Communication method and device, electronic device and computer readable storage medium

Abstract

The present disclosure provides a communication method and device, an electronic device, and a computer-readable storage medium. The communication method includes: sending first information, wherein the first information is used to enable a terminal to determine whether to initiate an artificial intelligence or machine learning operation type service. The technical solution provided by the present disclosure can notify the terminal of network-related information as early as possible to reasonably limit or allow the terminal to initiate AI / ML operation type services.

Description

Technical Field

[0001] The present disclosure relates to the field of communication technology, and in particular, to a communication method, a communication device, an electronic device, and a computer-readable storage medium. Background Art

[0002] With the continuous expansion and deepening of the fifth generation mobile communication technology (5G), it is expected to achieve a deep integration of mobile applications and networks based on artificial intelligence (AI) / machine learning (ML).

[0003] Mobile applications based on AI / ML are becoming increasingly computationally intensive, memory intensive, and power intensive. At the same time, terminals usually have strict energy consumption, computing, and memory cost constraints. Therefore, it is usually necessary to separate AI / ML operation-type services on the terminal and the network. However, for some nodes on the network side (for example, base stations), due to their limited resources, they are sometimes unable to process AI / ML operation-type services initiated by the terminal (for example, AI / ML model training operations), and can only initiate conventional services (for example, call services). It can be seen that the existing communication methods for AI / ML operation-type services still need to be improved. Summary of the invention

[0004] In order to solve at least one of the above problems, the present disclosure provides a communication method and device, an electronic device, and a computer-readable storage medium.

[0005] On the one hand, the present disclosure provides a communication method, comprising: sending first information, wherein the first information is used to enable a terminal to determine to initiate an artificial intelligence or machine learning operation type of service.

[0006] According to an embodiment of the present disclosure, the first information is used to enable the access layer of the terminal to determine a service of initiating an artificial intelligence or machine learning operation type.

[0007] According to an embodiment of the present disclosure, the first information includes at least one of the following: information related to network node capabilities; network comprehensive capability indication information; information related to terminal capabilities; direct indication information for indicating the initiation of an artificial intelligence or machine learning operation type of service.

[0008] According to an embodiment of the present disclosure, the information related to the network node capability includes: at least one item of network node capability indication information.

[0009] According to an embodiment of the present disclosure, the network comprehensive capability indication information is information obtained by comprehensively considering the at least one item of network node capability indication information.

[0010] According to an embodiment of the present disclosure, the information related to the network node capability further includes: a threshold corresponding to each item of the at least one item of network node capability indication information.

[0011] According to an embodiment of the present disclosure, the network comprehensive capability indication information further includes: a threshold corresponding to the network comprehensive capability.

[0012] According to an embodiment of the present disclosure, the information related to the terminal capability includes: a threshold corresponding to each item of the at least one item of the terminal capability information.

[0013] According to an embodiment of the present disclosure, sending the first information includes: sending the first message through at least one of main information, remaining minimum system message or other system messages.

[0014] According to an embodiment of the present disclosure, the communication method may further include: when sending the first message via other system messages, in response to a change in at least one item of information included in the first information, not changing a system message value tag in the system message.

[0015] On the other hand, the present disclosure provides a communication method, comprising: obtaining first information; and determining a business of initiating an artificial intelligence or machine learning operation type based on the first information.

[0016] According to an embodiment of the present disclosure, the obtaining and the determining are performed by an access layer of the terminal, wherein the communication method further comprises: notifying a non-access layer of the terminal of a result of the determination.

[0017] According to an embodiment of the present disclosure, determining to initiate a service of an artificial intelligence or machine learning operation type based on the first information includes at least one of the following:

[0018] In response to a result of comparing at least one item of the information related to the network node capability with a corresponding threshold, determining to initiate a service of an artificial intelligence or machine learning operation type;

[0019] In response to a result of comparing the network comprehensive capability indication information with a corresponding threshold, determining to initiate a service of an artificial intelligence or machine learning operation type;

[0020] In response to a result of comparing at least one item of the information related to the terminal capability with a corresponding threshold, determining to initiate a service of an artificial intelligence or machine learning operation type;

[0021] In response to the direct indication information, a business of initiating an artificial intelligence or machine learning operation type is directly determined.

[0022] According to an embodiment of the present disclosure, the communication method may further include: estimating resources required for a business of an artificial intelligence or machine learning operation type to be initiated. Determining to initiate a business of an artificial intelligence or machine learning operation type based on the first information includes: determining to initiate a business of an artificial intelligence or machine learning operation type based on the estimated resources and / or the first information.

[0023] In still another aspect, the present disclosure provides a communication device, comprising: a communication module, configured to: send first information, wherein the first information is used to enable a terminal to determine to initiate an artificial intelligence or machine learning operation type of service.

[0024] In another aspect, the present disclosure provides a communication device, comprising: a communication module configured to obtain first information; and a processing module configured to determine a business of initiating an artificial intelligence or machine learning operation type based on the first information.

[0025] The present disclosure also provides an electronic device, which includes a memory and a processor; the memory stores a computer program; and the processor is used to execute the method described above when running the computer program.

[0026] The present disclosure also provides a computer-readable storage medium, wherein the storage medium stores a computer program, and when the computer program is executed by a processor, the computer program is used to execute the method described above.

[0027] The beneficial effects brought about by the technical solution provided by the embodiments of the present disclosure will be described in detail in the following specific implementation description in conjunction with specific optional embodiments, and will not be elaborated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] In order to more clearly illustrate the technical solutions in the embodiments of the present disclosure, the drawings required for describing the embodiments of the present disclosure are briefly introduced below.

[0029] Figure 1 A schematic diagram of an architecture of a communication system;

[0030] Figure 2 A flow chart of a communication method provided in an embodiment of the present disclosure;

[0031] Figure 3 A schematic diagram of a communication device provided in an embodiment of the present disclosure;

[0032] Figure 4 A schematic diagram of another communication device provided in an embodiment of the present disclosure;

[0033] Figure 5 A schematic diagram of the structure of an electronic device provided by the present invention. DETAILED DESCRIPTION

[0034] Embodiments of the present disclosure are described in detail below, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present disclosure, and cannot be interpreted as limiting the present disclosure.

[0035] It will be understood by those skilled in the art that, unless expressly stated, the singular forms "one", "said", and "the" used herein may also include plural forms. It should be further understood that the term "comprising" used in the specification of the present disclosure refers to the presence of the features, integers, steps, operations, elements, and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof. It should be understood that when we refer to an element as being "connected" or "coupled" to another element, it may be directly connected or coupled to the other element, or there may be intermediate elements. In addition, the "connection" or "coupling" used herein may include wireless connection or wireless coupling. The term "and / or" used herein includes all or any unit and all combinations of one or more associated listed items.

[0036] Unless otherwise defined, all terms used herein (including technical terms and scientific terms) have the same meaning as the general understanding of those of ordinary skill in the field to which the present disclosure belongs. It will be understood that although the terms "first", "second", etc. can be used to describe various elements in this article, these elements should not be limited by these terms. These terms are only used to distinguish one element from another element. Therefore, without departing from the teaching of the exemplary embodiment, the first element discussed below can be referred to as the second element.

[0037] In order to make the objectives, technical solutions and advantages of the embodiments of the present disclosure more clear, the embodiments of the present disclosure will be further described in detail below with reference to the accompanying drawings.

[0038] Figure 1 A schematic diagram of the architecture of a communication system 100 applicable to an embodiment of the present disclosure.

[0039] Reference Figure 1 , the communication system 100 may include a base station 110 and a terminal 120. The terminal 120 is located in a cell covered by the base station 110 and can communicate with the base station 110. Figure 1Only one base station 110, one terminal 120, and three cells covered by the base station 110 are shown, but this is only exemplary and the exemplary embodiments of the present disclosure are not limited thereto. For example, the communication system 100 may also include multiple base stations, multiple terminals located in each cell, and / or access points, etc.

[0040] As examples, the terminal may include, but is not limited to, cellular phones, smart phones, wearable devices, computers, personal digital assistants (PDAs), personal communication system (PCS) devices, personal information managers (PIMs), personal navigation devices (PNDs), global positioning systems, multimedia devices, Internet of Things (IoT) devices, etc.

[0041] In order to split the AI / ML operation type business on the terminal and the network (e.g., base station 110), for example, the computationally intensive and energy-intensive parts of AI / ML can be offloaded to the network node, while the privacy-sensitive and delay-sensitive parts are left on the terminal. The terminal can execute a specific part / layer in the operation / model and send the intermediate data to the network node. The network node executes the remaining part / layer and feeds the inference result back to the terminal.

[0042] The key to splitting AI / ML operation-type services is to select the best split mode and split point to ensure that the required resources are lower than the upper limit of available resources on the terminal and optimize computing, storage / memory, power consumption, and communication resources on the terminal and network sides.

[0043] For different split modes, the resource requirements for uplink and downlink are very different. In one embodiment, for the training mode of AI / ML operation in the local area, because it involves the download of AI / ML model, a large amount of downlink bandwidth is required; for the mode of AI / ML operation training in the cloud of the network, because it involves the upload of training data, a large amount of uplink bandwidth is required, and for the downlink, only the result of inference after training is returned, no large downlink bandwidth is required; in addition, for the mode of local training and cloud training at the same time, both uplink and downlink require large bandwidth. Therefore, when a user (for example, the user's terminal 120) initiates a model training application, the bandwidth required may be as high as 20 Gbps (gigabits per second) and requires a large amount of computing power resources. From the perspective of network resource allocation, it corresponds to the allocation of a large amount of bandwidth, as well as the allocation of network computing power resources (memory, processor), etc. Therefore, for some base stations, due to their limited resources, they are sometimes unable to process AI / ML operation type services initiated by the terminal (for example, model training operations), and can only initiate conventional services (for example, call services). Therefore, it is necessary to notify the terminal network of computing power as soon as possible. To this end, the embodiment of the present disclosure proposes a mechanism for notifying the terminal of relevant information in a system message to restrict the terminal from initiating AI / ML operation type services.

[0044] Figure 2 A flow chart of a communication method according to an embodiment of the present disclosure is shown.

[0045] Reference Figure 2 , in step S110, the first information may be sent. Specifically, the base station may send (or notify) the first information to the terminal, however, this is only exemplary, and the embodiments of the present disclosure are not limited thereto. For example, the first information may also be sent through other devices (e.g., access points or any type of controller, etc.). The first information is used to enable the terminal to determine whether to initiate an AI / ML operation type service. According to an embodiment, the first message is used to enable the access (AS, Access Stratum) layer or the non-access (NAS, Non Access Stratum) layer of the terminal to determine whether to initiate an AI / ML operation type service. Preferably, the first message is used to enable the AS layer of the terminal to determine whether to initiate an AI / ML operation type service.

[0046] The specific manner in which the base station sends the first message to the terminal is not limited in the embodiment of the present disclosure. For example, the first message may be sent to the terminal via a system message or other agreed manners.

[0047] According to an embodiment, the first information may include at least one of the following: information related to network node capabilities; network comprehensive capability indication information; information related to terminal capabilities; direct indication information for indicating whether to initiate an artificial intelligence or machine learning operation type of service. In the following description, the direct indication information for indicating whether to initiate an artificial intelligence or machine learning operation type of service may be referred to as "direct indication information", and information other than the "direct indication information" may be referred to as "auxiliary information".

[0048] According to an embodiment of the present disclosure, the information related to the network node capability in the first information may include: at least one network node capability indication information. As an example, the at least one network node capability indication information may include at least one of the following: computing capability indication information, wireless resource capability indication information, and backward link bandwidth indication information. According to an embodiment, the at least one network node capability indication information may be a resource that a network node (e.g., a base station) can provide to a service of the AI / ML operation type (e.g., a resource provided for use in AI / ML model training), or it may be a resource that the network node has already occupied.

[0049] As a non-limiting example only, the computing capability indication information may include the occupancy of at least one of the memory, CPU, and storage space of the network node (which may be indicated in the form of a percentage or a high, medium, and low) or the current load of the network; the wireless resource capability indication information may include the bandwidth provided by the network node, the current spectrum utilization rate, etc., which may also be indicated in the form of a percentage or a high, medium, and low; the backward link bandwidth indication information may include the bandwidth of the interface link between the base station and the core network element, or the bandwidth of the interface link between the base station and a dedicated server providing AI / ML services.

[0050] It should be noted that the example of at least one network node capability indication information is not limited to the above embodiments. For example, at least one network node capability indication information may also include the number of operations broadcasted by the network node that it can support, such as the number of addition and multiplication operations.

[0051] Optionally, the information related to the network node capability in the first information may also include: a threshold corresponding to each network node capability indication information in at least one network node capability indication information. When at least one network node capability indication information is an available resource that a network node (e.g., a base station) can provide to an AI / ML operation type service (e.g., a resource provided for AI / ML model training), the threshold may be a threshold corresponding to the available resources. When at least one network node capability indication information is a resource that the network node has already occupied, the threshold may be a threshold corresponding to the resource that has already been occupied. However, the present invention is not limited to this. For example, when at least one network node capability indication information is a resource that the network node has already occupied, the threshold may be a threshold corresponding to the available resources. In this case, the terminal (e.g., AS layer) may first infer the threshold corresponding to the occupied resource based on the threshold corresponding to the available resource, and then determine whether the AI / ML operation type service can be initiated based on at least one network node capability indication information and the inferred threshold.

[0052] For example, in the case where at least one network node capability indication information includes computing capability indication information, radio resource capability indication information and / or backward link bandwidth indication information, the information related to the network node capability may also include: computing capability decision threshold, radio resource capability decision threshold and / or backward link bandwidth decision threshold. These threshold information are used to enable the terminal (e.g., the AS layer of the terminal) to compare the various network node capability indication information in the first information with the corresponding threshold to determine whether to initiate an AI / ML operation type service. This will be described in detail later in the decision step performed by the terminal (e.g., the AS layer of the terminal).

[0053] According to an embodiment of the present disclosure, the network comprehensive capability indication information in the first information is information obtained by comprehensively considering at least one of the above-mentioned network node capability indication information. For example, the base station can obtain the network comprehensive capability indication information by comprehensively evaluating the computing capability, wireless resource capability and backward link bandwidth of the network node, for example, the network comprehensive capability indication information can be represented by the signal load. As an example, the signal load can refer to the signal load currently carried by the network node or the remaining signal load of the network node.

[0054] Optionally, the network comprehensive capability indication information in the first information may further include: a threshold corresponding to the network comprehensive capability. For example, when the network comprehensive capability indication information is represented by the signal load, the network comprehensive capability indication information may further include a threshold corresponding to the signal load. Similarly, the threshold is used to enable the terminal (e.g., the AS layer of the terminal) to compare the network node capability indication information in the first information with the corresponding threshold to determine whether to initiate an AI / ML operation type service.

[0055] As an example, the above-mentioned threshold information (i.e., the threshold corresponding to each item of network node capability indication information in the at least one item of network node capability indication information, and the threshold corresponding to the network comprehensive capability) may be included in the first information, thereby being sent to the terminal through the network node; as another example, these threshold information may not be included in the first information, that is, not sent to the terminal through the network node, but may be pre-stored in the terminal or other devices connected to the terminal, and the pre-stored or solidified threshold information may be directly used when the terminal needs to make a decision; as another example, the terminal may pre-acquire the threshold information before receiving the first information; in addition, the network node may also send the threshold information periodically or when necessary to update the pre-stored threshold information.

[0056] According to an embodiment of the present disclosure, the information related to the terminal capability in the first information may include: a threshold corresponding to each terminal capability information of at least one terminal capability information. The at least one terminal capability information may include at least one of the following: terminal computing capability information, terminal power information.

[0057] As a non-limiting embodiment, the network node (e.g., a base station) needs to require that the terminal capability reaches a specific threshold before allowing the terminal to initiate AI / ML operation type services. For example, the network node may specify in the information related to the terminal capability: the threshold that the terminal's current computing power margin needs to reach (e.g., the occupancy of at least one of the terminal's memory, CPU, and storage space indicated in percentage form), the threshold that the terminal's current power margin needs to reach (which may be in percentage form), and / or the terminal needs to be in a charging state when the terminal power is lower than the required threshold, etc.

[0058] According to an embodiment, the first message may be sent via at least one of master information, remaining minimum system information (RMSI), or other system information (SI).

[0059] As a non-limiting embodiment, the base station can notify the terminal of the auxiliary information in the first message (i.e., information related to network node capabilities, network comprehensive capability indication information, and information related to terminal capabilities) in RMSI or other SI; and, the base station can notify the terminal of the direct indication information in the first message through main information (e.g., master information block MIB (Master Information Block)), RMSI or other system messages (e.g., system message block SIB (System Information Block)).

[0060] In one embodiment, the base station may use an indication bit (one or more bits) in a system message to send direct indication information to directly inform the terminal whether a service of the AI / ML operation type can be initiated. For example, the indication bit may be carried in the MIB; for another example, the indication bit may be carried in the RMSI or other SIBs.

[0061] According to an embodiment, Figure 2 The communication method shown in may also include: when sending the first message through other system messages (i.e., other system messages except MIB and RMSI), in response to a change in at least one item of information included in the first information, the system message value tag (SI value tag) in the system message is not changed.

[0062] If the SI value tag changes, the base station needs to page the terminal by sending a paging message (paging), and accordingly, the terminal needs to listen to the paging to obtain changes in the system message. According to an embodiment of the present disclosure, even if at least one item of information included in the first information changes, the SI value tag is not changed, so that the base station does not need to page the terminal, but the terminal listens to the system message by itself before initiating an AI / ML operation type service (i.e., initiating AI / ML access) to obtain and / or update the first message, thereby saving resources. In other words, the base station does not need to occupy resources to send paging messages, and the terminal does not need to frequently receive or parse the SI value tag, thereby saving power, transmission and / or computing resources.

[0063] According to an embodiment of the present disclosure, a network node (eg, a base station) may send different first information for services of different AI / ML operation types.

[0064] As an example, the network node may send multiple pieces of information in the first information and / or specify indication rules for valid information in the first information to the terminal according to the AI / ML operation type services that it can support, and the terminal may determine the valid information in the multiple pieces of information according to the indication rules, and determine whether to initiate AI / ML operation type services according to the valid information. As a non-limiting example, the multiple pieces of information may indicate information related to network node capabilities (e.g., at least one network node capability indication information and / or a corresponding threshold), network comprehensive capability indication information, information related to terminal capability information (e.g., a threshold corresponding to each item of at least one terminal capability information) and / or direct indication information.

[0065] It is understandable that the indication rule may not be sent through the network node, but may be pre-written or stored in the terminal or a device connected to the terminal, or may be agreed upon through a protocol. For example, the network node may only send multiple pieces of information (e.g., computing capability indication information, wireless resource capability indication information, backward link bandwidth indication information and its corresponding threshold) and indication rules specifying computing capability indication information and wireless resource capability indication information as valid information to the terminal. In this case, although the terminal receives multiple pieces of information, it only uses the computing capability indication information and wireless resource capability indication information and the corresponding threshold to determine whether to initiate an AI / ML operation type service according to the indication rule obtained locally.

[0066] As another example, the network node may predetermine which information is valid based on the AI / ML operation type services that it can support, and thus only send valid information to the terminal. For example, the network node may predetermine that the threshold of the radio resource capability indication information and / or the terminal power information is valid information, and thus only send the threshold of the radio resource capability indication information and / or the terminal power information to the terminal, so that the terminal uses them to determine whether to initiate the AI / ML operation type service.

[0067] As another example, the network node may determine direct indication information by comprehensively considering its capability information (e.g., network node capability indication information), and send the direct indication information to the terminal so that the terminal can directly determine whether to initiate an AI / ML operation type service based on the direct indication information.

[0068] As another example, the information sent by the network node to the terminal is valid by default, so the terminal can use the received information to determine whether to initiate an AI / ML operation type service.

[0069] Continue to refer to Figure 2 , the terminal may obtain the first information, and determine whether to initiate a service of the AI / ML operation type based on the obtained first information. According to an embodiment, the base station may send the first message to the terminal via a system message, that is, carry the first message in the system message, and the terminal may obtain the system message before the AI / ML service needs to be initiated to obtain the first information from the system message.

[0070] According to the embodiment, the above operation can be performed by the AS layer or NAS layer of the terminal. Preferably, in the embodiment of the present disclosure, the above acquisition and determination operations can be performed by the AS layer of the terminal. Compared with the NAS layer, the AS layer of the terminal allows the base station to have more control over the behavior of the terminal, because the policies are provided by the base station, and the terminal can make decisions according to the provided policies. For the NAS layer, some decision conditions are related to the user (for example, the user's preferences and privacy protection), and its decision is relatively complex.

[0071] When the AS layer of the terminal determines whether to initiate a service of the AI / ML operation type based on the acquired first information, the NAS layer of the terminal may be notified of the result of the determination, so that the NAS layer performs a corresponding operation according to the result of the determination. For example, when the AS layer of the terminal determines that a service of the AI / ML operation type may be initiated based on the acquired first information, in step S120, the NAS layer may execute the initiation of the service of the AI / ML operation type.

[0072] The terminal (e.g., the AS layer) determines whether to initiate an AI / ML operation type service based on the acquired first information, which may include at least one of the following:

[0073] In response to a result of comparing at least one item of information related to network node capabilities with a corresponding threshold, determining whether to initiate an AI / ML operation type service;

[0074] In response to a result of comparing the network comprehensive capability indication information with a corresponding threshold, determining whether to initiate an AI / ML operation type service;

[0075] In response to a result of comparing at least one item of information related to the terminal capability with a corresponding threshold, determining whether to initiate a service of the AI / ML operation type;

[0076] In response to the direct indication information, it is directly determined whether to initiate an AI / ML operation type service.

[0077] Similar to the above, the network node may send different first information for different AI / ML operation type services, and the terminal may make a decision based on the information sent by the network node to determine whether to initiate an AI / ML operation type service. When the terminal receives different first information from the base station, it can determine from the first information which information is valid (similar to that described in step S110), or determine the priority of each piece of information. For example, when the terminal receives direct indication information and other auxiliary information from the base station, the direct indication information can be determined to have the highest priority, thereby giving priority to or only based on the direct indication information to determine whether an AI / ML operation type service can be initiated.

[0078] As an embodiment, the terminal (e.g., the AS layer) may determine whether the computing capability indication information provided by the base station in the first message meets the resource requirements required for initiating AI / ML operation type services (e.g., access to AI / ML model training). If not, it is considered that this type of AI / ML service does not allow access to the cell (or base station). If it is met, the NAS layer is notified that AI / ML operation type services can be initiated. For example, the terminal (e.g., the AS layer) may compare the resources that can be provided by the network node (e.g., the size of the memory, CPU and / or storage space that can be provided) with the corresponding threshold to determine whether the AI / ML operation type service can be initiated by determining whether the resources provided by the network node reach the corresponding threshold. For another example, the terminal (e.g., the AS layer) may determine whether the current network load is lower than the corresponding threshold to determine whether the AI / ML operation type service can be initiated.

[0079] As an embodiment, the terminal (for example, the AS layer) can determine whether the wireless resource capability indication information provided by the base station in the first message meets the resource requirements required for initiating AI / ML operation type services (for example, access to AI / ML model training). If not, it is considered that this type of AI / ML service does not allow access to the cell (or base station). If it is satisfied, the NAS layer is notified that AI / ML operation type services can be initiated. For example, the terminal (for example, the AS layer) can determine whether AI / ML operation type services can be initiated by determining whether the resources provided by the network node (for example, the bandwidth provided by the network node) reach the corresponding threshold, or by determining whether the current frequency utilization of the network is lower than the corresponding threshold.

[0080] As an embodiment, the terminal (for example, the AS layer) can determine whether the backward link bandwidth indication information provided by the base station in the first message meets the resource requirements required for initiating AI / ML operation type services (for example, access to AI / ML model training). If not, it is considered that this type of AI / ML service does not allow access to the cell (or base station). If it is satisfied, the NAS layer is notified that AI / ML operation type services can be initiated. For example, by determining whether the resources provided by the network node (for example, the size of the backward link bandwidth provided by the network node) reaches the corresponding threshold, it is determined whether AI / ML operation type services can be initiated.

[0081] As an embodiment, the terminal (eg, AS layer) may compare the network comprehensive capability indication information (eg, signal carrying capacity) in the first message with the corresponding threshold to determine whether an AI / ML operation type service can be initiated.

[0082] As an embodiment, the terminal (for example, the AS layer) may compare its own computing capability with the corresponding threshold indicated by the terminal computing capability information of the first message, or compare the remaining power of the terminal with the corresponding threshold indicated by the terminal computing capability information to determine whether to initiate an AI / ML operation type service.

[0083] According to an embodiment of the present disclosure, the terminal (e.g., AS layer) may combine one or more of the above embodiments to determine whether an AI / ML operation type service can be initiated. For example, the terminal may determine whether the computing capability information of the base station and the computing capability of the terminal are sufficient to initiate an AI / ML operation type service.

[0084] According to an embodiment, Figure 2 The communication method shown in may also include: estimating the resources required for the AI / ML operation type service to be initiated. In this case, the terminal (e.g., the AS layer) may determine whether to initiate the AI / ML operation type service based on the estimated resources and / or the first information.

[0085] For example, the AS layer of the terminal can estimate the resources required for the AI / ML operation type service to be initiated in advance through historical records or other high-level instructions, or the AS layer of the terminal can be based on historical statistical information and / or user behavior (for example, the user's current communication behavior), thereby obtaining the resource requirements for access to the initiated AI / ML model training. As an example, the historical record may be the recorded information of the resources used when the terminal previously initiated an AI / ML operation type service. Historical statistical information may be information obtained by performing statistical calculations on the recorded information of the resources used when the AI / ML operation type service was previously initiated. Accordingly, the AS layer of the terminal can determine whether the resources provided by the network node meet the resource requirements (i.e., compare the resources provided by the network node with the resource requirements) to determine whether to initiate an AI / ML operation type service.

[0086] For example, the terminal may pre-estimate at least one of the memory, CPU, and storage space required for the AI / ML operation type service to be initiated, and compare the estimated value with the value provided by the network node in the computing capability indication information to determine whether to initiate the AI / ML operation type service.

[0087] For example, the terminal may pre-estimate the number of addition and multiplication operations required for the AI / ML operation type service to be initiated, and compare the estimated number with the number of addition and multiplication operations supported by the network broadcast to determine whether to initiate the AI / ML operation type service.

[0088] For example, the terminal can pre-estimate the bandwidth required for the AI / ML operation type service to be initiated (e.g., estimated bandwidth), and compare the estimated bandwidth with the bandwidth size provided by the network node in the wireless resource indication information to determine whether to initiate the AI / ML operation type service.

[0089] For example, the terminal may pre-estimate the backward bandwidth required for the AI / ML operation type service to be initiated, and compare the required backward bandwidth with the size of the backward link bandwidth provided by the network to determine whether to initiate the AI / ML operation type service.

[0090] According to an embodiment, Figure 2 The communication method shown may also include: in response to determining that traffic initiating AI / ML operation type is not allowed and only traffic initiating AI / ML operation type exists, identifying the cell state as "cell barred".

[0091] In one embodiment, for a terminal that only needs to initiate AI / ML model training access, if the AS layer of the terminal determines that access is not allowed, it means that the cell state is cell bar. In other words, the cell is prohibited for the terminal, and the terminal will initiate cell reselection, that is, the terminal selects another cell to reside. In addition, the terminal can receive system messages in the other cell and try to initiate AI / ML operation type services.

[0092] In one embodiment, for a terminal that needs to initiate access other than just AI / ML model training, if the AS layer judgment result of the terminal is that access is not allowed, the NAS layer is notified that the current cell prohibits AI / ML model access, but other services (for example, call services) can be initiated; if the AS layer judgment result of the terminal is that access is allowed, otherwise the NAS layer is notified that the current cell allows AI / ML model access.

[0093] The above communication method according to the embodiment of the present disclosure can notify the terminal of network-related information as early as possible, so as to reasonably restrict or allow the terminal to initiate AI / ML operation-type services.

[0094] Figure 3 is a schematic diagram showing a communication device 300 according to an embodiment of the present disclosure.

[0095] Reference Figure 3 , the communication device 300 may include a communication module 310. The communication module 310 is configured to: send first information. The first information is used to enable the terminal to determine whether to initiate an artificial intelligence or machine learning operation type of service. The description of the first information is similar to Figure 2In step S110, repeated description is omitted here for brevity.

[0096] According to an embodiment of the present disclosure, the communication module may be a node on the base station side, an access point in a wireless local area network, or other control devices.

[0097] According to an embodiment, the communication module 310 may be configured to send the first message via at least one of master information, remaining minimum system message or other system messages.

[0098] will understand, Figure 3 The structure of the communication device 300 shown in is merely exemplary, and the embodiments of the present disclosure are not limited thereto. For example, the communication device 300 may also include a processing device for processing AI / ML operation-type services, or a device for communicating with a dedicated server that provides AI / ML operation-type services through a core network, etc.

[0099] According to an embodiment, the processing module in the communication device 300 may be configured to, when sending the first message via other system messages, not change the system message value tag in the system message in response to a change in at least one item of information included in the first message.

[0100] The communication device 300 may perform the above-mentioned reference Figure 2 For the sake of brevity, repeated description of the operations in step S110 is omitted here.

[0101] Figure 4 is a schematic diagram showing another communication device 400 according to an embodiment of the present disclosure.

[0102] Reference Figure 4 , the communication device 400 may include a communication module 410 and a processing module 420 .

[0103] According to an embodiment of the present disclosure, the communication module 410 may be configured to obtain the first information. The processing module 420 may be configured to determine whether to initiate a service of the AI / ML operation type based on the first information. According to an embodiment, the communication module 410 and the processing module 420 may be included in the AS layer or NAS layer of the terminal. Preferably, the communication module 410 and the processing module 420 may both be included in the AS layer of the terminal.

[0104] According to an embodiment of the present disclosure, the operation performed by the processing module 420 to determine whether to initiate an artificial intelligence or machine learning operation type service based on the first information may include at least one of the following:

[0105] In response to a result of comparing at least one item of information related to network node capabilities with a corresponding threshold, determining whether to initiate an artificial intelligence or machine learning operation type of service;

[0106] In response to a result of comparing the network comprehensive capability indication information with a corresponding threshold, determining whether to initiate an artificial intelligence or machine learning operation type service;

[0107] In response to a result of comparing at least one item of information related to the terminal capability with a corresponding threshold, determining whether to initiate a service of an artificial intelligence or machine learning operation type;

[0108] In response to the direct indication information, it is directly determined whether to initiate an artificial intelligence or machine learning operation type of business.

[0109] The processing module 420 can perform and refer to Figure 2 The decision operation of the described terminal (eg, AS layer) is similar to the operation, and for the sake of brevity, repeated description is omitted here.

[0110] According to an embodiment of the present disclosure, the processing module 420 can also be configured to: estimate the resources required for the artificial intelligence or machine learning operation type business to be initiated, and determine whether to initiate the artificial intelligence or machine learning operation type business based on the estimated resources and / or the first information.

[0111] According to an embodiment of the present disclosure, the processing module 420 may also be configured to: in response to determining that services that initiate artificial intelligence or machine learning operation types are not allowed and only services that initiate artificial intelligence or machine learning operation types exist, identify the cell status as "cell prohibited".

[0112] will understand, Figure 4 The structure of the communication device 400 shown in is only exemplary, and the embodiments of the present disclosure are not limited thereto. For example, the communication device 400 may also include a NAS layer for receiving a determination result from the AS layer, and when the AS layer determines that access is allowed, the NAS layer may initiate an artificial intelligence or machine learning operation type service. For another example, the communication device 400 may also include a memory for storing various data and information, and / or a sending module for transmitting data required for AI / ML operation type services to a network node, etc.

[0113] It should be noted that, since the device provided in the embodiments of the present disclosure is a device that can execute the corresponding method provided in the embodiments of the present disclosure, based on the method provided in the embodiments of the present disclosure, the technical personnel in the field can understand the specific implementation of the device in the embodiments of the present disclosure and its various variations, so how the device implements the method in the embodiments of the present disclosure is not described in detail here. As long as the technical personnel in the field implement the device used in the method in the embodiments of the present disclosure, it belongs to the scope of protection of the present disclosure. Among them, each module included in the above-mentioned device can be implemented by software and / or hardware.

[0114] The present disclosure also provides an electronic device, which may include at least one processor, and the processor may be configured to execute the method provided in any optional embodiment of the present disclosure.

[0115] Optionally, the electronic device may include at least one memory storing a computer program (or may also be referred to as computer instructions or codes), and the at least one processor may execute the communication method shown in any optional embodiment of the present disclosure when running the computer program.

[0116] The present disclosure further provides a computer-readable storage medium, in which a computer program is stored. When the computer program is executed by a processor, the communication method shown in any optional embodiment of the present disclosure can be executed.

[0117] As a non-limiting example, Figure 5 FIG. 1 shows a schematic diagram of the structure of an electronic device that can be applied to the solution provided by the present disclosure. Figure 5 As shown, the electronic device 5000 includes: a processor 5001 and a memory 5003. The processor 5001 and the memory 5003 are connected, such as through a bus 5002. Optionally, the electronic device 5000 may also include a transceiver 5004. It should be noted that in actual applications, the transceiver 5004 is not limited to one, and the structure of the electronic device 5000 does not constitute a limitation on the embodiments of the present disclosure.

[0118] Processor 5001 may be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array) or other programmable logic devices, transistor logic devices, hardware components or any combination thereof. It may implement or execute various exemplary logic blocks, modules and circuits described in conjunction with the disclosure of the present invention. Processor 5001 may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, etc.

[0119] The bus 5002 may include a path to transmit information between the above components. The bus 5002 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus. The bus 5002 may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 5 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0120] The memory 5003 can be a ROM (Read Only Memory) or other types of static storage devices that can store static information and instructions, a RAM (Random Access Memory) or other types of dynamic storage devices that can store information and instructions, or an EEPROM (Electrically Erasable Programmable Read Only Memory), a CD-ROM (Compact Disc Read Only Memory) or other optical disk storage, optical disk storage (including compressed optical disk, laser disk, optical disk, digital versatile disk, Blu-ray disk, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited to these.

[0121] The memory 5003 is used to store application code (computer program) for executing the solution of the present disclosure, and the execution is controlled by the processor 5001. The processor 5001 is used to execute the application code stored in the memory 5003 to implement the content shown in any of the above method embodiments.

[0122] It should be understood that, although the steps in the flowchart of the accompanying drawings are displayed in sequence as indicated by the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least a part of the steps in the flowchart of the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a part of the sub-steps or stages of other steps.

[0123] The above description is only a partial implementation mode of the present disclosure. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present disclosure. These improvements and modifications should also be regarded as the protection scope of the present disclosure.

Claims

1. A communication method, performed by a network node, the communication method comprising: Sending first information via a system message, wherein the first information is used to enable the terminal to determine to initiate a service of an artificial intelligence or machine learning operation type, wherein in response to a change in at least one item of information included in the first information, a system message value tag in the system message is not changed, The first information includes at least one of the following: Information related to network node capabilities; Network comprehensive capability indication information; Information related to terminal capabilities; including direct indication information for instructing the terminal to initiate a service of an artificial intelligence or machine learning operation type, The information related to the network node capability includes: computing capability indication information, wireless resource capability indication information, and backward link bandwidth indication information. The network comprehensive capability indication information is information obtained by comprehensively evaluating the computing capability indication information, the wireless resource capability indication information and the backward link bandwidth indication information.

2. The communication method according to claim 1, wherein: The first information is used to enable the access layer of the terminal to determine a service of initiating an artificial intelligence or machine learning operation type.

3. The communication method according to claim 1, wherein: The information related to the network node capability also includes: a threshold corresponding to each item of the at least one item of network node capability indication information.

4. The communication method according to claim 1, wherein: The network comprehensive capability indication information also includes: a threshold corresponding to the network comprehensive capability.

5. The communication method according to claim 1, wherein: The information related to the terminal capability includes: a threshold corresponding to each item of the at least one item of terminal capability information.

6. A communication method, executed by a terminal, the communication method comprising: Acquiring first information through a system message, wherein the system message value tag in the system message does not change in response to a change in at least one item of information included in the first information, wherein the first information includes at least one of the following: information related to network node capabilities, network comprehensive capability indication information, information related to terminal capabilities, and direct indication information for indicating that the terminal initiates a service of an artificial intelligence or machine learning operation type, wherein the information related to network node capabilities includes: computing capability indication information, wireless resource capability indication information, and backward link bandwidth indication information, wherein the network comprehensive capability indication information is information obtained by comprehensively evaluating the computing capability indication information, the wireless resource capability indication information, and the backward link bandwidth indication information; Determine a business that initiates an artificial intelligence or machine learning operation type based on the first information.

7. The communication method according to claim 6, wherein: The obtaining and the determining are performed by an access layer of the terminal, Wherein, the communication method further includes: The non-access layer of the terminal is notified of the result of the determination.

8. The communication method according to claim 6, wherein: The information related to the network node capability also includes: a threshold corresponding to each item of the at least one item of network node capability indication information.

9. The communication method according to claim 6, wherein: The network comprehensive capability indication information also includes: a threshold corresponding to the network comprehensive capability.

10. The communication method according to claim 6, wherein: The information related to the terminal capability includes: a threshold corresponding to each item of the at least one item of terminal capability information.

11. The communication method according to claim 6, wherein: Determining, based on the first information, to initiate a business of an artificial intelligence or machine learning operation type includes at least one of the following: In response to a result of comparing at least one item of the information related to the network node capability with a corresponding threshold, determining to initiate a service of an artificial intelligence or machine learning operation type; In response to a result of comparing the network comprehensive capability indication information with a corresponding threshold, determining to initiate a service of an artificial intelligence or machine learning operation type; In response to a result of comparing at least one item of the information related to the terminal capability with a corresponding threshold, determining to initiate a service of an artificial intelligence or machine learning operation type; In response to the direct indication information, a business of initiating an artificial intelligence or machine learning operation type is directly determined.

12. The communication method according to claim 6 or 7, wherein: The communication method also includes: estimating resources required for a service of the type of artificial intelligence or machine learning operation to be initiated; Determining, based on the first information, to initiate an artificial intelligence or machine learning operation type of business, including: Determine a business to initiate an artificial intelligence or machine learning operation type based on the estimated resources and / or the first information.

13. A communication device, applied to a network node, comprising: A communication module is configured to: send first information through a system message, wherein the first information is used to enable the terminal to determine to initiate a service of an artificial intelligence or machine learning operation type, wherein in response to a change in at least one item of information included in the first information, a system message value tag in the system message is not changed, wherein the first information includes at least one of the following: Information related to network node capabilities; Network comprehensive capability indication information; Information related to terminal capabilities; Direct instruction information for instructing the terminal to initiate an artificial intelligence or machine learning operation type service, The information related to the network node capability includes: computing capability indication information, wireless resource capability indication information, and backward link bandwidth indication information. The network comprehensive capability indication information is information obtained by comprehensively evaluating the computing capability indication information, the wireless resource capability indication information and the backward link bandwidth indication information.

14. A communication device, applied to a terminal, the communication device comprising: A communication module, configured to: obtain first information through a system message, wherein the system message value tag in the system message does not change in response to a change in at least one item of information included in the first information, wherein the first information includes at least one of the following: information related to network node capabilities, network comprehensive capability indication information, information related to terminal capabilities, and direct indication information for indicating that the terminal initiates a service of an artificial intelligence or machine learning operation type, wherein the information related to network node capabilities includes: computing capability indication information, wireless resource capability indication information, and backward link bandwidth indication information, wherein the network comprehensive capability indication information is information obtained by comprehensively evaluating the computing capability indication information, the wireless resource capability indication information, and the backward link bandwidth indication information; The processing module is configured to determine a business that initiates an artificial intelligence or machine learning operation type based on the first information.

15. An electronic device, comprising a memory and a processor; The memory stores a computer program; The processor is configured to perform the method of any one of claims 1 to 5 or any one of claims 6 to 12 when running the computer program.

16. A computer-readable storage medium, wherein a computer program is stored in the storage medium, and when the computer program is executed by a processor, the computer program is used to execute the method of any one of claims 1 to 5 or any one of claims 6 to 12.

Images