodiments of the present disclosure can be implemented as an independent embodiment, and any combination of any element, any row, or any column can also be implemented as an independent embodiment.

[0138] FIG. 1 is an architecture schematic diagram of a communication system according to an embodiment of the present disclosure.

[0139] As shown in FIG. 1, the communication system 100 includes a terminal 101 and a network device 102. The network device 102 can include an access network device and / or a core network device. The terminal can also be referred to as a UE.

[0140] In some embodiments, the UE 101 includes at least one of a mobile phone, a wearable device, an Internet of Things device, a communication-capable automobile, a smart automobile, a Pad, a computer with wireless transceiver function, a virtual reality (VR) UE device, an augmented reality (AR) UE device, a wireless UE device in industrial control, a wireless UE device in self-driving, a wireless UE device in remote medical surgery, a wireless UE device in smart grid, a wireless UE device in transportation safety, a wireless UE device in smart city, a wireless UE device in smart home, but is not limited thereto.

[0141] In some embodiments, the UE is also referred to as a User Equipment (UE).

[0142] In some embodiments, the access network device may, for example, be at least one of a node or a device that accesses a UE to a wireless network, and the access network device may, for example, include at least one of an evolved NodeB (eNB), a next generation eNB (ng-eNB), a next generation NodeB (gNB), a node B (NB), a home node B (HNB), a home evolved node B (HeNB), a wireless backhaul device, a radio network controller (RNC), a base station controller (BSC), a base transceiver station (BTS), a base band unit (BBU), a mobile switching center, a base station in a 6G communication system, an Open RAN, a Cloud RAN, a base station in other communication systems, an access node in a Wi-Fi system, but is not limited thereto.

[0143] In some embodiments, the technical means of the present disclosure can be applicable to an Open RAN architecture, at which time, the interfaces between or within the access network devices involved in the embodiments of the present disclosure can become internal interfaces of the Open RAN, and the processes and information interactions between these internal interfaces can be implemented through software or programs.

[0144] In some embodiments, the access network device can be composed of a central unit (CU) and a distributed unit (DU), where the CU can also be referred to as a control unit. The CU-DU structure can split the protocol layers of the access network device, and some of the protocol layers can be controlled by the CU, and the rest or all of the protocol layers can be distributed in the DU and controlled by the CU, but is not limited thereto.

[0145] In some embodiments, the core network device can be one device including the first network element, etc., or can be multiple devices or device groups, each including the first network element. The network element can be virtual or physical. The core network may, for example, include at least one of an evolved packet core (EPC), a 5G core network (5GCN), and a next generation core (NGC).

[0146] It can be understood that the communication system described in the embodiments of the present disclosure is for more clearly illustrating the technical means of the embodiments of the present disclosure, and does not constitute a limitation on the technical means provided by the embodiments of the present disclosure. It can be known by those skilled in the art that, as the system architecture evolves and new service scenarios appear, the technical means provided by the embodiments of the present disclosure are also applicable to similar technical problems.

[0147] The following embodiments of the present disclosure can be applied to the communication system 100 shown in FIG. 1 or part of the subject, but are not limited thereto. The subjects shown in FIG. 1 are illustrative, and the communication system can include all or part of the subjects in FIG. 1, or other subjects other than FIG. 1. The number and form of each subject is arbitrary, and the connection relationship between the subjects is illustrative. The subjects can be connected or not connected, and the connection can be in any way, can be direct connection or indirect connection, can be wired connection or wireless connection.

[0148] Embodiments of the present disclosure can be applied to Long Term Evolution (LTE), LTE-Advanced (LTE-A), LTE-Beyond (LTE-B), SUPER 3G, IMT-Advanced, 4th generation mobile communication system (4G), 5th generation mobile communication system (5G), 5G new radio (NR), Future Radio Access (FRA), New-Radio Access Technology (RAT), New Radio (NR), New radio access (NX), Future generation radio access (FX), Global System for Mobile communications (GSM (registered trademark)), CDMA2000, Ultra Mobile Broadband (UMB), IEEE 802.11 (Wi-Fi (registered trademark)), IEEE 802.16 (WiMAX (registered trademark)), IEEE 802.20, Ultra-WideBand (UWB), Bluetooth (Bluetooth (registered trademark)), Public Land Mobile Network (PLMN) network, Device-to-Device (D2D) system, Machine to Machine (M2M) system, Internet of Things (IoT) system, Vehicle-to-Everything (V2X), system using other resources, next-generation system extended based thereon, and the like. In addition, a plurality of systems can be combined (for example, LTE and NR can be combined).

[0149] In the current machine learning and big data technology, when connecting with the same industry or non-industry institutions, there will be a problem of data island. Each party, each organization or personal device will generate individual data islands. There is no good method for the data between these information islands to flow freely. Federated learning provides a mechanism for data not to leave the local training or reasoning. Federated learning is a new technology in the fifth generation mobile communication (5G) era. thA typical scenario in 5G networks involves 5G terminals generating raw data. The goal is to aggregate data from numerous 5G terminals using federated learning to train an artificial intelligence model for use within those terminals. Federated learning is a distributed machine learning method that allows multiple devices or servers to collaboratively train a model while maintaining data locality—meaning the data doesn't need to leave the user's device or their respective server. This method is particularly useful when dealing with privacy-sensitive data or when data analysis needs to be performed across multiple geographical locations. The basic process of federated learning includes the following steps: Local Training: Each participating device or server trains an initial model using its local data. Model Aggregation: Each device or server sends the trained model parameters or gradients to a central server. Global Update: The central server aggregates these parameters or gradients and updates the global model. Model Distribution: The updated global model is distributed back to the individual devices or servers. Iterative Optimization: The above process is repeated until the model achieves the expected performance.

[0150] Federated learning has applications in various fields, such as personalized recommendation systems on mobile devices, medical data analysis, and data integration of IoT devices. With increasing demands for data privacy and security, federated learning, as an effective solution, is experiencing rapid research and application development.

[0151] In sixth-generation mobile communication (6 th In research on Generation 6G, consideration is being given to enabling terminals to access computing power for the network. In future mobile networks, given the large number of terminals, if multiple terminals can provide computing power to application nodes, not only can the limited computing resources on the terminals be utilized, but privacy concerns regarding the terminals are also eliminated. Currently, the use of federated learning in 6G network deployments is still in the early stages of research. This paper presents a working framework for using federated learning on mobile terminals.

[0152] The possibility of terminals opening up their computing capabilities to the network is being considered. In future mobile networks, due to the large number of terminals, multiple terminals could provide computing power to application nodes, utilizing the limited computing resources on the terminals themselves without raising privacy concerns. Currently, the application of federated learning in 6G network deployments is still in the early research stages. This paper presents a working framework for using federated learning on mobile terminals.

[0153] As shown in Figure 2, this embodiment of the present disclosure provides a task processing method, executed by the communication system shown in Figure 1. The method may include:

[0154] S2101: The first node sends the eighth message to the second node.

[0155] In some embodiments, the first node can include, but is not limited to, an access network node and / or an application server. Exemplarily, the first node can include, but is not limited to, a radio resource management node and / or an application server.

[0156] In some embodiments, the second node includes, but is not limited to, a core network node and / or an application server.

[0157] In some embodiments, the first task is a task related to a first model.

[0158] In some embodiments, the first model is an artificial intelligence (AI) model and / or a machine learning (ML) model.

[0159] In some embodiments, the first task can be a training task of the first model. Exemplarily, the training task can include, but is not limited to, a learning task. Exemplarily, the learning task can also be referred to as a federated training task. Exemplarily, the training task can also be referred to as a learning task.

[0160] In some embodiments, the first task can be an inference task using the first model.

[0161] In some embodiments, the eighth information is used to indicate whether the first node supports performing the first task.

[0162] In some embodiments, the eighth information can be capability information of the first node.

[0163] In some embodiments, the eighth information can also be version information and the like of the first node, so as to facilitate the second node to determine whether the first node supports the execution of the first task according to the version information and the like.

[0164] In some embodiments, the eighth information can be state information of the first node, which can indicate whether the first node is suitable for participating in the execution of the first task in the current period or a future period.

[0165] In some embodiments, the eighth information can be willingness information of the first node, which can indicate whether the first node is willing to participate in the execution of the first task in the current period or a future period.

[0166] S2102: The second node sends first information to the first node.

[0167] In some embodiments, the first information is related to the terminal performing the first task.

[0168] In some embodiments, the first task is a task related to a first model.

[0169] In some embodiments, the first model is an artificial intelligence (AI) model and / or a machine learning (ML) model.

[0170] In some embodiments, the first information comprises at least one of:

[0171] task information for performing the first task;

[0172] first index information for indicating an ability index of the first model after training;

[0173] second index information for indicating an index that the inference result of the first model needs to satisfy;

[0174] model information for indicating the first model;

[0175] terminal information for the first node to determine a terminal capable of performing the first task.

[0176] In some embodiments, the task information can be any information describing the first task. For example, a task name, a task identifier, or the like of the first task. Illustratively, the task information comprises at least one of: a task identifier for identifying the first task; and a task time for indicating a start time and / or an end time of the first task.

[0177] In some embodiments, the task information can further comprise, but is not limited to, at least one of:

[0178] time information for indicating an execution time of the first task;

[0179] region information for indicating a region where the terminal or the first node of the first task is located.

[0180] In some embodiments, the first task is a training task, and the index information (i.e., the first index information) contained in the first information can be used to indicate an ability index of the first model after completing training. For example, the ability index comprises at least one of: a convergence time, a computing performance, a training efficiency, an accuracy, an inference efficiency, and / or an accuracy.

[0181] In some embodiments, the second index information can be used to indicate an index that the inference result of the first model needs to satisfy, for example, a completion time and / or an accuracy of the inference result.

[0182] In some embodiments, the model information can comprise, but is not limited to, a model identifier, a model size, and / or a model parameter of the first model.

[0183] In some embodiments, the terminal information can comprise, but is not limited to, at least one of:

[0184] an ability index of the terminal;

[0185] type information of the terminal;

[0186] terminal quantity;

[0187] terminal status, for example, the terminal status can be a status of the terminal performing the first task. The terminal status includes but is not limited to a terminal load status, a terminal movement status and / or a terminal temperature status.

[0188] In some embodiments, the terminal information includes at least one of the following: capability information, for indicating terminal capability of the terminal performing the first task; terminal type, for indicating a type of the terminal performing the first task; terminal quantity, for indicating a number of the terminal performing the first task.

[0189] In some embodiments, the second node sends the first information to the first node according to eighth information. Illustratively, the eighth information indicates that the first node is able, willing or in need to participate in the execution of the first task, and the first information is sent to the first node. Illustratively, the eighth information indicates that the first node is able, willing or in need to participate in the execution of the first task, and the first information is not sent to the first node.

[0190] S2103: The first node sends fourth information to the second terminal.

[0191] In some embodiments, the second terminal can include but is not limited to at least one of the following: a terminal having a connection with the first node, a terminal connectable to the first node. In some embodiments, the third information can include but is not limited to information collected by the first node itself, information received by the first node from the second terminal, information of the second terminal obtained by the first node from other nodes.

[0192] In some embodiments, the first node sends the fourth information through a connection with the second terminal.

[0193] In some embodiments, the fourth information can include but is not limited to a broadcast message, a multicast message or a unicast message.

[0194] In some embodiments, the fourth information can be used to instruct the second terminal to report the third information.

[0195] In some embodiments, the third information can be any information used by the first node to determine the first terminal from the second terminal. It is worth noting that the third information is not limited to information reported by the second terminal itself.

[0196] In some embodiments, the fourth information can include but is not limited to at least one of the following:

[0197] request information, for indicating terminal capability and / or terminal status of the terminal performing the first task;

[0198] inquiry information, for inquiring information related to the execution of the first task by the second terminal.

[0199] In some embodiments, the fourth information can be inquiry information inquiring whether the second terminal is willing to participate in the execution of the first task. The fourth information can be information informing the second terminal of the terminal required to execute the first task. At this time, the fourth information can be understood as information for the second terminal to determine whether it can participate in the execution of the first task.

[0200] In some embodiments, the inquiry information can be used to inquire the capability, state, specific location, and / or user willingness of the second terminal.

[0201] In some embodiments, S2103 is an optional step. For example, in a scheme in which the second terminal actively reports the third information, the first node does not need to send the fourth information to the second terminal. For another example, the first node has collected the third information in the past information interaction with the second terminal, or the first node receives the capability information and / or willingness information of the second terminal from another node (e.g., a user data management (UDM)). For another example, the first node receives the mobility information of the second terminal from an access management function (AMF). In these scenarios, S2103 is an optional step.

[0202] S2104: The second terminal sends the third information to the first node.

[0203] In some embodiments, the second terminal sends the third information to the first node based on the fourth information.

[0204] In some embodiments, the second terminal actively reports the third information.

[0205] In some embodiments, the third information is contained in the assistance information sent by the second terminal. For example, the third information is carried in user assistance information (UAI). For example, the UAI can be any information carried by a UAI information element (IE).

[0206] In the embodiments of the present disclosure, the third information is carried in the UAI, and there is no need to additionally provide an IE carrying the third information.

[0207] In some embodiments, the second terminal can report the third information according to a prohibit timer of the UAI. For example, the second terminal starts a prohibit timer each time the third information is sent. During the running of the prohibit timer, the second terminal no longer repeatedly sends the third information.

[0208] In some embodiments, during the process of establishing a connection with the first node, the second terminal sends third information to the first node. For example, if the terminal state of the second terminal changes or the user's intention changes, the second terminal may proactively report third information based on a trigger from the first node.

[0209] In some embodiments, the third information includes at least one of the following:

[0210] Status information, used to indicate the terminal status of the second terminal;

[0211] Capability information, used to indicate the capabilities of the second terminal;

[0212] Willingness information, used to indicate whether the second terminal is willing to participate in the execution of the first task;

[0213] Location information, used to indicate the geographical location of the second terminal;

[0214] Channel information is used to indicate the current channel state of the second terminal and / or the estimated channel state within a specified time period;

[0215] Mobility information, used to indicate the mobility of the second terminal.

[0216] For example, the status information of the second terminal can be used to indicate the current load status, current computing power status, current storage status, current temperature status, current remaining bandwidth status, load status for a future period of time, computing power status for a future period of time, storage status for a current period of time, temperature status for a future period of time, and / or remaining bandwidth status for a future period of time.

[0217] As an example, the terminal state includes at least one of the following: battery status; computing power status; storage status; temperature status.

[0218] In some embodiments, the battery status may be determined by the remaining battery percentage of the terminal or the power supply status of the device.

[0219] In some embodiments, the computing power status may indicate whether the terminal has a processor that is conducive to performing tasks related to AI models and / or ML models. For example, the computing power status may be used to indicate whether the terminal has an image processor, the number of processors in the terminal, the number of cores of the processor, the number of bits supported by the processor, etc.

[0220] In some embodiments, the storage status may be related to the remaining available storage capacity of the terminal, the maximum storage capacity of the terminal, the storage capacity already used, the type of memory, and other relevant information.

[0221] In some embodiments, the temperature status can be used to indicate whether the terminal is overheating, or the current temperature range of the terminal. This temperature may be the overall average temperature of the terminal, and / or the temperature of the terminal's processor.

[0222] In some embodiments, capability information may indicate information such as the terminal's computing power status, storage capacity, and bandwidth capacity.

[0223] In some embodiments, if the second terminal receives the fourth information sent by the first node, the second terminal may also refuse to report the information indicated by the fourth information. That is, S2104 is an optional step. For example, if the second terminal does not receive the third information and does not actively report the third information, the second terminal may not need to execute S2104.

[0224] In some embodiments, the fourth information may be carried in system information, or it may be carried in Radio Resource Control (RRC) messages, Media Access Control (MAC) control elements (CE), or Uplink Control Information (UCI).

[0225] S2105: The first node determines the first terminal.

[0226] In some embodiments, the first node determines the first terminal from the second terminal based on third information related to the second terminal.

[0227] In some embodiments, the first node determines the first terminal from the second terminal based on third information it has collected. In other embodiments, the first node determines the first terminal from the second terminal based on third information reported by the second terminal. For example, the first node determines the first terminal based on third information received from other nodes.

[0228] In other embodiments, the first terminal may randomly select a terminal with which it has established a connection as the first terminal based on the number of terminals required to perform the first task. In other embodiments, the first terminal may also select or determine the first terminal based on the instruction of the second node. In short, there are multiple ways for the first node to determine the first terminal, and it is not limited to any of the above methods.

[0229] In some embodiments, S2105 may be an optional step. For example, instead of selecting a first terminal, the first node broadcasts second information, and the terminal receiving the second information actively responds to determine whether to participate in the execution of the first task. For example, if the terminal determining the execution of the first task actively responds and / or submits the execution result, then the step of the first node determining the first terminal can be omitted.

[0230] S2106: The first node sends the second information to the first terminal.

[0231] In some embodiments, the first node broadcasts second information to one or more first terminals.

[0232] In some embodiments, the first node multicasts second information to one or more first terminals.

[0233] In some embodiments, the first node unicasts second information to one or more first terminals.

[0234] In some embodiments, second information is sent to each of the at least one first terminal based on the first information.

[0235] In some embodiments, second information is sent to a terminal group based on the first information; the terminal group includes the at least one first terminal.

[0236] In some embodiments, broadcast multicast service (MBS) information is sent to the at least one first terminal based on the first information; the MBS information includes the first information.

[0237] S2107: The first node sends the fifth message to the second node.

[0238] In some embodiments, the fifth information is used by the second node to determine the execution information of the first task. For example, the execution status may include, but is not limited to, execution status information and / or execution result information.

[0239] In some embodiments, execution status information is used to indicate the execution status. The execution status includes, but is not limited to, at least one of the following: execution started, execution in progress, execution completed, and execution interrupted.

[0240] In some embodiments, execution result information may be used to indicate the execution result. This execution result may include, but is not limited to, at least one of the following: execution success and / or execution failure.

[0241] In some embodiments, if the first task fails to execute or the first task is not started, the fifth information includes the reason for the failure.

[0242] In some embodiments, the failure reason includes at least one of the following:

[0243] Unable to obtain a terminal capable of performing the first task;

[0244] A sufficient number of terminals to execute the first task could not be obtained.

[0245] S2108: The first node sends the sixth message to the third terminal.

[0246] In some embodiments, satisfying the first condition means sending the sixth information to the third terminal.

[0247] In some embodiments, the sixth information is used to instruct the third terminal to stop executing the first task.

[0248] In other embodiments, the third terminal is a terminal that is performing the first task.

[0249] In some embodiments, when the third terminal stops executing the first task, it reports the execution status of the first task at the time of stopping to the first node, so that the first node can use the execution result of the third terminal.

[0250] S2109: Identify at least one fourth terminal as a terminal that participates in the execution of the first task midway.

[0251] In some embodiments, when a first condition is met, at least one fourth terminal is identified as a terminal that participates in the execution of the first task midway. If the fourth terminal participates in the execution of the first task midway, second information is sent to the fourth terminal. This second information can be used by the fourth terminal to execute the first task.

[0252] In some embodiments, the first condition may be a condition that the first node needs to meet to change the execution terminal of the first task. In some embodiments, the first node determines the most suitable execution terminal for the first task based on the terminal status of its reachable terminals. If the execution terminal of the first task changes in two consecutive determinations, the sixth message instructs the third terminal currently executing the first task to stop the execution of the first task, and sends the first information to the fourth terminal that has been newly determined as the first terminal, so that the first task takes over from the third terminal to participate in the execution of the first task. For example, compared to the first terminal, the first information received by the fourth terminal may also include: the current execution status of the first task, but it is always an instruction to the terminal to execute the first task.

[0253] In some embodiments, the first condition includes at least one of the following:

[0254] The terminal status of the third terminal does not meet the requirements for performing the first task;

[0255] The terminal status of the fourth terminal changes from not meeting the requirements for performing the first task to meeting the requirements for performing the first task;

[0256] The terminal state of the fourth terminal is more in line with the requirements for performing the first task than the terminal state of the third terminal.

[0257] As shown in Figure 3, this embodiment of the present disclosure provides a task processing method, executed by a first node, the method further comprising:

[0258] S3101: Send the eighth message;

[0259] In some embodiments, the first node sends an eighth message to the second node.

[0260] In some embodiments, the description of the first node, the second node, and / or the eighth information can be found in the embodiment corresponding to Figure 2.

[0261] In some embodiments, the optional operation of the first node sending the eighth information can be found in the relevant part of the embodiment corresponding to FIG2.

[0262] S3102: Receive the first message.

[0263] In some embodiments, the description of the first node can be found in the embodiment corresponding to Figure 2.

[0264] S3103: Send the fourth message.

[0265] In some embodiments, the first node sends fourth information to the second terminal.

[0266] In some embodiments, the relevant descriptions of the second terminal and the fourth information can be found in the embodiment corresponding to Figure 2.

[0267] In some embodiments, the optional method by which the first node sends the fourth information can be found in the optional implementation methods related to the embodiment corresponding to FIG2.

[0268] S3104: Receive third information.

[0269] In some embodiments, third information sent by a second terminal is received.

[0270] In some embodiments, the relevant description of the third information can be found in the embodiment corresponding to Figure 2.

[0271] In some embodiments, one or more of S3103 and S3104 are optional steps, and the execution order of S3103 and S3104 may be before S3101 and / or before S3102, or after S3102.

[0272] S3105: Identify the first terminal.

[0273] In some embodiments, the optional method by which the first node determines the first terminal can be found in the optional implementation methods related to the embodiment corresponding to FIG2.

[0274] S3106: Send the second message.

[0275] In some embodiments, the relevant description of the second information can be found in the embodiment corresponding to Figure 2.

[0276] In some embodiments, the optional method for the first node to send the second information can be found in the description related to the embodiment corresponding to Figure 2.

[0277] S3107: Send the fifth message.

[0278] In some embodiments, the relevant description of the fifth information can be found in the embodiment corresponding to Figure 2.

[0279] In some embodiments, the optional method for the first node to send the fifth information can be found in the description related to the embodiment corresponding to Figure 2.

[0280] In some embodiments, steps S3101, S3103 to S3107 are all optional. For example, upon receiving the first information, the first node may initiate the execution of the first task, or it may choose not to initiate the execution of the first task. If the execution of the first task is not initiated, then steps S3104 to S3107 are all optional. As another example, taking the first node as a radio resource management node, if the first node has the default capability to execute the first task according to the protocol or operator configuration, then the transmission of the eighth information can be omitted.

[0281] In some embodiments, if the first node collects the third information through other transmissions, then steps S3103 and / or S3104 are optional. In some embodiments, if the second terminal actively reports the third information, then the first node does not need to send the fourth information, i.e., step S3103 is optional. In some embodiments, the first node has the default capability to execute the first task and defaults to completing the execution of the first task, then the transmission of execution information can be omitted.

[0282] As shown in Figure 4, this embodiment of the present disclosure provides a task processing method, executed by a second node, the method further comprising:

[0283] S4101: Receive the eighth message.

[0284] In some embodiments, the second node receives the eighth message sent by the first node.

[0285] In some embodiments, the description of the first node, the second node, and / or the eighth information can be found in the embodiment corresponding to Figure 2.

[0286] S4102: Send the first message.

[0287] In some embodiments, the second node sends first information to the first node.

[0288] In some embodiments, the description of the first information can be found in the embodiment corresponding to FIG2.

[0289] In some embodiments, the optional method by which the first node sends the first information can be found in the optional implementation of the embodiment corresponding to FIG2.

[0290] S4103: Receive the fifth message.

[0291] In some embodiments, the second node receives the fifth information from the first node.

[0292] In some embodiments, the description of the fifth information can be found in the embodiment corresponding to Figure 2.

[0293] As shown in Figure 5, this embodiment of the present disclosure provides a task processing method executed by a terminal, the method further comprising:

[0294] S5101: Receive fourth information.

[0295] In some embodiments, the terminal receives fourth information sent by the first node.

[0296] In some embodiments, the description of the fourth information can be found in the embodiment corresponding to Figure 2.

[0297] S5102: Send third information;

[0298] In some embodiments, the terminal sends third information to the first node.

[0299] In some embodiments, the description of the third information can be found in the embodiment corresponding to Figure 2.

[0300] In some embodiments, the optional method for the terminal to send third information can be found in the optional implementation of the embodiment corresponding to FIG2.

[0301] S5103: Receive the second information.

[0302] In some embodiments, the terminal receives second information sent by the first node.

[0303] In some embodiments, the description of the second information can be found in the embodiment corresponding to FIG2.

[0304] In some embodiments, the optional method for the terminal to send the second information can be found in the optional implementation of the embodiment corresponding to FIG2.

[0305] This disclosure provides a working mechanism for machine learning in a wireless network. This machine learning may include, but is not limited to, federated learning. The working mechanism may include: a first node obtaining the requirements of an AI-related task, such as a federated learning task, from a second node. The first node may be a wireless resource management node. The second node may be an application server.

[0306] In one embodiment, the first node is a base station.

[0307] In one embodiment, the second node is the core network or an AI-related functional network element deployed in the core network.

[0308] In one embodiment, the core network node will notify the base station of the task requirements for federated learning, which is used by the base station to determine whether to accept the task and as the basis for subsequent related operations.

[0309] In one embodiment, the task requirements for core network nodes to notify base stations of federated learning may include, but are not limited to, at least one of the following:

[0310] Capability metrics directly related to AI computing performance include, for example, convergence time, energy efficiency of joint communication and computation, training efficiency and accuracy, and inference efficiency and accuracy.

[0311] Model information, such as model information identifiers or descriptions of the AI ​​model's structure and / or model parameters; the start and end times of the task.

[0312] In one embodiment, the core network node will notify the base station of the user number requirement for the federated learning task, such as the minimum number of users.

[0313] In one embodiment, the wireless resource management node (base station) and the AI ​​application server-related nodes (such as the core network) need to interact in advance to see if they support AI-related task requirements, such as whether the wireless resource management node or the AI ​​application server has federated learning capabilities.

[0314] After obtaining the learning task, the wireless resource management node publishes the task and notifies the terminal nodes to participate in the learning task.

[0315] In one embodiment, the base station sends training model information to the UE. This information can be used to train the AI ​​model on the terminal, infer the results, and return them to the radio resource management node.

[0316] When base stations and other radio resource management nodes distribute training model information, they can notify terminal nodes to participate in the task on a per UE or per UE group basis.

[0317] In one embodiment, each UE group may include one terminal or multiple associated terminals. For example, the UE group may include: an in-vehicle terminal and a portable terminal belonging to the same user.

[0318] In one embodiment, the base station selects users who meet the requirements to participate in AI tasks, which can be based on auxiliary information reported by the terminal. For example, a connected terminal can report information such as the computing power, memory, and battery power it can provide, as well as the user's willingness to participate. This information can be used by the base station as a basis for selecting target terminals.

[0319] In one embodiment, the base station first queries the terminal and selects a task that can participate in federated learning based on the terminal's feedback. In another embodiment, the terminal can provide information indicating its ability to participate in the task. For example, this information may indicate the time the terminal can participate in task execution, its contribution, etc. This contribution may include information such as available computing resources and / or storage resources. In another embodiment, the terminal can provide information indicating its inability to participate in the task and / or the reason for this inability. The reason may indicate insufficient computing power or the terminal overheating.

[0320] In one embodiment, the base station will issue learning tasks to terminals that intend to participate in federated learning.

[0321] In one embodiment, the wireless resource management node can notify multiple terminal nodes to participate in the learning task.

[0322] In one embodiment, the base station can notify the terminal of auxiliary information or rules for the learning task to be participated in in the system information, and the terminal that meets the conditions will participate in the learning task.

[0323] For example, the rules that need to be met to participate in a learning task may include, but are not limited to, at least one of the following:

[0324] The terminal's channel quality was detected to be better than the threshold. The terminal's mobility was detected to be lower than the threshold.

[0325] The terminal was detected to be within a certain geographical location range.

[0326] The terminal was detected to be within a certain time range. The terminal's computing power reserve was detected to be sufficient to meet the task.

[0327] The prediction assumes that the terminal's wireless conditions will not deteriorate within a certain period, such as a radio link failure (RLF) or handover. It also considers the terminal's willingness, such as how long they are willing to participate in the task.

[0328] In one embodiment, the base station may notify the terminals of the learning task to be participated in in the form of a multicast broadcast (MBS) service; the task begins after the first or at least N terminals join the MBS session.

[0329] In one embodiment, a specific terminal can be removed from the learning task.

[0330] In one embodiment, the terminal may proactively report auxiliary information and no longer participate in the learning task; or the terminal may proactively leave, and if the base station does not obtain the predetermined result, it may select another candidate UE to perform the task.

[0331] In one embodiment, if a high-computing-power terminal joins, the base station can remove a low-computing-power terminal.

[0332] As one embodiment, the wireless resource management node can monitor the execution of the learning task and provide feedback to the second node. In one embodiment, if the calculation results of at least N users cannot be obtained during the execution process, and the task training fails, feedback can be provided to the second node.

[0333] In the embodiments disclosed herein, some or all of the steps and their optional implementations may be arbitrarily combined with some or all of the steps in other embodiments, or may be arbitrarily combined with the optional implementations in other embodiments.

[0334] In the embodiments disclosed herein, some or all of the steps and their optional implementations may be arbitrarily combined with some or all of the steps in other embodiments, or may be arbitrarily combined with the optional implementations in other embodiments.

[0335] This disclosure also provides apparatus for implementing any of the above methods. For example, an apparatus is provided that includes units or modules for implementing the steps performed by the UE in any of the above methods. Alternatively, another apparatus is provided that includes units or modules for implementing the steps performed by a network device (e.g., an access network device, or a core network device) in any of the above methods.

[0336] It should be understood that the division of units or modules in the above device is only a logical functional division. In actual implementation, they can be fully or partially integrated into a single physical entity, or they can be physically separated. Furthermore, the units or modules in the device can be implemented by a processor calling software: for example, the device includes a processor connected to a memory containing instructions. The processor calls the instructions stored in the memory to implement any of the above methods or to implement the functions of the units or modules in the above device. The processor can be, for example, a general-purpose processor, such as a Central Processing Unit (CPU) or a microprocessor, and the memory can be internal or external to the device. Alternatively, the units or modules in the device can be implemented in the form of hardware circuits. The functionality of some or all of the units or modules can be achieved through the design of these hardware circuits, which can be understood as one or more processors. For example, in one implementation, the hardware circuit is an application-specific integrated circuit (ASIC). The functionality of some or all of the units or modules is achieved through the design of the logical relationships between the components within the circuit. In another implementation, the hardware circuit can be implemented using a programmable logic device (PLD). Taking a field-programmable gate array (FPGA) as an example, it can include a large number of logic gates. The connection relationships between the logic gates are configured through configuration files, thereby achieving the functionality of some or all of the units or modules. All units or modules of the above device can be implemented entirely through processor-called software, entirely through hardware circuits, or partially through processor-called software with the remaining parts implemented through hardware circuits.

[0337] In this disclosure, the processor is a circuit with signal processing capabilities. In one implementation, the processor can be a circuit with instruction read and execute capabilities, such as a Central Processing Unit (CPU), a microprocessor, a graphics processing unit (GPU) (which can be understood as a type of microprocessor), or a digital signal processor (DSP). In another implementation, the processor can implement certain functions through the logical relationships of hardware circuits. The logical relationships of the aforementioned hardware circuits are fixed or reconfigurable. For example, the processor is a hardware circuit implemented using an application-specific integrated circuit (ASIC) or a programmable logic device (PLD), such as an FPGA. In a reconfigurable hardware circuit, the process of the processor loading a configuration document and configuring the hardware circuit can be understood as the process of the processor loading instructions to implement the functions of some or all of the above units or modules. Furthermore, it can also be a hardware circuit designed for artificial intelligence, which can be understood as an ASIC, such as a Neural Network Processing Unit (NPU), a Tensor Processing Unit (TPU), or a Deep Learning Processing Unit (DPU). Unit, DPU, etc.

[0338] As shown in Figure 6A, this embodiment of the present disclosure provides a first node, including:

[0339] The receiving module 6101 is configured to receive first information sent by the second node, the first information being related to the terminal performing a first task; the first task being a task related to a first model; the first model being an artificial intelligence (AI) model and / or a machine learning (ML) model.

[0340] In some embodiments, the first node further includes a processing module and / or a sending module.

[0341] In some embodiments, the transmitting module and / or receiving module may correspond to the network interface and / or transceiver antenna of the first node.

[0342] In some embodiments, the processing module can be used by the first node to execute information processing-related steps in any task processing method.

[0343] In some embodiments, the sending module can be used by the first node to execute information sending-related steps in any task processing method.

[0344] In some embodiments, the receiving module can be used by the first node to perform information sending-related steps in any task processing method.

[0345] In some embodiments, the first information includes at least one of the following:

[0346] Task information, used to execute the first task;

[0347] The first indicator information is used to indicate the capability indicators of the first model after training.

[0348] The second indicator information is used to indicate the indicators that the inference results of the first model must meet;

[0349] Model information, used to indicate the first model;

[0350] Terminal information is used by the first node to determine the terminal capable of performing the first task.

[0351] In some embodiments, the task information includes at least one of the following:

[0352] Task identifier, used to identify the first task;

[0353] Task time, used to indicate the start and / or end time of the first task.

[0354] In some embodiments, the terminal information includes at least one of the following:

[0355] Capability information, used to indicate the terminal capabilities possessed by the terminal performing the first task;

[0356] Terminal type, the type of terminal used to perform at least the first task;

[0357] Terminal quantity, used to indicate the number of terminals performing the first task.

[0358] In some embodiments, the sending module is configured to send second information to at least one first terminal based on the first information; the second information is used to cause the at least one first terminal to perform the first task.

[0359] In some embodiments, the sending module is configured to send second information to each of the at least one first terminal according to the first information; or, to send second information to a terminal group according to the first information; wherein the terminal group includes the at least one first terminal.

[0360] In some embodiments, the processing module is configured to determine the first terminal from the second terminal based on third information associated with the second terminal before sending the second information to the at least one first terminal.

[0361] In some embodiments, the third information includes at least one of the following:

[0362] Status information, used to indicate the terminal status of the second terminal;

[0363] Capability information, used to indicate the capabilities of the second terminal;

[0364] Willingness information, used to indicate whether the second terminal is willing to participate in the execution of the first task;

[0365] Location information, used to indicate the geographical location of the second terminal;

[0366] Channel information is used to indicate the current channel state of the second terminal and / or the estimated channel state within a specified time period;

[0367] Mobility information, used to indicate the mobility of the second terminal.

[0368] In some embodiments, the terminal state includes at least one of the following: battery status; computing power status; storage status; and temperature status.

[0369] In some embodiments, the sending module is configured to send fourth information to the second terminal before sending the second information to at least one first terminal;

[0370] The receiving module is configured to receive the third information sent by the second terminal based on the fourth information.

[0371] In some embodiments, the fourth information includes at least one of the following:

[0372] Required information to indicate the terminal capabilities and / or terminal status for performing the first task;

[0373] The query information is used to query the second terminal for information related to the execution of the first task.

[0374] In some embodiments, the sending module is configured to send system information to the second terminal; the system information includes the fourth information.

[0375] In some embodiments, the receiving module is configured to receive the third information sent by the second terminal before determining the first terminal from the second terminal based on the third information associated with the second terminal.

[0376] In some embodiments, the third information is included in the auxiliary information sent by the second terminal.

[0377] In some embodiments, the sending module is configured to send fifth information to the second node; the fifth information is used by the second node to determine the execution information of the first task.

[0378] In some embodiments, if the first task fails to execute or the first task is not started, the fifth information includes the reason for the failure.

[0379] In some embodiments, the failure reason includes at least one of the following:

[0380] Unable to obtain a terminal capable of performing the first task;

[0381] A sufficient number of terminals to execute the first task could not be obtained.

[0382] In some embodiments, the sending module is configured to send a sixth message to at least one third terminal when a first condition is met; the sixth message is used to instruct the third terminal to stop executing the first task; the third terminal is a terminal that is currently executing the first task; and / or, the processing module is configured to determine at least one fourth terminal as a terminal that participates in the execution of the first task midway when the first condition is met.

[0383] In some embodiments, the first condition includes at least one of the following:

[0384] The terminal status of the third terminal does not meet the requirements for performing the first task;

[0385] The terminal status of the fourth terminal changes from not meeting the requirements for performing the first task to meeting the requirements for performing the first task;

[0386] The terminal state of the fourth terminal is more in line with the requirements for performing the first task than the terminal state of the third terminal.

[0387] In some embodiments, the sending module is configured to send an eighth message to the second node before receiving the first message sent by the second node; the eighth message is used to indicate whether the first node supports performing the first task.

[0388] In some embodiments, the sending module is configured to send Broadcast Multicast Service (MBS) information to the at least one first terminal based on the first information; the MBS information includes the first information.

[0389] In some embodiments, the first node includes at least one of the following:

[0390] Wireless resource management node;

[0391] Application server.

[0392] As shown in Figure 6B, this embodiment of the present disclosure provides a second node, wherein the second node includes:

[0393] The sending module 6201 is configured to send first information to the first node; the first information is related to the terminal performing a first task; the first task is a task related to a first model; the first model is an artificial intelligence (AI) model and / or a machine learning (ML) model.

[0394] In some embodiments, the second node may further include a processing module and / or a receiving module.

[0395] In some embodiments, the transmitting module and / or receiving module may correspond to the network interface and / or transceiver antenna of the network node.

[0396] In some embodiments, the processing module can be used by the second node to execute information processing-related steps in any task processing method.

[0397] In some embodiments, the sending module can be used by the second node to execute information sending-related steps in any task processing method.

[0398] In some embodiments, the receiving module can be used by the second node to perform information sending-related steps in any task processing method.

[0399] In some embodiments, the first information includes at least one of the following:

[0400] Task information, used to execute the first task;

[0401] The first indicator information is used to indicate the capability indicators of the first model after training.

[0402] The second indicator information is used to indicate the indicators that the inference results of the first model must meet;

[0403] Model information, used to indicate the first model;

[0404] Terminal information is used by the first node to determine the terminal capable of performing the first task.

[0405] In some embodiments, the task information includes at least one of the following:

[0406] Task identifier, used to identify the first task;

[0407] Task time, used to indicate the start and / or end time of the first task.

[0408] In some embodiments, the terminal information includes at least one of the following:

[0409] Capability information, used to indicate the terminal capabilities possessed by the terminal performing the first task;

[0410] Terminal type, the type of terminal used to perform at least the first task;

[0411] Terminal quantity, used to indicate the number of terminals performing the first task.

[0412] In some embodiments, the receiving module is configured to receive fifth information sent by the first node; the fifth information is used by the second node to determine the execution information of the first task.

[0413] In some embodiments, if the first task fails to execute or the first task is not started, the fifth information includes the reason for the failure.

[0414] In some embodiments, the failure reason includes at least one of the following:

[0415] Unable to obtain a terminal capable of performing the first task;

[0416] A sufficient number of terminals to execute the first task could not be obtained.

[0417] In some embodiments, the receiving module is configured to receive eighth information sent by the first node; the eighth information is used to indicate whether the first node supports the execution of the first task.

[0418] As shown in Figure 6C, this embodiment of the present disclosure provides a terminal, including:

[0419] The receiving module 6301 is configured to receive second information sent by the first node; the second information is used to cause the terminal to perform a first task; the first task is to train a first model; the first model is an artificial intelligence (AI) model and / or a machine learning (ML) model.

[0420] In some embodiments, the terminal may further include a processing module and / or a sending module.

[0421] In some embodiments, the transmitting module and / or receiving module may correspond to the network interface and / or transceiver antenna of the network node.

[0422] In some embodiments, the processing module can be used by the terminal to execute information processing-related steps in any task processing method.

[0423] In some embodiments, the sending module can be used by the terminal to execute information sending-related steps in any task processing method.

[0424] In some embodiments, the receiving module can be used by the terminal to perform information sending-related steps in any task processing method.

[0425] In some embodiments, the sending module is configured to send third information to the first node before receiving second information sent by the first node; the third information is used by the first node to determine the terminal performing the first task.

[0426] In some embodiments, the receiving module is configured to receive fourth information sent by the first node before sending the third information to the first node; the fourth information is used by the terminal to send the third information to the first node.

[0427] In some embodiments, the fourth information includes at least one of the following:

[0428] Required information to indicate the terminal capabilities and / or terminal status for performing the first task;

[0429] The query information is used to query the terminal for information related to the execution of the first task.

[0430] In some embodiments, the sending module is configured to send auxiliary information containing the third information to the first node.

[0431] In some embodiments, the receiving module is configured to receive a sixth message sent by the first node; the sixth message is used to instruct the terminal that is performing the first task to stop performing the first task.

[0432] In some embodiments, the receiving module is configured to receive the second information sent by the first node when a first condition is met.

[0433] In some embodiments, the first condition includes at least one of the following:

[0434] The terminal status of the third terminal does not meet the requirements for executing the first task; the third terminal is the terminal that is currently executing the first task.

[0435] The terminal status of the fourth terminal changes from not meeting the requirements for executing the first task to meeting the requirements for executing the first task; the fourth terminal is a terminal that has not yet started executing the first task;

[0436] The terminal state of the fourth terminal is more in line with the requirements for performing the first task than the terminal state of the third terminal.

[0437] This disclosure also provides a communication device, which may include one or more processors; wherein the processors are configured to invoke instructions to cause the communication device to execute a task processing method that can be implemented in any of the foregoing embodiments.

[0438] In some embodiments, as shown in FIG7A and / or FIG7B, the communication device 8100 further includes one or more memories 8102 for storing instructions. Optionally, all or part of the memories 8102 may also be located outside the communication device 8100.

[0439] The communication device may be the aforementioned UE or network device. In some embodiments, the network device may be a primary node and / or a secondary node.

[0440] In some embodiments, the communication device 8100 further includes one or more transceivers 8103. When the communication device 8100 includes one or more transceivers 8103, the communication steps such as sending and receiving in the above method are performed by the transceivers 8103, and other steps are performed by the processor 8101.

[0441] In some embodiments, a transceiver may include a receiver and a transmitter, which may be separate or integrated. Optionally, the terms transceiver, transceiver unit, transceiver, transceiver circuit, etc., may be used interchangeably; the terms transmitter, transmitting unit, transmitter, transmitting circuit, etc., may be used interchangeably; and the terms receiver, receiving unit, receiver, receiving circuit, etc., may be used interchangeably.

[0442] Optionally, the communication device 8100 further includes one or more interface circuits 8104, which are connected to the memory 8102. The interface circuits 8104 can be used to receive signals from the memory 8102 or other devices, and can be used to send signals to the memory 8102 or other devices. For example, the interface circuits 8104 can read instructions stored in the memory 8102 and send the instructions to the processor 8101.

[0443] The communication device 8100 described in the above embodiments may be a network device or a UE, but the scope of the communication device 8100 described in this disclosure is not limited thereto, and the structure of the communication device 8100 may not be limited by FIG. 7A. The communication device may be a standalone device or a part of a larger device. For example, the communication device may be: (1) a standalone integrated circuit IC, or chip, or chip system or subsystem; (2) a collection of one or more ICs, optionally, the IC collection may also include storage components for storing data and programs; (3) an ASIC, such as a modem; (4) a module that can be embedded in other devices; (5) a receiver, UE device, smart UE device, cellular phone, wireless device, handheld device, mobile unit, vehicle device, network device, cloud device, artificial intelligence device, etc.; (6) others, etc.

[0444] Figure 7B is a schematic diagram of the structure of chip 8200 provided in an embodiment of this disclosure. For cases where the communication device 8100 can be a chip or a chip system, please refer to the schematic diagram of chip 8200 shown in Figure 7B, but it is not limited thereto.

[0445] Chip 8200 includes one or more processors 8201, which are used to invoke instructions to cause chip 8200 to execute any of the above task processing methods.

[0446] In some embodiments, chip 8200 further includes one or more interface circuits 8202 connected to memory 8203. Interface circuits 8202 can be used to receive signals from memory 8203 or other devices, and can also be used to send signals to memory 8203 or other devices. For example, interface circuit 8202 can read instructions stored in memory 8203 and send those instructions to processor 8201. Optionally, terms such as interface circuit, interface, transceiver pin, and transceiver can be used interchangeably.

[0447] In some embodiments, chip 8200 further includes one or more memories 8203 for storing instructions. Optionally, all or part of the memories 8203 may be located outside of chip 8200.

[0448] This disclosure also provides a storage medium storing instructions that, when executed on a communication device 8100, cause the communication device 8100 to perform any of the methods described above. Optionally, the storage medium is an electronic storage medium. Optionally, the storage medium is a computer-readable storage medium, but it can also be a storage medium readable by other devices. Optionally, the storage medium can be a non-transitory storage medium, but it can also be a temporary storage medium.

[0449] This disclosure also provides a program product, which, when executed by a communication device 8100, causes the communication device 8100 to perform any of the above task processing methods. Optionally, the program product is a computer program product.

[0450] This disclosure also provides a computer program that, when run on a computer, causes the computer to perform any of the above task processing methods.

[0451] 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 disclosure is intended to cover any variations, uses, or adaptations of the embodiments of this disclosure that follow the general principles of the embodiments of this disclosure and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of the embodiments of this disclosure are indicated by the following claims.

[0452] It should be understood that the embodiments disclosed herein are 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 their scope. The scope of the embodiments disclosed herein is limited only by the appended claims.

Claims

1. A task processing method, wherein, Executed by the first node, the method includes: The terminal receives first information sent by the second node, the first information being related to the execution of a first task; the first task is a task related to a first model; the first model is an artificial intelligence (AI) model and / or a machine learning (ML) model.

2. The method according to claim 1, wherein, The first information includes at least one of the following: Task information, used to execute the first task; The first indicator information is used to indicate the capability indicators of the first model after training. The second indicator information is used to indicate the indicators that the inference results of the first model must meet; Model information, used to indicate the first model; Terminal information is used by the first node to determine the terminal capable of performing the first task.

3. The method according to claim 2, wherein, The task information includes at least one of the following: Task identifier, used to identify the first task; Task time, used to indicate the start and / or end time of the first task.

4. The method according to claim 2 or 3, wherein, The terminal information includes at least one of the following: Capability information, used to indicate the terminal capabilities possessed by the terminal performing the first task; Terminal type, the type of terminal used to perform at least the first task; Terminal quantity, used to indicate the number of terminals performing the first task.

5. The method according to any one of claims 1 to 4, wherein, The method further includes: Based on the first information, second information is sent to at least one first terminal; the second information is used to cause the at least one first terminal to perform the first task.

6. The method according to any one of claims 1 to 5, wherein, The step of sending second information to at least one terminal based on the first information includes: Based on the first information, send the second information to each of the at least one first terminal; or... Based on the first information, second information is sent to the terminal group; the terminal group includes the at least one first terminal.

7. The method according to any one of claims 1 to 6, wherein, Before sending the second information to the at least one first terminal, the method further includes: determining the at least one first terminal from the second terminal based on third information associated with the second terminal.

8. The method according to claim 7, wherein, The third information includes at least one of the following: Status information, used to indicate the terminal status of the second terminal; Capability information, used to indicate the capabilities of the second terminal; Willingness information, used to indicate whether the second terminal is willing to participate in the execution of the first task; Location information, used to indicate the geographical location of the second terminal; Channel information is used to indicate the current channel state of the second terminal and / or the estimated channel state within a specified time period; Mobility information, used to indicate the mobility of the second terminal.

9. The method according to claim 8, wherein, The terminal status includes at least one of the following: Battery status; Computing power status; Storage status; Temperature status.

10. The method according to claim 8, wherein, Before sending the second information to at least one first terminal, the method further includes: Send the fourth message to the second terminal; Receive the third information sent by the second terminal based on the fourth information.

11. The method according to claim 10, wherein, The fourth information includes at least one of the following: Required information to indicate the terminal capabilities and / or terminal status for performing the first task; The query information is used to query the second terminal for information related to the execution of the first task.

12. The method according to claim 10 or 11, wherein, Sending the fourth information to the second terminal includes: sending system information to the second terminal; the system information includes the fourth information.

13. The method according to claim 7, wherein, Before determining the first terminal from the second terminal based on the third information associated with the second terminal, the method further includes: receiving the third information sent by the second terminal.

14. The method according to any one of claims 9 to 13, wherein, The third information is included in the auxiliary information sent by the second terminal.

15. The method according to any one of claims 6 to 14, wherein, The method further includes: Send a fifth message to the second node; the fifth message is used by the second node to determine the execution information of the first task.

16. The method according to claim 15, wherein, If the first task fails to execute or the first task is not started, the fifth information includes the reason for the failure.

17. The method according to claim 16, wherein, The reasons for the failure include at least one of the following: Unable to obtain a terminal capable of performing the first task; A sufficient number of terminals to execute the first task could not be obtained.

18. The method according to any one of claims 1 to 17, wherein, The method further includes at least one of the following: When the first condition is met, a sixth message is sent to at least one third terminal; the sixth message is used to instruct the third terminal to stop executing the first task; the third terminal is a terminal that is currently executing the first task. And / or, When the first condition is met, at least one fourth terminal is identified as a terminal that participates in the execution of the first task midway.

19. The method according to claim 18, wherein, The first condition includes at least one of the following: The terminal status of the third terminal does not meet the requirements for performing the first task; The terminal status of the fourth terminal changes from not meeting the requirements for performing the first task to meeting the requirements for performing the first task; The terminal state of the fourth terminal is more in line with the requirements for performing the first task than the terminal state of the third terminal.

20. The method according to any one of claims 1 to 19, wherein, Before receiving the first information sent by the second node, the method further includes: Send an eighth message to the second node; the eighth message is used to indicate whether the first node supports executing the first task.

21. The method according to any one of claims 1 to 20, wherein, The step of sending second information to at least one first terminal based on the first information includes: Based on the first information, broadcast multicast service (MBS) information is sent to the at least one first terminal; the MBS information includes the first information.

22. The method according to any one of claims 1 to 21, wherein, The first node includes at least one of the following: Wireless resource management node; Application server.

23. A task processing method, wherein, Executed by the second node, the method includes: Send first information to the first node; the first information is related to the terminal executing a first task; the first task is a task related to a first model; the first model is an artificial intelligence (AI) model and / or a machine learning (ML) model.

24. The method according to claim 23, wherein, The first information includes at least one of the following: Task information, used to execute the first task; The first indicator information is used to indicate the capability indicators of the first model after training. The second indicator information is used to indicate the indicators that the inference results of the first model must meet; Model information, used to indicate the first model; Terminal information is used by the first node to determine the terminal capable of performing the first task.

25. The method according to claim 24, wherein, The task information includes at least one of the following: Task identifier, used to identify the first task; Task time, used to indicate the start and / or end time of the first task.

26. The method according to claim 24 or 25, wherein, The terminal information includes at least one of the following: Capability information, used to indicate the terminal capabilities possessed by the terminal performing the first task; Terminal type, the type of terminal used to perform at least the first task; Terminal quantity, used to indicate the number of terminals performing the first task.

27. The method according to any one of claims 23 to 26, wherein, The method further includes: The second node receives the fifth information sent by the first node; the fifth information is used by the second node to determine the execution information of the first task.

28. The method according to claim 27, wherein, If the first task fails to execute or the first task is not started, the fifth information includes the reason for the failure.

29. The method according to claim 28, wherein, The reasons for the failure include at least one of the following: Unable to obtain a terminal capable of performing the first task; A sufficient number of terminals to execute the first task could not be obtained.

30. The method according to any one of claims 23 to 29, wherein, The method further includes: The system receives an eighth message sent by the first node; the eighth message is used to indicate whether the first node supports executing the first task.

31. A task processing method, wherein, The method, executed by a terminal, includes: The terminal receives second information sent by the first node; the second information is used to cause the terminal to perform a first task; the first task is to train a first model; the first model is an artificial intelligence (AI) model and / or a machine learning (ML) model.

32. The method according to claim 31, wherein, Before receiving the second information sent by the first node, the method further includes: sending third information to the first node; the third information is used by the first node to determine the terminal performing the first task.

33. The method according to claim 32, wherein, Before sending the third information to the first node, the method further includes: The terminal receives the fourth information sent by the first node; the fourth information is used by the terminal to send the third information to the first node.

34. The method according to claim 33, wherein, The fourth information includes at least one of the following: Required information to indicate the terminal capabilities and / or terminal status for performing the first task; The query information is used to query the terminal for information related to the execution of the first task.

35. The method according to claim 34, wherein, Sending the third information to the first node includes: Send auxiliary information containing the third information to the first node.

36. The method according to claim 35, wherein, The method further includes: The sixth message sent by the first node is received; the sixth message is used to instruct the terminal that is performing the first task to stop performing the first task.

37. The method according to any one of claims 31 to 36, wherein, The step of receiving the second information sent by the first node further includes: receiving the second information sent by the first node when the first condition is met.

38. The method according to claim 37, wherein, The first condition includes at least one of the following: The terminal status of the third terminal does not meet the requirements for executing the first task; the third terminal is the terminal that is currently executing the first task. The terminal status of the fourth terminal changes from not meeting the requirements for executing the first task to meeting the requirements for executing the first task; the fourth terminal is a terminal that has not yet started executing the first task; The terminal state of the fourth terminal is more in line with the requirements for performing the first task than the terminal state of the third terminal.

39. A first node, wherein, The first node includes: The receiving module is configured to receive first information sent by the second node, the first information being related to the terminal performing a first task; the first task being a task related to a first model; the first model being an artificial intelligence (AI) model and / or a machine learning (ML) model.

40. A second node, wherein, The second node includes: The sending module is configured to send first information to the first node; the first information is related to the terminal performing a first task; the first task is a task related to a first model; the first model is an artificial intelligence (AI) model and / or a machine learning (ML) model.

41. A terminal, wherein, The terminal includes: a receiving module configured to receive second information sent by a first node; the second information is used to cause the terminal to perform a first task; the first task is a task of training a first model; the first model is an artificial intelligence (AI) model and / or a machine learning (ML) model.

42. A communication system, wherein, The communication system includes a first node, a second node, and a terminal; The first node is used to perform the method according to any one of claims 1 to 22; The second node is used to perform the method according to any one of claims 23 to 30; The terminal is used to perform the method according to any one of claims 31 to 38.

43. A communication device, wherein, The communication device includes: One or more processors; The processor is configured to invoke instructions to cause the communication device to execute the task processing method according to any one of claims 1 to 22, 23 to 30, or 31 to 38.

44. A storage medium, wherein, The storage medium stores instructions that, when executed on a communication device, cause the communication device to perform the task processing method according to any one of claims 1 to 22, 23 to 30, or 31 to 38.

45. A program product, wherein, The program product includes a computer program that, when executed by a communication device, enables the communication device to implement any one of 1 to 22, 23 to 30, or 31 to 38.

Images