WO2022000216A1 - Communication method and device, electronic device, and computer-readable storage medium - Google Patents
Communication method and device, electronic device, and computer-readable storage medium Download PDFInfo
- Publication number
- WO2022000216A1 WO2022000216A1 PCT/CN2020/099051 CN2020099051W WO2022000216A1 WO 2022000216 A1 WO2022000216 A1 WO 2022000216A1 CN 2020099051 W CN2020099051 W CN 2020099051W WO 2022000216 A1 WO2022000216 A1 WO 2022000216A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- information
- terminal
- communication method
- network node
- initiate
- Prior art date
Links
- 238000004891 communication Methods 0.000 title claims abstract description 86
- 238000000034 method Methods 0.000 title claims abstract description 58
- 238000013473 artificial intelligence Methods 0.000 claims abstract description 42
- 238000010801 machine learning Methods 0.000 claims abstract description 42
- 230000004044 response Effects 0.000 claims description 22
- 238000012545 processing Methods 0.000 claims description 15
- 238000004590 computer program Methods 0.000 claims description 14
- 230000000977 initiatory effect Effects 0.000 claims description 11
- 238000012549 training Methods 0.000 description 16
- 238000010586 diagram Methods 0.000 description 8
- 230000006399 behavior Effects 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 238000005265 energy consumption Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 238000013468 resource allocation Methods 0.000 description 1
- 238000001228 spectrum Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W74/00—Wireless channel access
- H04W74/002—Transmission of channel access control information
- H04W74/006—Transmission of channel access control information in the downlink, i.e. towards the terminal
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
Definitions
- the present disclosure relates to the field of communication technologies, and in particular, the present disclosure relates to a communication method, a communication device, an electronic device, and a computer-readable storage medium.
- AI/ML-based mobile applications are increasingly computationally intensive, memory-intensive, and power-hungry.
- terminals often have strict energy consumption, computing and memory cost constraints. Therefore, it is usually necessary to separate the AI/ML operation type services on the terminal and the network.
- AI/ML operation type services for example, AI/ML model training operations
- service eg, call service
- the present disclosure provides a communication method and device, an electronic device, and a computer-readable storage medium.
- the present disclosure provides a communication method, the communication method comprising: sending first information, wherein the first information is used to enable a terminal to determine to initiate a service of an artificial intelligence or machine learning operation type.
- the first information is used to enable the access layer of the terminal to determine to initiate a service of an artificial intelligence or machine learning operation type.
- 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 of the business.
- the information related to the network node capability includes: at least one item of network node capability indication information.
- the network comprehensive capability indication information is information obtained by comprehensively considering the at least one item of network node capability indication information.
- the information related to the network node capability further includes: a threshold corresponding to each item of network node capability indication information in the at least one item of network node capability indication information.
- the network comprehensive capability indication information further includes: a threshold corresponding to the network comprehensive capability.
- the information related to the terminal capability includes: a threshold corresponding to each item of terminal capability information of the at least one item of terminal capability information.
- the sending the first information includes: sending the first message through at least one of main information, a remaining minimum system message, or other system messages.
- the communication method may further include: when the first message is sent through other system messages, in response to at least one item of information included in the first information being changed, not changing the system message The system message value label in .
- the present disclosure provides a communication method, the communication method includes: acquiring first information; and determining to initiate a service of an artificial intelligence or machine learning operation type based on the first information.
- the acquiring and the determining are performed through an access stratum of a terminal, wherein the communication method further includes: notifying a non-access stratum of the terminal of a result of the determination.
- determining to initiate a business of an artificial intelligence or machine learning operation type based on the first information includes at least one of the following:
- 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.
- the present disclosure provides a communication device, the communication device comprising: a communication module configured to: send first information, wherein the first information is used to make a terminal determine to initiate an artificial intelligence or machine learning operation type of business.
- the present disclosure provides a communication device, the communication device comprising: a communication module configured to: acquire first information; and a processing module configured to: determine to initiate an artificial intelligence or a machine based on the first information Learn to operate types of business.
- the present disclosure also provides an electronic device, the electronic device includes a memory and a processor; a computer program is stored in the memory; the processor is configured to execute the above-mentioned method when the computer program is executed.
- the present disclosure also provides a computer-readable storage medium, in which a computer program is stored, the computer program being used to execute the method as described above when executed by a processor.
- 1 is a schematic diagram of an architecture of a communication system
- FIG. 2 is a schematic flowchart of a communication method provided in an embodiment of the present disclosure
- FIG. 3 is a schematic diagram of a communication device provided in an embodiment of the present disclosure.
- FIG. 4 is a schematic diagram of another communication device provided in an embodiment of the present disclosure.
- FIG. 5 is a schematic structural diagram of an electronic device provided by the present disclosure.
- FIG. 1 is a schematic diagram of the architecture of a communication system 100 to which an embodiment of the disclosure is applied.
- a communication system 100 may include a base station 110 and a terminal 120 .
- Terminal 120 is located in a cell covered by base station 110 and can communicate with base station 110 .
- FIG. 1 shows only one base station 110, one terminal 120, and three cells that the base station 110 can cover, these are only exemplary, and exemplary embodiments of the present disclosure are not limited thereto.
- the communication system 100 may further include multiple base stations, multiple terminals located in various cells, and/or access points, and the like.
- terminals may include, but are 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.
- PDAs personal digital assistants
- PCS personal communication system
- PIMs personal information managers
- PNDs personal navigation devices
- global positioning systems multimedia devices
- IoT Internet of Things
- the computationally intensive, energy-intensive part of AI/ML can be offloaded to the network node, while the Privacy-sensitive and latency-sensitive parts are left on the terminal.
- Terminals can perform operations/specific parts/layers in the model and send intermediate data to network nodes.
- the network nodes execute the remaining parts/layers and feed back the inference results to the terminal.
- the key to splitting the business of AI/ML operation types is to choose the best splitting mode and splitting point to ensure that the required resources are lower than the upper limit of the resources available on the terminal, and to optimize computing, storage/memory, power consumption, terminal side and network side communication resources, etc.
- the resource requirements for uplink and downlink are very different.
- a large amount of downlink bandwidth is required because the AI/ML model download is involved; while for the AI/ML operation in the network cloud training mode, because it involves For the upload of training data, a large amount of uplink bandwidth is required, while for downlink only the result of inference after training is not required. large bandwidth. Therefore, when a user (eg, the user's terminal 120 ) initiates an application for model training, the required bandwidth may be as high as 20 Gbps (gigabits per second) and a large amount of computing resources are required.
- an embodiment of the present disclosure proposes a mechanism for notifying a terminal of related information in a system message to restrict the terminal from initiating a service of an AI/ML operation type.
- FIG. 2 shows a schematic flowchart of a communication method according to an embodiment of the present disclosure.
- first information may be sent.
- the base station may send (or notify) the first information to the terminal.
- the first information is used to enable the terminal to determine whether to initiate an AI/ML operation type service.
- the first message is used to make an access (AS, Access Stratum) layer or a non-access (NAS, Non Access Stratum) layer of the terminal determine whether to initiate an AI/ML operation type service.
- the first message is used to make the AS layer of the terminal determine whether to initiate an AI/ML operation type service.
- 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.
- the first message may be sent to the terminal through a system message or other agreed manner.
- 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 instruction information.
- direct indication information for indicating whether to initiate an artificial intelligence or machine learning operation type service may be referred to as "direct indication information”
- auxiliary information information other than “direct indication information”
- the information related to the network node capability in the first information may include: at least one item of network node capability indication information.
- the at least one item of network node capability indication information may include at least one of the following: computing capability indication information, radio resource capability indication information, and backward link bandwidth indication information.
- the at least one item of network node capability indication information may be a resource that a network node (eg, a base station) can provide for AI/ML operation type services (eg, a resource provided for AI/ML model training), or It can be a resource already occupied by a network node.
- the computing capability indication information may include the occupancy of at least one of the memory, CPU, storage space of the network node (this may be indicated in the form of a percentage or high, high, low) or the current load of the network situation;
- 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 percentage or high, medium and low;
- the backward link bandwidth indication information may include the relationship between the base station and the core network element. The bandwidth of the interface link between them, or the bandwidth of the interface link between the base station and the dedicated server that provides AI/ML services.
- the example of the at least one item of network node capability indication information is not limited to the above embodiments.
- the at least one item of network node capability indication information may also include the number of operations broadcasted by the network node that it can support, such as addition and multiplication operations. number of times.
- the information related to the network node capability in the first information may further include: a threshold corresponding to each item of network node capability indication information in the at least one item of network node capability indication information.
- a threshold corresponding to each item of network node capability indication information in the at least one item of network node capability indication information.
- the threshold may be the same as the one used for AI/ML model training.
- the threshold may be a threshold corresponding to the already occupied resource.
- the inventive concept is not limited thereto, for example, when at least one item of network node capability indication information is a resource that has been occupied by the network node, the threshold may be a threshold corresponding to the available resources, in this case, the terminal (for example, AS layer) can first infer the threshold corresponding to the occupied resources based on the threshold corresponding to the available resources, and then determine whether AI/ML can be initiated according to at least one item of network node capability indication information and the inferred threshold Operation type business.
- the information related to the network node capability may further include: computation capability decision Threshold, radio resource capability decision threshold and/or backward link bandwidth decision threshold.
- the threshold information is used to make the terminal (eg, the AS layer of the terminal) compare each item of 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 (eg, the AS layer of the terminal).
- the network comprehensive capability indication information in the first information is information obtained by comprehensively considering at least one item of network node capability indication information described above.
- the base station can obtain the network comprehensive capability indication information by comprehensively evaluating the computing capability, radio 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.
- the traffic capacity may refer to the traffic capacity currently carried by the network node or the remaining traffic capacity of the network node.
- the network comprehensive capability indication information in the first information may further include: a threshold corresponding to the network comprehensive capability.
- the network comprehensive capability indication information 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.
- the threshold is used to make the terminal (eg, the AS layer of the terminal) compare each item of network node capability indication information in the first information with the corresponding threshold to determine whether to initiate an AI/ML operation type service.
- the above-mentioned threshold information (ie, the threshold corresponding to each item of network node capability indication information in the at least one item of network node capability indication information, the threshold corresponding to the network comprehensive capability) may be included in the first information, so as to be 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 connected to the terminal.
- the pre-stored or solidified threshold information can be directly used when the terminal needs to make a decision; as another example, the terminal can obtain the threshold information in advance before receiving the first information; in addition, the network node can also periodically or at When necessary, the threshold information is sent, and the pre-stored threshold information is updated.
- the information related to the terminal capability in the first information may include: a threshold corresponding to each item of terminal capability information of the at least one item of terminal capability information.
- the at least one item of terminal capability information may include at least one of the following: terminal computing capability information, terminal power information.
- the network node eg, base station
- the network node needs to allow the terminal to initiate an AI/ML operation type service only when the terminal capability reaches a certain threshold.
- the threshold that the terminal's current computing capacity margin needs to reach for example, the occupancy of at least one of the terminal's memory, CPU, and storage space indicated in the form of a percentage
- the threshold that the terminal's current power margin needs to reach can be In the form of a percentage
- the terminal power is lower than the required threshold, the terminal needs to be in a charging state, etc.
- the first message may be sent through at least one of main information, Remaining Minimum System Information (RMSI, Remaining Minimum System Information), or other system information (SI, System Information).
- RMSI Remaining Minimum System Information
- SI System Information
- the base station may notify the terminal in RMSI or other SI of the auxiliary information in the first message (ie, information related to network node capabilities, network integrated capability indication information, information related to terminal capabilities); and , the base station can notify the terminal of the direct indication information in the first message through master information (for example, master information block MIB (Master Information Block)), RMSI or other system messages (for example, system message block SIB (System Information Block)).
- master information for example, master information block MIB (Master Information Block)
- RMSI or other system messages for example, system message block SIB (System Information Block)
- the base station may use an indication bit (one or more bits) in the system message to send direct indication information to directly inform the terminal whether the AI/ML operation type service can be initiated.
- the indication bit may be carried in the MIB; for another example, the indication bit may be carried in the RMSI or other SIBs.
- the communication method shown in FIG. 2 may further include: when the first message is sent through other system messages (ie, other system messages except MIB and RMSI), in response to at least one of the first messages included in the first message
- the system message value tag (SI value tag) in the system message is not changed.
- the base station needs to page the terminal by sending a paging message (paging), and accordingly, the terminal needs to monitor paging to obtain the change of the system message.
- the SI value tag is not changed, so that the base station does not need to notify the terminal by paging, but the terminal needs to initiate an AI/ML operation type when the Before the service (ie, initiating AI/ML access), it monitors system messages by itself to obtain and/or update the first message, thereby saving resources. That is, 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.
- a network node eg, a base station
- the network node may send a plurality of pieces of information in the first information and/or an indication rule specifying valid information in the first information to the terminal according to the service of the AI/ML operation type that it can support, and the terminal may, according to the indication rule to determine the valid information among the multiple pieces of information, and to decide whether to initiate an AI/ML operation type service according to the valid information.
- multiple pieces of information may indicate information related to network node capabilities (eg, at least one item of network node capability indication information and/or corresponding thresholds), network comprehensive capability indication information, and information related to terminal capability information (eg, a threshold corresponding to each item of at least one item of terminal capability information) and/or direct indication information.
- the instruction rules may not be sent by the network node, but may be pre-written or stored in the terminal or a device connected to the terminal, or may be agreed through a protocol.
- the network node may only send multiple pieces of information (eg, computing capability indication information, radio resource capability indication information, backward link bandwidth indication information and their corresponding thresholds) to the terminal, as well as designated computing capability indication information and radio resource capability indication
- the information is an indication rule for valid information.
- the terminal has received multiple pieces of information, it only uses the computing capability indication information, the wireless resource capability indication information and the corresponding threshold according to the indication rule obtained from the local area. Determines whether to initiate an AI/ML operation type service.
- the network node may predetermine which information is valid according to the services of the AI/ML operation type that it can support, so as to send only 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, so as to only send the radio resource capability indication information and/or the threshold of the terminal power information to the terminal, so that the terminal can use them to decide whether to Initiate business of AI/ML operation type.
- the network node may comprehensively consider its capability information (eg, network node capability indication information) to determine the direct indication information, and send the direct indication information to the terminal, so that the terminal can directly determine whether to initiate or not according to the direct indication information AI/ML operation type business.
- its capability information eg, network node capability indication information
- the information sent by the network node to the terminal is valid by default, so the terminal can use the received information to decide whether to initiate an AI/ML operation type service.
- the terminal may acquire the first information, and determine whether to initiate an AI/ML operation type service based on the acquired first information.
- the base station may send the first message to the terminal through the system message, that is, carry the first message in the system message, and the terminal may obtain the system message before initiating the AI/ML service, so as to obtain the first information from the system message .
- the above operations may be performed through the AS layer or the NAS layer of the terminal.
- the above-mentioned acquisition and determination operations may be performed through the AS layer of the terminal.
- the AS layer of the terminal is more controllable for the behavior of the terminal, because the policies are provided by the base station, and the terminal can make a decision according to the provided policy.
- some decision conditions are related to users (eg, user preferences and privacy protection), and the decision is relatively complicated.
- the AS layer of the terminal may notify the NAS layer of the terminal of the determination result, so that the NAS layer performs corresponding operations according to the determined result. For example, when the AS layer of the terminal determines based on the acquired first information that the service of the AI/ML operation type can be initiated, in step S120, the NAS layer can execute the service of initiating the AI/ML operation type.
- the terminal 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:
- the network node may send different first information for services of different AI/ML operation types, and the terminal may make a decision based on the information sent by the network node to determine whether to initiate the AI/ML operation type service.
- the terminal receives different first information from the base station, it can judge which information is valid from the first information (similar to that described in step S110 ), or judge the priority of each piece of information.
- the direct indication information may be determined as having the highest priority, so as to decide whether to initiate an AI/ML operation type based on the direct indication information preferentially or only based on the direct indication information. business.
- the terminal may determine whether the computing capability indication information provided by the base station in the first message satisfies the requirements for initiating a service of an AI/ML operation type (eg, access for AI/ML model training). required resource requirements. If it is not satisfied, it is considered that the AI/ML service part of this type is allowed to access the cell (or base station).
- the terminal eg, AS layer
- the terminal can compare the resources (eg, the size of memory, CPU, and/or storage space that can be provided) that can be provided by the network node with the corresponding threshold, so as to determine whether the resources provided by the network node reach the threshold.
- the corresponding threshold is used to determine whether AI/ML operation type services can be initiated.
- the terminal for example, the AS layer
- the terminal may decide whether the radio resource capability indication information provided by the base station in the first message satisfies the service of initiating AI/ML operation type (for example, the access of AI/ML model training) required resource requirements. If it is not satisfied, it is considered that the AI/ML service part of this type is allowed to access the cell (or base station).
- the terminal for example, the AS layer
- the terminal can determine whether it can initiate the operation by judging whether the resources provided by the network node (for example, the bandwidth provided by the network node) reach the corresponding threshold, or by judging whether the current frequency utilization rate of the network is lower than the corresponding threshold.
- AI/ML operation type business.
- the terminal may decide whether the backward link bandwidth indication information provided by the base station in the first message satisfies the service of initiating AI/ML operation type (for example, the connection for AI/ML model training). input) required resource requirements. If it is not satisfied, it is considered that the AI/ML service part of this type is allowed to access the cell (or base station). For example, whether the AI/ML operation type service can be initiated is determined by judging whether the resources provided by the network node (eg, the size of the backward link bandwidth provided by the network node) reach a corresponding threshold.
- the service of initiating AI/ML operation type for example, the connection for AI/ML model training. input
- the terminal may compare the network comprehensive capability indication information (eg, the signal load) in the first message with a corresponding threshold to determine whether to initiate an AI/ML operation type service.
- the network comprehensive capability indication information eg, the signal load
- the terminal 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 itself with the terminal computing capability information indicated by the terminal computing capability information.
- the corresponding thresholds are compared to determine whether the AI/ML operation type service can be initiated.
- a terminal may combine one or more of the above-described 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 both sufficient to initiate an AI/ML operation type service.
- the communication method shown in FIG. 2 may further comprise: estimating the resources required for the service of the AI/ML operation type to be initiated.
- the terminal eg, AS layer
- the terminal may determine whether to initiate AI/ML operation type services based on the estimated resources and/or the first information.
- the AS layer of the terminal can use historical records or other high-level instructions, or the AS layer of the terminal can pre-estimate the AI/ML to be initiated based on historical statistical information and/or user behavior (eg, the user's current communication behavior).
- the resources required by the operation type of business so as to obtain the resource requirements of the initiated AI/ML model training access.
- the history record may be record information of resources used when the terminal previously initiated the AI/ML operation type service.
- the historical statistical information may be information obtained by performing statistical calculation on the record information of resources used when a service of the AI/ML operation type was previously initiated. Accordingly, the AS layer of the terminal can judge whether the resources provided by the network node meet the resource requirements (ie, compare the resources provided by the network nodes with the resource requirements) to determine whether to initiate an AI/ML operation type service.
- the terminal may estimate in advance at least one of 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 Compare to determine whether to initiate an AI/ML operation type business.
- 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 of times with the number of addition and multiplication operations supported by the network broadcast to determine whether to initiate the AI/ML operation type Business.
- the terminal may pre-estimate the bandwidth (for example, the estimated bandwidth) required by the AI/ML operation type service to be initiated, and compare the estimated bandwidth with the bandwidth provided by the network node in the radio resource indication information to obtain Determines whether to initiate an AI/ML operation type business.
- the bandwidth for example, the estimated bandwidth
- the terminal can pre-estimate the required backward bandwidth of the AI/ML operation type to be initiated, and compare the required backward bandwidth with the bandwidth of the backward link provided by the network to determine whether to initiate AI /ML operation type business.
- the communication method shown in FIG. 2 may further include: in response to determining that the AI/ML operation type service is not allowed to be initiated and only the AI/ML operation type service is initiated, identifying the cell state as "cell prohibited (cell prohibited)" bar)".
- the terminal may receive system messages in the further cell and attempt to initiate AI/ML operation type traffic.
- the NAS layer is notified that the current cell has access to the AI/ML model. Access is prohibited, but other services (for example, call services) can be initiated; if the AS layer of the terminal judges that access is allowed, otherwise the NAS layer is notified that the current cell is allowed to access the AI/ML model.
- the above communication method 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.
- FIG. 3 is a schematic diagram illustrating a communication device 300 according to an embodiment of the present disclosure.
- the communication device 300 may include a communication module 310 .
- the communication module 310 is configured to: send the first information.
- the first information is used to enable the terminal to determine whether to initiate an artificial intelligence or machine learning operation type service.
- the description about the first information is similar to step S110 in FIG. 2 , and repeated descriptions are omitted here for brevity.
- 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.
- the communication module 310 may be configured to transmit the first message through at least one of a master message, a remaining minimum system message, or other system messages.
- the structure of the communication device 300 shown in FIG. 3 is only exemplary, and embodiments of the present disclosure are not limited thereto, for example, the communication device 300 may further include a processing device for processing AI/ML operation type services, or A device that communicates with a dedicated server that provides AI/ML operation type services through the core network, etc.
- the processing module in the communication device 300 may be configured to not change the system message in response to at least one item of information included in the first information being changed when the first message is sent through other system messages The system message value label in .
- the communication device 300 may perform the operations in step S110 described above with reference to FIG. 2 , and repeated descriptions are omitted here for brevity.
- FIG. 4 is a schematic diagram illustrating another communication device 400 according to an embodiment of the present disclosure.
- the communication device 400 may include a communication module 410 and a processing module 420 .
- the communication module 410 may be configured to acquire the first information.
- the processing module 420 may be configured to: determine whether to initiate an AI/ML operation type service based on the first information.
- the communication module 410 and the processing module 420 may be included in the AS layer or the NAS layer of the terminal. Preferably, both the communication module 410 and the processing module 420 may be included in the AS layer of the terminal.
- 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:
- the processing module 420 may perform operations similar to the decision operation of the terminal (eg, the AS layer) described with reference to FIG. 2 , and repeated descriptions are omitted here for brevity.
- the processing module 420 may be further configured to: estimate the resources required for a business of the type of artificial intelligence or machine learning operation to be initiated, and determine whether to Launch an AI or machine learning operation type business.
- the processing module 420 may be further configured to: in response to determining that initiation of services of the artificial intelligence or machine learning operation type is not allowed and that there are only services of the initiation artificial intelligence or machine learning operation type, identify the cell status as "Cell Prohibition".
- the communication device 400 may further include a NAS layer for receiving the determined result from the AS layer, And when the AS layer determines to allow access, the NAS layer can initiate artificial intelligence or machine learning operations.
- the communication device 400 may further 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 network nodes, and the like.
- the devices provided in the embodiments of the present disclosure are devices that can execute the corresponding methods provided in the embodiments of the present disclosure, those skilled in the art can understand the The specific implementation of the device in the disclosed embodiment and its various modifications are not described in detail here for how the device implements the method in the embodiment of the present disclosure. As long as the devices used by those skilled in the art to implement the methods in the embodiments of the present disclosure fall within the scope of the intended protection of the present disclosure. Wherein, each module included in the above device may be specifically implemented by software and/or hardware.
- the present disclosure also provides an electronic device, which may include at least one processor, and the processor may be configured to perform the method provided in any optional embodiment of the present disclosure.
- the electronic device may include at least one memory in which a computer program (or may also be referred to as computer instructions or codes) is stored, and the at least one processor may execute any one of the present disclosure when running the computer program.
- a computer program or may also be referred to as computer instructions or codes
- the at least one processor may execute any one of the present disclosure when running the computer program.
- the present disclosure also provides a computer-readable storage medium, where a computer program is stored, and when the computer program is executed by a processor, the computer program can execute the communication method shown in any optional embodiment of the present disclosure.
- FIG. 5 shows a schematic structural diagram of an electronic device that can be applied to the solution provided by the present disclosure.
- the electronic device 5000 includes: a processor 5001 and a memory 5003 .
- the processor 5001 is connected to the memory 5003, for example, through a bus 5002.
- the electronic device 5000 may also include a transceiver 5004 .
- the transceiver 5004 is not limited to one, and the structure of the electronic device 5000 does not constitute a limitation to the embodiments of the present disclosure.
- the processor 5001 can be CPU (Central Processing Unit, central processing unit), general-purpose processor, DSP (Digital Signal Processor, data signal processor), ASIC (Application Specific Integrated Circuit, application-specific integrated circuit), FPGA (Field Programmable Gate Array) , field programmable gate array) or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It may implement or execute the various exemplary logical blocks, modules and circuits described in connection with this disclosure.
- the processor 5001 may also be a combination that realizes computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, and the like.
- the bus 5002 may include a path to transfer information between the components described above.
- the bus 5002 may be a PCI (Peripheral Component Interconnect, Peripheral Component Interconnect Standard) bus or an EISA (Extended Industry Standard Architecture, Extended Industry Standard Architecture) bus or the like.
- the bus 5002 can be divided into an address bus, a data bus, a control bus, and the like. For ease of presentation, only one thick line is used in FIG. 5, but it does not mean that there is only one bus or one type of bus.
- the memory 5003 can be a ROM (Read Only Memory, read only memory) or other types of static storage devices that can store static information and instructions, a RAM (Random Access Memory, random access memory) or other types of storage devices that can store information and instructions.
- Dynamic storage device can also be EEPROM (Electrically Erasable Programmable Read Only Memory, electrically erasable programmable read only memory), CD-ROM (Compact Disc Read Only Memory, CD-ROM) or other optical disk storage, optical disk storage (including compressed compact disc, laser disc, compact disc, digital versatile disc, blu-ray disc, etc.), magnetic disk storage medium or other magnetic storage device, or capable of carrying or storing desired program code in the form of instructions or data structures and capable of being accessed by a computer any other medium, but not limited to this.
- the memory 5003 is used for storing application program codes (computer programs) for executing the solutions of the present disclosure, and the execution is controlled by the processor 5001 .
- the processor 5001 is configured to execute the application program code stored in the memory 5003, so as to realize the content shown in any of the foregoing method embodiments.
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Mobile Radio Communication Systems (AREA)
Abstract
Provided are a communication method and device, an electronic device, and a computer-readable storage medium. The communication method comprises: transmitting first information, wherein the first information is used to make a terminal determine whether to initiate a service of an artificial intelligence or machine learning operation type. The technical solution provided by the present disclosure can inform, as early as possible, a terminal of information related to a network, in order to reasonably limit or allow the terminal to initiate a service of an AI/ML operation type.
Description
本公开涉及通信技术领域,具体而言,本公开涉及通信方法、通信设备、电子设备以及计算机可读存储介质。The present disclosure relates to the field of communication technologies, and in particular, the present disclosure relates to a communication method, a communication device, an electronic device, and a computer-readable storage medium.
随着第五代移动通信技术(5G)的不断扩展和深入,期望以人工智能(AI,Artificial Intelligence)/机器学习(ML,Machine Learning)等为基础,实现移动应用与网络的深度融合。With the continuous expansion and deepening of the fifth-generation mobile communication technology (5G), it is expected to realize the deep integration of mobile applications and networks based on artificial intelligence (AI, Artificial Intelligence)/Machine Learning (ML, Machine Learning).
基于AI/ML的移动应用越来越计算密集、内存消耗和功耗大。同时,终端通常具有严格的能耗、计算和内存成本限制。因此,通常需要将AI/ML操作类型的业务在终端和网络上进行分离。然而,对于某些网络侧的节点(例如,基站),因为其资源的有限,有时无法处理终端发起的AI/ML操作类型的业务(例如,AI/ML模型训练操作),而仅能进行常规的业务(例如,呼叫业务)的发起。可见,现有的有关AI/ML操作类型的业务的通信方法仍有待改进。AI/ML-based mobile applications are increasingly computationally intensive, memory-intensive, and power-hungry. At the same time, terminals often have strict energy consumption, computing and memory cost constraints. Therefore, it is usually necessary to separate the AI/ML operation type services on the terminal and the network. However, for some network-side nodes (for example, base stations), due to their limited resources, sometimes they cannot process AI/ML operation type services (for example, AI/ML model training operations) initiated by the terminal, and can only perform conventional AI/ML operations. service (eg, call service). It can be seen that the existing communication methods for AI/ML operation type services still need to be improved.
发明内容SUMMARY OF THE INVENTION
为了解决上述的至少一个问题,本公开提供了通信方法及设备、电子设备以及计算机可读存储介质。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.
一方面,本公开提供了一种通信方法,所述通信方法包括:发送第一信息,其中,所述第一信息用于使得终端确定发起人工智能或机器学习操作类型的业务。In one aspect, the present disclosure provides a communication method, the communication method comprising: sending first information, wherein the first information is used to enable a terminal to determine to initiate a service of an artificial intelligence or machine learning operation type.
根据本公开的实施例,所述第一信息用于使得终端的接入层确定发起人工智能或机器学习操作类型的业务。According to an embodiment of the present disclosure, the first information is used to enable the access layer of the terminal to determine to initiate a service of an artificial intelligence or machine learning operation type.
根据本公开的实施例,所述第一信息包括以下至少一项:与网络节点 能力相关的信息;网络综合能力指示信息;与终端能力相关的信息;用于指示发起人工智能或机器学习操作类型的业务的直接指示信息。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 of the business.
根据本公开的实施例,所述与网络节点能力相关的信息包括:至少一项网络节点能力指示信息。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.
根据本公开的实施例,所述网络综合能力指示信息是通过综合考虑所述至少一项网络节点能力指示信息而获得的信息。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.
根据本公开的实施例,所述与网络节点能力相关的信息还包括:与所述至少一项网络节点能力指示信息中的每一项网络节点能力指示信息相对应的门限。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 network node capability indication information in the at least one item of network node capability indication information.
根据本公开的实施例,所述网络综合能力指示信息还包括:与网络综合能力相对应的门限。According to an embodiment of the present disclosure, the network comprehensive capability indication information further includes: a threshold corresponding to the network comprehensive capability.
根据本公开的实施例,所述与终端能力相关的信息包括:与至少一项终端能力信息的每一项终端能力信息相对应的门限。According to an embodiment of the present disclosure, the information related to the terminal capability includes: a threshold corresponding to each item of terminal capability information of the at least one item of terminal capability information.
根据本公开的实施例,所述发送第一信息包括:通过主信息、剩余最小***消息或其他***消息中的至少一项来发送所述第一消息。According to an embodiment of the present disclosure, the sending the first information includes: sending the first message through at least one of main information, a remaining minimum system message, or other system messages.
根据本公开的实施例,所述通信方法还可以包括:通过其他***消息发送所述第一消息时,响应于所述第一信息中包括的至少一项信息发生变更,不变更所述***消息中的***消息值标签。According to an embodiment of the present disclosure, the communication method may further include: when the first message is sent through other system messages, in response to at least one item of information included in the first information being changed, not changing the system message The system message value label in .
另一方面,本公开提供了一种通信方法,所述通信方法包括:获取第一信息;基于所述第一信息确定发起人工智能或机器学习操作类型的业务。In another aspect, the present disclosure provides a communication method, the communication method includes: acquiring first information; and determining to initiate a service of an artificial intelligence or machine learning operation type based on the first information.
根据本公开的实施例,所述获取和所述确定是通过终端的接入层来执行的,其中,所述通信方法还包括:向所述终端的非接入层通知所述确定的结果。According to an embodiment of the present disclosure, the acquiring and the determining are performed through an access stratum of a terminal, wherein the communication method further includes: notifying a non-access stratum of the terminal of a result of the determination.
根据本公开的实施例,基于所述第一信息确定发起人工智能或机器学习操作类型的业务,包括以下至少一项:According to an embodiment of the present disclosure, determining to initiate a business of an artificial intelligence or machine learning operation type based on the first information includes at least one of the following:
响应于所述与网络节点能力相关的信息中的至少一项信息与相对应的门限比较的结果,确定发起人工智能或机器学习操作类型的业务;In response to a result of comparing at least one piece of 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;
响应于所述网络综合能力指示信息与相对应的门限比较的结果,确定发起人工智能或机器学习操作类型的业务;In response to the result of comparing the network comprehensive capability indication information with the corresponding threshold, determine to initiate an artificial intelligence or machine learning operation type service;
响应于所述与终端能力相关的信息中的至少一项信息与相对应的门限比较的结果,确定发起人工智能或机器学习操作类型的业务;In response to a result of comparing at least one piece of information related to the terminal capability with a corresponding threshold, determining to initiate a service of an artificial intelligence or machine learning operation type;
响应于所述直接指示信息,直接确定发起人工智能或机器学习操作类型的业务。In response to the direct indication information, it is directly determined to initiate a business of the type of artificial intelligence or machine learning operation.
根据本公开的实施例,所述通信方法还可以包括:估计即将发起的人工智能或机器学习操作类型的业务所需的资源。基于所述第一信息确定发起人工智能或机器学习操作类型的业务,包括:基于所估计的资源和/或所述第一信息确定发起人工智能或机器学习操作类型的业务。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.
再一个方面,本公开提供了一种通信设备,所述通信设备包括:通信模块,被配置为:发送第一信息,其中,所述第一信息用于使得终端确定发起人工智能或机器学习操作类型的业务。In yet another aspect, the present disclosure provides a communication device, the communication device comprising: a communication module configured to: send first information, wherein the first information is used to make a terminal determine to initiate an artificial intelligence or machine learning operation type of business.
另一个方面,本公开提供了一种通信设备,所述通信设备包括:通信模块,被配置为:获取第一信息;处理模块,被配置为:基于所述第一信息确定发起人工智能或机器学习操作类型的业务。In another aspect, the present disclosure provides a communication device, the communication device comprising: a communication module configured to: acquire first information; and a processing module configured to: determine to initiate an artificial intelligence or a machine based on the first information Learn to operate types of business.
本公开还提供了一种电子设备,所述电子设备包括存储器和处理器;所述存储器中存储有计算机程序;所述处理器用于在运行所述计算机程序时执行如上所述的方法。The present disclosure also provides an electronic device, the electronic device includes a memory and a processor; a computer program is stored in the memory; the processor is configured to execute the above-mentioned method when the computer program is executed.
本公开还提供了一种计算机可读存储介质,所述存储介质中存储有计算机程序,所述计算机程序在被处理器运行时用于执行如上所述的方法。The present disclosure also provides a computer-readable storage medium, in which a computer program is stored, the computer program being used to execute the method as described above when executed by a processor.
本公开实施例提供的技术方案所带来的有益效果将在下文的具体实施方式描述中,结合具体的可选实施例进行详细描述,在此不再展开说明。The beneficial effects brought about by the technical solutions provided by the embodiments of the present disclosure will be described in detail in conjunction with specific optional embodiments in the following description of the specific implementation, and will not be further described here.
为了更清楚地说明本公开实施例中的技术方案,下面将对本公开实施例描述中所需要使用的附图作简单地介绍。In order to illustrate the technical solutions in the embodiments of the present disclosure more clearly, the following briefly introduces the accompanying drawings that are required to be used in the description of the embodiments of the present disclosure.
图1为一种通信***的架构的示意图;1 is a schematic diagram of an architecture of a communication system;
图2为本公开实施例中提供的通信方法的流程示意图;FIG. 2 is a schematic flowchart of a communication method provided in an embodiment of the present disclosure;
图3为本公开实施例中提供的通信设备的示意图;3 is a schematic diagram of a communication device provided in an embodiment of the present disclosure;
图4为本公开实施例中提供的另一通信设备的示意图;FIG. 4 is a schematic diagram of another communication device provided in an embodiment of the present disclosure;
图5为本公开提供的一种电子设备的结构示意图。FIG. 5 is a schematic structural diagram of an electronic device provided by the present disclosure.
下面详细描述本公开的实施例,所述实施例的示例在附图中示出,其中自始至终相同或类似的标号表示相同或类似的元件或具有相同或类似功能的元件。下面通过参考附图描述的实施例是示例性的,仅用于解释本公开,而不能解释为对本公开的限制。Embodiments of the present disclosure are described in detail below, examples of which are illustrated in the accompanying drawings, wherein the same or similar reference numerals refer to the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present disclosure, but not to be construed as a limitation of the present disclosure.
本技术领域技术人员可以理解,除非特意声明,这里使用的单数形式“一”、“一个”、“所述”和“该”也可包括复数形式。应该进一步理解的是,本公开的说明书中使用的措辞“包括”是指存在所述特征、整数、步骤、操作、元件和/或组件,但是并不排除存在或添加一个或多个其他特征、整数、步骤、操作、元件、组件和/或它们的组。应该理解,当我们称元件被“连接”或“耦接”到另一元件时,它可以直接连接或耦接到其他元件,或者也可以存在中间元件。此外,这里使用的“连接”或“耦接”可以包括无线连接或无线耦接。这里使用的措辞“和/或”包括一个或更多个相关联的列出项的全部或任一单元和全部组合。It will be understood by those skilled in the art that the singular forms "a", "an", "the" and "the" as used herein can include the plural forms as well, unless expressly stated otherwise. It should be further understood that the word "comprising" used in the specification of the present disclosure refers to the presence of the stated features, integers, steps, operations, elements and/or components, but does not preclude the presence or addition of one or more other features, Integers, steps, operations, elements, components and/or groups thereof. It will be understood that when we refer to an element as being "connected" or "coupled" to another element, it can be directly connected or coupled to the other element or intervening elements may also be present. Furthermore, "connected" or "coupled" as used herein may include wirelessly connected or wirelessly coupled. As used herein, the term "and/or" includes all or any element and all combination of one or more of the associated listed items.
除非另外定义,这里使用的所有术语(包括技术术语和科学术语),具有与本公开所属领域中的普通技术人员的一般理解相同的意义。将理解的是,尽管术语“第一”、“第二”等在本文中可以用于描述各种元素,但是这些元素不应受这些术语的限制。这些术语仅用于将一个元素与另一个元素区分开。因此,在不脱离示例实施例的教导的情况下,下面讨论的第一元素可以被称为第二元素。Unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this disclosure belongs. It will be understood that, although the terms "first," "second," etc. may be used herein to describe various elements, these elements should not be limited by these terms. These terms are only used to distinguish one element from another. Thus, a first element discussed below could be termed a second element without departing from the teachings of example embodiments.
为使本公开的实施例的目的、技术方案和优点更加清楚,下面将结合附图对本公开的实施方式作进一步地详细描述。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.
图1为本公开实施例所适用的一种通信***100的架构的示意图。FIG. 1 is a schematic diagram of the architecture of a communication system 100 to which an embodiment of the disclosure is applied.
参照图1,通信***100可以包括基站110以及终端120。终端120位于基站110所覆盖的小区中,并且可以与基站110进行通信。虽然图1中仅示出了一个基站110、一个终端120,以及基站110所能覆盖的三个小区,但是,这仅是示例性的,本公开的示例实施例不限于此。例如,通信***100还可以包括多个基站、位于各个小区的多个终端、和/或接入点等。Referring to FIG. 1 , a communication system 100 may include a base station 110 and a terminal 120 . Terminal 120 is located in a cell covered by base station 110 and can communicate with base station 110 . Although FIG. 1 shows only one base station 110, one terminal 120, and three cells that the base station 110 can cover, these are only exemplary, and exemplary embodiments of the present disclosure are not limited thereto. For example, the communication system 100 may further include multiple base stations, multiple terminals located in various cells, and/or access points, and the like.
作为示例,终端可以包括但不限于:蜂窝电话、智能电话、可穿戴设备、计算机、个人数字助理(PDA)、个人通信***(PCS)设备、个人信息管理器(PIM)、个人导航设备(PND)、全球定位***、多媒体设备、物联网(IoT)设备等。As examples, terminals may include, but are 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.
为了将AI/ML操作类型的业务在终端和网络(例如,基站110)上进行拆分,例如,例如,可以将AI/ML中的计算密集型、能源密集型部分卸载到网络节点,而将隐私敏感和延迟敏感部分留在终端上。终端可以执行操作/模型中的特定的部分/层,并将中间数据发送到网络节点。网络节点执行剩余的部分/层,并将推理结果反馈给终端。In order to split the AI/ML operation type traffic between the terminal and the network (eg, base station 110 ), for example, the computationally intensive, energy-intensive part of AI/ML can be offloaded to the network node, while the Privacy-sensitive and latency-sensitive parts are left on the terminal. Terminals can perform operations/specific parts/layers in the model and send intermediate data to network nodes. The network nodes execute the remaining parts/layers and feed back the inference results to the terminal.
拆分AI/ML操作类型的业务的关键是选择最佳的拆分模式和拆分点,以保证所需资源低于终端上可用资源的上限,并优化计算、存储/内存、功耗、终端侧和网络侧的通信资源等。The key to splitting the business of AI/ML operation types is to choose the best splitting mode and splitting point to ensure that the required resources are lower than the upper limit of the resources available on the terminal, and to optimize computing, storage/memory, power consumption, terminal side and network side communication resources, etc.
对于不同的拆分模式来说,对于上下行的资源需求是差异非常大的。在一个实施例,对于AI/ML操作在本地的训练模式,因为涉及到AI/ML模型的下载,因此需要大量的下行带宽;而对于AI/ML操作在网络的云端进行训练的模式,因为涉及到训练数据的上传,因此需要大量的上行带宽,而对于下行仅仅返回训练之后推理的结果则不需要大两的下行带宽;此外,对于本地训练和云端训练同时进行的模式,则上下行都需要大的带宽。因此当用户(例如,用户的终端120)发起一个模型训练的应用,其需要的带宽可能高达20几个Gbps(千兆比特每秒)并且需要大量的算力资源。从网络资源分配的角度看,对应着大量的带宽的分配,以及网络的算力资源(内存、处理器)的分配等。因此对于某些基站,因为其资源的有限,有时无法处理终端发起的AI/ML操作类型的业务(例如,模型训练操作),而仅能进行常规的业务(例如,呼叫业务)的发起。因此有必要尽早通知终端网络的算力情况。为此,本公开实施例提出一种在***消息中通知终端相关信息来限制终端发起AI/ML操作类型的业务的机制。For different split modes, the resource requirements for uplink and downlink are very different. In one embodiment, for the AI/ML operation in the local training mode, a large amount of downlink bandwidth is required because the AI/ML model download is involved; while for the AI/ML operation in the network cloud training mode, because it involves For the upload of training data, a large amount of uplink bandwidth is required, while for downlink only the result of inference after training is not required. large bandwidth. Therefore, when a user (eg, the user's terminal 120 ) initiates an application for model training, the required bandwidth may be as high as 20 Gbps (gigabits per second) and a large amount of computing resources are required. 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 resources (memory, processor), etc. Therefore, some base stations cannot process AI/ML operation type services (eg, model training operations) initiated by terminals due to limited resources, but can only initiate regular services (eg, call services). Therefore, it is necessary to notify the computing power of the terminal network as soon as possible. To this end, an embodiment of the present disclosure proposes a mechanism for notifying a terminal of related information in a system message to restrict the terminal from initiating a service of an AI/ML operation type.
图2示出根据本公开的实施例的一种通信方法的流程示意图。FIG. 2 shows a schematic flowchart of a communication method according to an embodiment of the present disclosure.
参照图2,在步骤S110中,可以发送第一信息。具体地说,基站可以向终端发送(或通知)第一信息,然而,这仅是示例性的,本公开的实施 例不限于此,例如,也可以通过其他设备(例如,接入点或任何类型的控制器等)来发送第一信息。该第一信息用于使得终端确定是否发起AI/ML操作类型的业务。根据实施例,该第一消息用于使得终端的接入(AS,Access Stratum)层或者非接入(NAS,Non Access Stratum)层确定是否发起AI/ML操作类型的业务。优选地,该第一消息用于使得终端的AS层确定是否发起AI/ML操作类型的业务。Referring to FIG. 2, in step S110, 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, other devices (eg, an access point or any type of controller, etc.) to send the first information. 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 make an access (AS, Access Stratum) layer or a non-access (NAS, Non Access Stratum) layer of the terminal determine whether to initiate an AI/ML operation type service. Preferably, the first message is used to make the AS layer of the terminal determine whether to initiate an AI/ML operation type service.
其中,基站向终端发送第一消息的具体方式本公开实施例不作限定,如可以通过***消息或者其他约定的方式向终端发送第一消息。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 through a system message or other agreed manner.
根据实施例,第一信息可以包括以下至少一项:与网络节点能力相关的信息;网络综合能力指示信息;与终端能力相关的信息;用于指示是否发起人工智能或机器学习操作类型的业务的直接指示信息。在以下描述中,用于指示是否发起人工智能或机器学习操作类型的业务的直接指示信息可以称为“直接指示信息”,除“直接指示信息”之外的信息可以称为“辅助信息”。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 instruction information. In the following description, direct indication information for indicating whether to initiate an artificial intelligence or machine learning operation type service may be referred to as "direct indication information", and information other than "direct indication information" may be referred to as "auxiliary information".
根据本公开的实施例,第一信息中的与网络节点能力相关的信息可以包括:至少一项网络节点能力指示信息。作为示例,至少一项网络节点能力指示信息可以包括以下至少一项:计算能力指示信息、无线资源能力指示信息、后向链路带宽指示信息。根据实施例,至少一项网络节点能力指示信息可以是网络节点(例如,基站)可以提供给AI/ML操作类型的业务的资源(例如,提供给AI/ML模型训练所使用的资源),也可以是网络节点已经被占用的资源。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 item of network node capability indication information. As an example, the at least one item of network node capability indication information may include at least one of the following: computing capability indication information, radio resource capability indication information, and backward link bandwidth indication information. According to an embodiment, the at least one item of network node capability indication information may be a resource that a network node (eg, a base station) can provide for AI/ML operation type services (eg, a resource provided for AI/ML model training), or It can be a resource already occupied by a network node.
仅作为非限制性的实施例,计算能力指示信息可以包括网络节点的内存、CPU、存储空间中的至少一者的占用情况(这可以以百分比或者高中低的形式来指示)或者网络的当前负载情况;无线资源能力指示信息可以包括网络节点提供的带宽、当前频谱利用率等,其也可以以百分比或者高中低的形式来指示;后向链路带宽指示信息可以包括基站与核心网网元之间的接口链路的带宽、或者基站与提供AI/ML服务的专用服务器之间的接口链路的带宽。As a non-limiting example only, the computing capability indication information may include the occupancy of at least one of the memory, CPU, storage space of the network node (this may be indicated in the form of a percentage or high, high, low) or the current load of the network situation; 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 percentage or high, medium and low; the backward link bandwidth indication information may include the relationship between the base station and the core network element. The bandwidth of the interface link between them, or the bandwidth of the interface link between the base station and the dedicated server that provides AI/ML services.
应注意的是,至少一项网络节点能力指示信息的示例不限于以上实施 例,例如,至少一项网络节点能力指示信息还可以包括网络节点广播的其能够支持的运算次数,例如,加乘运算的次数。It should be noted that the example of the at least one item of network node capability indication information is not limited to the above embodiments. For example, the at least one item of network node capability indication information may also include the number of operations broadcasted by the network node that it can support, such as addition and multiplication operations. number of times.
可选择地,第一信息中的与网络节点能力相关的信息还可以包括:与至少一项网络节点能力指示信息中的每一项网络节点能力指示信息相对应的门限。当至少一项网络节点能力指示信息为网络节点(例如,基站)可以提供给AI/ML操作类型的业务的可用资源(例如,提供给AI/ML模型训练使用的资源)时,门限可以是与可用资源相对应的门限。当至少一项网络节点能力指示信息为网络节点已经被占用的资源时,门限可以是与已经被占用的资源相对应的门限。然而,本发明构思不限于此,例如,当至少一项网络节点能力指示信息为网络节点已经被占用的资源时,门限可以是与可用资源相对应的门限,在此情况下,终端(例如,AS层)可以先基于与可用资源相对应的门限推断出与已经被占用的资源相对应的门限,然后根据至少一项网络节点能力指示信息以及推断出的门限,来确定是否可以发起AI/ML操作类型的业务。Optionally, the information related to the network node capability in the first information may further include: a threshold corresponding to each item of network node capability indication information in the at least one item of network node capability indication information. When at least one item of network node capability indication information is available resources (eg, resources provided for AI/ML model training) that the network node (eg, base station) can provide for AI/ML operation type services, the threshold may be the same as the one used for AI/ML model training. The threshold corresponding to the available resources. When the at least one item of network node capability indication information is a resource already occupied by the network node, the threshold may be a threshold corresponding to the already occupied resource. However, the inventive concept is not limited thereto, for example, when at least one item of network node capability indication information is a resource that has been occupied by the network node, the threshold may be a threshold corresponding to the available resources, in this case, the terminal (for example, AS layer) can first infer the threshold corresponding to the occupied resources based on the threshold corresponding to the available resources, and then determine whether AI/ML can be initiated according to at least one item of network node capability indication information and the inferred threshold Operation type business.
例如,在至少一项网络节点能力指示信息包括计算能力指示信息、无线资源能力指示信息和/或后向链路带宽指示信息的情况下,与网络节点能力相关的信息还可以包括:计算能力判决门限、无线资源能力判决门限和/或后向链路带宽判决门限。这些门限信息用于使得终端(例如,终端的AS层)将第一信息中的各项网络节点能力指示信息与相应的门限进行比较,以判决是否发起AI/ML操作类型的业务。这稍后将在终端(例如,终端的AS层)执行的判决步骤中进行详细描述。For example, in the case where at least one item of 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 further include: computation capability decision Threshold, radio resource capability decision threshold and/or backward link bandwidth decision threshold. The threshold information is used to make the terminal (eg, the AS layer of the terminal) compare each item of 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 (eg, the AS layer of the terminal).
根据本公开的实施例,第一信息中的网络综合能力指示信息是通过综合考虑上述的至少一项网络节点能力指示信息而获得的信息。例如,基站可以通过对网络节点的计算能力、无线资源能力和后向链路带宽进行综合评估来获得网络综合能力指示信息,例如,可以以信载量来表示网络综合能力指示信息。作为示例,信载量可以指网络节点当前已经承载的信载量或者网络节点剩余的信载量。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 item of network node capability indication information described above. For example, the base station can obtain the network comprehensive capability indication information by comprehensively evaluating the computing capability, radio 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 traffic capacity may refer to the traffic capacity currently carried by the network node or the remaining traffic capacity of the network node.
可选择地,第一信息中的网络综合能力指示信息还可以包括:与网络综合能力相对应的门限。例如,当以信载量来表示网络综合能力指示信息 时,网络综合能力指示信息还可以包括与信载量相对应的门限。类似地,该门限用于使得终端(例如,终端的AS层)将第一信息中的各项网络节点能力指示信息与相应的门限进行比较,以判决是否发起AI/ML操作类型的业务。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 make the terminal (eg, the AS layer of the terminal) compare each item of network node capability indication information in the first information with the corresponding threshold to determine whether to initiate an AI/ML operation type service.
作为示例,上述的门限信息(即,与所述至少一项网络节点能力指示信息中的每一项网络节点能力指示信息相对应的门限、与网络综合能力相对应的门限)可以包括在第一信息中,从而通过网络节点发送到终端;作为另一示例,这些门限信息可以不包括在第一信息中,即,不通过网络节点发送到终端,而是可以预先存储在终端或者与终端连接的其他设备中,在需要终端判决时可以直接使用预先存储或固化的门限信息;作为又一示例,终端可以在接收到第一信息之前预先获取门限信息;此外,网络节点还可以周期性地或者在需要时发送门限信息,对预先存储的门限信息进行更新。As an example, the above-mentioned threshold information (ie, the threshold corresponding to each item of network node capability indication information in the at least one item of network node capability indication information, the threshold corresponding to the network comprehensive capability) may be included in the first information, so as to be 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 connected to the terminal In other devices, the pre-stored or solidified threshold information can be directly used when the terminal needs to make a decision; as another example, the terminal can obtain the threshold information in advance before receiving the first information; in addition, the network node can also periodically or at When necessary, the threshold information is sent, and the pre-stored threshold information is updated.
根据本公开的实施例,第一信息中的与终端能力相关的信息可以包括:与至少一项终端能力信息的每一项终端能力信息相对应的门限。至少一项终端能力信息可以包括以下至少一项:终端计算能力信息、终端电量信息。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 item of terminal capability information of the at least one item of terminal capability information. The at least one item of terminal capability information may include at least one of the following: terminal computing capability information, terminal power information.
作为非限制性的实施例,网络节点(例如,基站)需要要求终端能力在达到特定门限的情况时才允许终端发起AI/ML操作类型的业务,例如,网络节点可以在与终端能力相关的信息中指定:终端当前计算能力余量需要达到的门限(例如,以百分比形式指示的终端的内存、CPU、存储空间中的至少一者的占用情况)、终端当前电量余量需要达到的门限(可以具有百分比的形式)和/或当终端电量低于要求的门限时需要终端处于充电状态等。As a non-limiting example, the network node (eg, base station) needs to allow the terminal to initiate an AI/ML operation type service only when the terminal capability reaches a certain threshold. Specified in: the threshold that the terminal's current computing capacity margin needs to reach (for example, the occupancy of at least one of the terminal's memory, CPU, and storage space indicated in the form of a percentage), the threshold that the terminal's current power margin needs to reach (can be In the form of a percentage) and/or when the terminal power is lower than the required threshold, the terminal needs to be in a charging state, etc.
根据实施例,可以通过主信息、剩余最小***消息(RMSI,Remaining Minimum System Information)或其他***消息(SI,System Information)中的至少一项来发送第一消息。According to an embodiment, the first message may be sent through at least one of main information, Remaining Minimum System Information (RMSI, Remaining Minimum System Information), or other system information (SI, System Information).
作为非限制性实施例,基站可以在RMSI或其他SI中通知终端第一消息中的辅助信息(即,与网络节点能力相关的信息、网络综合能力指示信息、与终端能力相关的信息);并且,基站可以通过主信息(例如,主 信息块MIB(Master Information Block))、RMSI或其他***消息(例如,***消息块SIB(System Information Block))来通知终端第一消息中的直接指示信息。As a non-limiting example, the base station may notify the terminal in RMSI or other SI of the auxiliary information in the first message (ie, information related to network node capabilities, network integrated capability indication information, information related to terminal capabilities); and , the base station can notify the terminal of the direct indication information in the first message through master information (for example, master information block MIB (Master Information Block)), RMSI or other system messages (for example, system message block SIB (System Information Block)).
在一个实施例中,基站可以利用***消息中的指示比特(一位或者更多位)来发送直接指示信息,以直接告知终端是否可以发起AI/ML操作类型的业务。例如,可以在MIB中携带该指示比特;再例如,可以在RMSI或者其他SIB中携带该指示比特。In one embodiment, the base station may use an indication bit (one or more bits) in the system message to send direct indication information to directly inform the terminal whether the AI/ML operation type service 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.
根据实施例,图2中所示的通信方法还可以包括:通过其他***消息(即,除了MIB和RMSI之外的其他***消息)发送第一消息时,响应于第一信息中包括的至少一项信息发生变更,不变更***消息中的***消息值标签(SI value tag)。According to an embodiment, the communication method shown in FIG. 2 may further include: when the first message is sent through other system messages (ie, other system messages except MIB and RMSI), in response to at least one of the first messages included in the first message When the item information is changed, the system message value tag (SI value tag) in the system message is not changed.
如果SI value tag变更,则基站需要通过发送寻呼消息(paging)来寻呼终端,相应地,终端需要监听paging以获取***消息的变更。根据本公开的实施例,即使第一信息中的包括的至少一项信息发生变更,也不变更SI value tag,这样基站不需要寻呼通知终端,而是终端在需要发起AI/ML操作类型的业务(即,发起AI/ML的接入)之前自己去监听***消息,以获得和/或更新第一消息,从而可以节省资源。也就是说,基站不需要占用资源发送寻呼消息,终端也不需要频繁接收或解析SI value tag,从而可以节省电力、传输和/或计算资源。If the SI value tag is changed, the base station needs to page the terminal by sending a paging message (paging), and accordingly, the terminal needs to monitor paging to obtain the change of the system message. According to the embodiment of the present disclosure, even if at least one item of information included in the first information is changed, the SI value tag is not changed, so that the base station does not need to notify the terminal by paging, but the terminal needs to initiate an AI/ML operation type when the Before the service (ie, initiating AI/ML access), it monitors system messages by itself to obtain and/or update the first message, thereby saving resources. That is, 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.
根据本公开的实施例,网络节点(例如,基站)可以针对不同的AI/ML操作类型的业务发送不同的第一信息。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.
作为示例,网络节点可以根据其所能够支持的AI/ML操作类型的业务向终端发送第一信息中的多项信息和/或指定第一信息中的有效信息的指示规则,终端可以根据指示规则来确定多项信息中的有效信息,并且根据有效信息来判决是否发起AI/ML操作类型的业务。作为非限制性示例,多项信息可以指示与网络节点能力相关的信息(例如,至少一项网络节点能力指示信息和/或对应的门限)、网络综合能力指示信息、与终端能力信息相关的信息(例如,与至少一项终端能力信息的每一项相对应的门限)和/或直接指示信息。As an example, the network node may send a plurality of pieces of information in the first information and/or an indication rule specifying valid information in the first information to the terminal according to the service of the AI/ML operation type that it can support, and the terminal may, according to the indication rule to determine the valid information among the multiple pieces of information, and to decide whether to initiate an AI/ML operation type service according to the valid information. As a non-limiting example, multiple pieces of information may indicate information related to network node capabilities (eg, at least one item of network node capability indication information and/or corresponding thresholds), network comprehensive capability indication information, and information related to terminal capability information (eg, a threshold corresponding to each item of at least one item of terminal capability information) and/or direct indication information.
可以理解的是,指示规则可以不通过网络节点来发送,而是预先写入或存储在终端或连接到终端的设备中,或者可以通过协议约定。例如,网络节点可以仅向终端发送多项信息(例如,计算能力指示信息、无线资源能力指示信息、后向链路带宽指示信息及其相应的门限)以及指定计算能力指示信息和无线资源能力指示信息为有效信息的指示规则,在此情况下,终端虽然接收到了多项信息,但是根据从本地获取的指示规则,而仅使用计算能力指示信息和无线资源能力指示信息以及对应的门限,来进行判决是否发起AI/ML操作类型的业务。It can be understood that the instruction rules may not be sent by the network node, but may be pre-written or stored in the terminal or a device connected to the terminal, or may be agreed through a protocol. For example, the network node may only send multiple pieces of information (eg, computing capability indication information, radio resource capability indication information, backward link bandwidth indication information and their corresponding thresholds) to the terminal, as well as designated computing capability indication information and radio resource capability indication The information is an indication rule for valid information. In this case, although the terminal has received multiple pieces of information, it only uses the computing capability indication information, the wireless resource capability indication information and the corresponding threshold according to the indication rule obtained from the local area. Determines whether to initiate an AI/ML operation type service.
作为另一示例,网络节点可以根据其所能够支持的AI/ML操作类型的业务预先确定哪些信息是有效的,从而仅向终端发送有效信息。例如,网络节点可以预先确定无线资源能力指示信息和/或终端电量信息的门限是有效信息,从而仅向终端发送无线资源能力指示信息和/或终端电量信息的门限,以使得终端利用他们判决是否发起AI/ML操作类型的业务。As another example, the network node may predetermine which information is valid according to the services of the AI/ML operation type that it can support, so as to send only 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, so as to only send the radio resource capability indication information and/or the threshold of the terminal power information to the terminal, so that the terminal can use them to decide whether to Initiate business of AI/ML operation type.
作为另一示例,网络节点可以综合考虑其能力信息(例如,网络节点能力指示信息)来确定直接指示信息,并且将直接指示信息发送到终端,以使得终端能够根据直接指示信息来直接判断是否发起AI/ML操作类型的业务。As another example, the network node may comprehensively consider its capability information (eg, network node capability indication information) to determine the direct indication information, and send the direct indication information to the terminal, so that the terminal can directly determine whether to initiate or not according to the direct indication information AI/ML operation type business.
作为又一示例,网络节点向终端发送的信息默认地均是有效的,因此终端可以利用所接收到的信息判决是否发起AI/ML操作类型的业务。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 decide whether to initiate an AI/ML operation type service.
继续参照图2,终端可以获取第一信息,并且基于获取的第一信息确定是否发起AI/ML操作类型的业务。根据实施例,基站可以通过***消息向终端发送第一消息,即将第一消息携带在***消息中,终端可以在需要发起AI/ML业务之前,获取***消息,以从***消息中获取第一信息。Continuing to refer to FIG. 2 , the terminal may acquire the first information, and determine whether to initiate an AI/ML operation type service based on the acquired first information. According to an embodiment, the base station may send the first message to the terminal through the system message, that is, carry the first message in the system message, and the terminal may obtain the system message before initiating the AI/ML service, so as to obtain the first information from the system message .
根据实施例,可以通过终端的AS层或者NAS层来执行上述操作。优选地,在本公开的实施例中,可以通过终端的AS层来执行上述获取和确定的操作。终端的AS层相比于NAS层而言,基站对于终端的行为更加可控,这是因为策略都是基站提供的,终端按照所提供的策略进行判决即可。而对于NAS层而言,有一些判决条件和用户有关(例如,用户的喜好和隐私保护),其判决相对复杂。According to the embodiment, the above operations may be performed through the AS layer or the NAS layer of the terminal. Preferably, in the embodiment of the present disclosure, the above-mentioned acquisition and determination operations may be performed through the AS layer of the terminal. Compared with the NAS layer, the AS layer of the terminal is more controllable for the behavior of the terminal, because the policies are provided by the base station, and the terminal can make a decision according to the provided policy. For the NAS layer, some decision conditions are related to users (eg, user preferences and privacy protection), and the decision is relatively complicated.
当终端的AS层基于获取的第一信息确定是否发起AI/ML操作类型的业务时,可以向终端的NAS层通知该确定的结果,从而NAS层根据确定的结果执行相应的操作。例如,当终端的AS层基于获取的第一信息确定可以发起AI/ML操作类型的业务时,在步骤S120中,NAS层可以执行发起AI/ML操作类型的业务。When the AS layer of the terminal determines whether to initiate an AI/ML operation type service based on the acquired first information, it may notify the NAS layer of the terminal of the determination result, so that the NAS layer performs corresponding operations according to the determined result. For example, when the AS layer of the terminal determines based on the acquired first information that the service of the AI/ML operation type can be initiated, in step S120, the NAS layer can execute the service of initiating the AI/ML operation type.
终端(例如,AS层)基于获取的第一信息确定是否发起AI/ML操作类型的业务,可以包括以下至少一项:The terminal (for example, 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:
响应于与网络节点能力相关的信息中的至少一项信息与相对应的门限比较的结果,确定是否发起AI/ML操作类型的业务;In response to a result of comparing at least one item of information related to the network node capability with a corresponding threshold, determining whether to initiate an AI/ML operation type service;
响应于网络综合能力指示信息与相对应的门限比较的结果,确定是否发起AI/ML操作类型的业务;In response to the result of comparing the network comprehensive capability indication information with the corresponding threshold, determine whether to initiate an AI/ML operation type service;
响应于与终端能力相关的信息中的至少一项信息与相对应的门限比较的结果,确定是否发起AI/ML操作类型的业务;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 an AI/ML operation type service;
响应于直接指示信息,直接确定是否发起AI/ML操作类型的业务。In response to the direct indication information, it is directly determined whether to initiate a service of the AI/ML operation type.
与上文相似地,网络节点可以针对不同的AI/ML操作类型的业务发送不同的第一信息,终端可以基于网络节点发送的信息来进行判决,以确定是否发起AI/ML操作类型的业务。当终端从基站接收到不同的第一信息时,可以从第一信息中判断哪些信息是有效的(类似于步骤S110所描述的),或者判断各项信息的优先级。例如,当终端接收到来自基站的直接指示信息以及其他辅助信息时,可以将直接指示信息确定为具有最高优先级,从而优先基于或者仅基于直接指示信息来判决是否可以发起AI/ML操作类型的业务。Similar to the above, the network node may send different first information for services of different AI/ML operation types, and the terminal may make a decision based on the information sent by the network node to determine whether to initiate the AI/ML operation type service. When the terminal receives different first information from the base station, it can judge which information is valid from the first information (similar to that described in step S110 ), or judge the priority of each piece of information. For example, when the terminal receives the direct indication information and other auxiliary information from the base station, the direct indication information may be determined as having the highest priority, so as to decide whether to initiate an AI/ML operation type based on the direct indication information preferentially or only based on the direct indication information. business.
作为一个实施例,终端(例如,AS层)可以判决基站在第一消息中所提供的计算能力指示信息是否满足发起AI/ML操作类型的业务(例如,AI/ML模型训练的接入)所需要的资源需求。如果不满足,则认为该类型的AI/ML业务部允许接入该小区(或基站),如果满足,则通知NAS层可以发起AI/ML操作类型的业务。例如,终端(例如,AS层)可以将网络节点可以提供的资源(例如,可以提供的内存、CPU和/或存储空间的大小)与相应门限进行比较,以通过判决网络节点提供的资源是否达到相 应门限,来确定是否可以发起AI/ML操作类型的业务。再例如,终端(例如,AS层)可以判决网络当前负载是否低于相对应的门限,来确定是否可以发起AI/ML操作类型的业务。As an embodiment, the terminal (eg, the AS layer) may determine whether the computing capability indication information provided by the base station in the first message satisfies the requirements for initiating a service of an AI/ML operation type (eg, access for AI/ML model training). required resource requirements. If it is not satisfied, it is considered that the AI/ML service part of this type is allowed to access the cell (or base station). For example, the terminal (eg, AS layer) can compare the resources (eg, the size of memory, CPU, and/or storage space that can be provided) that can be provided by the network node with the corresponding threshold, so as to determine whether the resources provided by the network node reach the threshold. The corresponding threshold is used to determine whether AI/ML operation type services can be initiated. For another example, the terminal (for example, the AS layer) may determine whether the current load of the network is lower than a corresponding threshold to determine whether the AI/ML operation type service can be initiated.
作为一个实施例,终端(例如,AS层)可以判决基站在第一消息中所提供的无线资源能力指示信息是否满足发起AI/ML操作类型的业务(例如,AI/ML模型训练的接入)所需要的资源需求。如果不满足,则认为该类型的AI/ML业务部允许接入该小区(或基站),如果满足,则通知NAS层可以发起AI/ML操作类型的业务。例如,终端(例如,AS层)可以通过判决网络节点提供的资源(例如,网络节点提供的带宽)是否达到相应门限,或者通过判决网络当前频率利用率是否低于相应门限,来确定是否可以发起AI/ML操作类型的业务。As an embodiment, the terminal (for example, the AS layer) may decide whether the radio resource capability indication information provided by the base station in the first message satisfies the service of initiating AI/ML operation type (for example, the access of AI/ML model training) required resource requirements. If it is not satisfied, it is considered that the AI/ML service part of this type is allowed to access the cell (or base station). For example, the terminal (for example, the AS layer) can determine whether it can initiate the operation by judging whether the resources provided by the network node (for example, the bandwidth provided by the network node) reach the corresponding threshold, or by judging whether the current frequency utilization rate of the network is lower than the corresponding threshold. AI/ML operation type business.
作为一个实施例,终端(例如,AS层)可以判决基站在第一消息中所提供的后向链路带宽指示信息是否满足发起AI/ML操作类型的业务(例如,AI/ML模型训练的接入)所需要的资源需求。如果不满足,则认为该类型的AI/ML业务部允许接入该小区(或基站),如果满足,则通知NAS层可以发起AI/ML操作类型的业务。例如,通过判决网络节点提供的资源(例如,网络节点提供的后向链路带宽的大小)是否达到相应门限,来确定是否可以发起AI/ML操作类型的业务。As an embodiment, the terminal (for example, the AS layer) may decide whether the backward link bandwidth indication information provided by the base station in the first message satisfies the service of initiating AI/ML operation type (for example, the connection for AI/ML model training). input) required resource requirements. If it is not satisfied, it is considered that the AI/ML service part of this type is allowed to access the cell (or base station). For example, whether the AI/ML operation type service can be initiated is determined by judging whether the resources provided by the network node (eg, the size of the backward link bandwidth provided by the network node) reach a corresponding threshold.
作为一个实施例,终端(例如,AS层)可以将第一消息中的网络综合能力指示信息(例如,信载量)与相应门限进行比较,来确定是否可以发起AI/ML操作类型的业务。As an embodiment, the terminal (eg, AS layer) may compare the network comprehensive capability indication information (eg, the signal load) in the first message with a corresponding threshold to determine whether to initiate an AI/ML operation type service.
作为一个实施例,终端(例如,AS层)可以将自身的计算能力与第一消息的终端计算能力信息所指示的相应门限进行比较,或者将终端自身的剩余电量与终端计算能力信息所指示的相应门限进行比较,来确定可以是否发起AI/ML操作类型的业务。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 itself with the terminal computing capability information indicated by the terminal computing capability information. The corresponding thresholds are compared to determine whether the AI/ML operation type service can be initiated.
根据本公开的实施例,终端(例如,AS层)可以将上述实施例中的一个或更多个进行组合来确定是否可以发起AI/ML操作类型的业务。例如,终端可以判决基站的计算能力信息和终端的计算能力是否都足够发起AI/ML操作类型的业务。According to an embodiment of the present disclosure, a terminal (eg, the AS layer) may combine one or more of the above-described 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 both sufficient to initiate an AI/ML operation type service.
根据实施例,图2中所示的通信方法还可以包括:估计即将发起的AI/ML操作类型的业务所需的资源。在此情况下,终端(例如,AS层)可以基于所估计的资源和/或第一信息确定是否发起AI/ML操作类型的业务。According to an embodiment, the communication method shown in FIG. 2 may further comprise: estimating the resources required for the service of the AI/ML operation type to be initiated. In this case, the terminal (eg, AS layer) may determine whether to initiate AI/ML operation type services based on the estimated resources and/or the first information.
例如,终端的AS层可以通过历史记录或者其他高层的指示,或者,终端的AS层可以基于历史统计信息和/或用户行为(例如,用户当前的通信行为),预先估计即将发起的AI/ML操作类型的业务所需的资源,从而得到发起的AI/ML模型训练的接入的资源需求。作为示例,历史记录可以是终端先前发起AI/ML操作类型的业务时所使用的资源的记录信息。历史统计信息可以是通过对先前发起AI/ML操作类型的业务时所使用的资源的记录信息进行统计学计算而获得的信息。相应地,终端的AS层可以判决网络节点提供的资源是否满足该资源需求(即,将网络节点提供的资源与该资源需求进行比较),以确定是否发起AI/ML操作类型的业务。For example, the AS layer of the terminal can use historical records or other high-level instructions, or the AS layer of the terminal can pre-estimate the AI/ML to be initiated based on historical statistical information and/or user behavior (eg, the user's current communication behavior). The resources required by the operation type of business, so as to obtain the resource requirements of the initiated AI/ML model training access. As an example, the history record may be record information of resources used when the terminal previously initiated the AI/ML operation type service. The historical statistical information may be information obtained by performing statistical calculation on the record information of resources used when a service of the AI/ML operation type was previously initiated. Accordingly, the AS layer of the terminal can judge whether the resources provided by the network node meet the resource requirements (ie, compare the resources provided by the network nodes with the resource requirements) to determine whether to initiate an AI/ML operation type service.
例如,终端可以预先估计即将发起的AI/ML操作类型的业务所需的内存、CPU、存储空间中的至少一者,并且将估计的值与网络节点在计算能力指示信息中所提供的值进行比较,以确定是否发起AI/ML操作类型的业务。For example, the terminal may estimate in advance at least one of 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 Compare to determine whether to initiate an AI/ML operation type business.
例如,终端可以预先估计即将发起的AI/ML操作类型的业务所需的加乘运算次数,并且将估计的次数与网络广播支持的加乘运算次数进行比较,以确定是否发起AI/ML操作类型的业务。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 of times with the number of addition and multiplication operations supported by the network broadcast to determine whether to initiate the AI/ML operation type Business.
例如,终端可以预先估计即将发起的AI/ML操作类型的业务所需要的带宽(例如,预估带宽),并且将预估带宽与网络节点在无线资源指示信息中提供的带宽大小进行比较,以确定是否发起AI/ML操作类型的业务。For example, the terminal may pre-estimate the bandwidth (for example, the estimated bandwidth) required by the AI/ML operation type service to be initiated, and compare the estimated bandwidth with the bandwidth provided by the network node in the radio resource indication information to obtain Determines whether to initiate an AI/ML operation type business.
例如,终端可以预先估计即将发起的AI/ML操作类型的业务所需要的后向带宽,并且将所需要的后向带宽与网络提供的后向链路带宽的大小进行比较,以确定是否发起AI/ML操作类型的业务。For example, the terminal can pre-estimate the required backward bandwidth of the AI/ML operation type to be initiated, and compare the required backward bandwidth with the bandwidth of the backward link provided by the network to determine whether to initiate AI /ML operation type business.
根据实施例,图2所示的通信方法还可以包括:响应于确定不允许发起AI/ML操作类型的业务并且仅存在发起AI/ML操作类型的业务,将小 区状态标识为“小区禁止(cell bar)”。According to an embodiment, the communication method shown in FIG. 2 may further include: in response to determining that the AI/ML operation type service is not allowed to be initiated and only the AI/ML operation type service is initiated, identifying the cell state as "cell prohibited (cell prohibited)" bar)".
在一个实施例中,对于仅仅需要发起AI/ML模型训练接入的终端而言,如果该终端的AS层判断结果为不允许接入,则表示该小区状态为cell bar。也就是说,该小区对于该终端而言是被禁止的,那么该终端会发起小区重选,即,该终端选择另外小区去驻留。此外,该终端可以在该另外小区接收***消息,并且尝试发起AI/ML操作类型的业务。In one embodiment, for a terminal that only needs to initiate AI/ML model training access, if the AS layer judgment result of the terminal is that access is not allowed, it means that the cell state is cell bar. That is, if the cell is prohibited for the terminal, the terminal will initiate cell reselection, that is, the terminal selects another cell to camp on. Furthermore, the terminal may receive system messages in the further cell and attempt to initiate AI/ML operation type traffic.
在一个实施例中,对于非仅仅需要发起AI/ML模型训练接入的终端而言,如果该终端的AS层判断结果为不允许接入,则通知NAS层,当前小区对于AI/ML模型接入为禁止,但是可以发起其他业务(例如,呼叫业务);如果该终端的AS层判断结果为允许接入,否则通知NAS层,当前小区对于AI/ML模型接入为允许。In one embodiment, for a terminal that not only needs to initiate AI/ML model training access, if the AS layer judgment result of the terminal is that access is not allowed, the NAS layer is notified that the current cell has access to the AI/ML model. Access is prohibited, but other services (for example, call services) can be initiated; if the AS layer of the terminal judges that access is allowed, otherwise the NAS layer is notified that the current cell is allowed to access the AI/ML model.
根据本公开实施例的上述通信方法能够尽早通知终端与网络相关的信息,以合理地限制或者允许终端发起AI/ML操作类型的业务。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.
图3是示出根据本公开的实施例的通信设备300的示意图。FIG. 3 is a schematic diagram illustrating a communication device 300 according to an embodiment of the present disclosure.
参照图3,通信设备300可以包括通信模块310。通信模块310被配置为:发送第一信息。第一信息用于使得终端确定是否发起人工智能或机器学习操作类型的业务。关于第一信息的描述类似于图2中的步骤S110,为了简明在此省略重复的描述。Referring to FIG. 3 , the communication device 300 may include a communication module 310 . The communication module 310 is configured to: send the first information. The first information is used to enable the terminal to determine whether to initiate an artificial intelligence or machine learning operation type service. The description about the first information is similar to step S110 in FIG. 2 , and repeated descriptions are omitted here for brevity.
根据本公开的实施例,通信模块可以是基站侧的节点、无线局域网中的接入点、或其他控制设备。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.
根据实施例,通信模块310可以被配置为通过主信息、剩余最小***消息或其他***消息中的至少一项来发送所述第一消息。According to an embodiment, the communication module 310 may be configured to transmit the first message through at least one of a master message, a remaining minimum system message, or other system messages.
将理解,图3中所示的通信设备300的结构仅是示例性的,本公开的实施例不限于此,例如,通信设备300还可以包括处理AI/ML操作类型的业务的处理设备、或者通过核心网与提供AI/ML操作类型的业务的专用服务器进行通信的设备等。It will be understood that the structure of the communication device 300 shown in FIG. 3 is only exemplary, and embodiments of the present disclosure are not limited thereto, for example, the communication device 300 may further include a processing device for processing AI/ML operation type services, or A device that communicates with a dedicated server that provides AI/ML operation type services through the core network, etc.
根据实施例,通信设备300中的处理模块可以被配置为通过其他***消息发送所述第一消息时,响应于所述第一信息中包括的至少一项信息发生变更,不变更所述***消息中的***消息值标签。According to an embodiment, the processing module in the communication device 300 may be configured to not change the system message in response to at least one item of information included in the first information being changed when the first message is sent through other system messages The system message value label in .
通信设备300可以执行上述参照图2所描述的步骤S110中的操作,为了简明,在此省略重复的描述。The communication device 300 may perform the operations in step S110 described above with reference to FIG. 2 , and repeated descriptions are omitted here for brevity.
图4是示出根据本公开的实施例的另一通信设备400的示意图。FIG. 4 is a schematic diagram illustrating another communication device 400 according to an embodiment of the present disclosure.
参照图4,通信设备400可以包括通信模块410和处理模块420。Referring to FIG. 4 , the communication device 400 may include a communication module 410 and a processing module 420 .
根据本公开的实施例,通信模块410可以被配置为获取第一信息。处理模块420可以被配置为:基于第一信息确定是否发起AI/ML操作类型的业务。根据实施例,通信模块410和处理模块420可以包括在终端的AS层或NAS层中。优选地,通信模块410和处理模块420均可以包括终端的AS层中。According to an embodiment of the present disclosure, the communication module 410 may be configured to acquire the first information. The processing module 420 may be configured to: determine whether to initiate an AI/ML operation type service 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 the NAS layer of the terminal. Preferably, both the communication module 410 and the processing module 420 may be included in the AS layer of the terminal.
根据本公开的实施例,处理模块420执行的基于所述第一信息确定是否发起人工智能或机器学习操作类型的业务的操作可以包括以下至少一项: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:
响应于与网络节点能力相关的信息中的至少一项信息与相对应的门限比较的结果,确定是否发起人工智能或机器学习操作类型的业务;In response to a result of comparing at least one item of information related to the network node capability with a corresponding threshold, determining whether to initiate an artificial intelligence or machine learning operation type service;
响应于网络综合能力指示信息与相对应的门限比较的结果,确定是否发起人工智能或机器学习操作类型的业务;In response to the result of comparing the network comprehensive capability indication information with the corresponding threshold, determine whether to initiate an artificial intelligence or machine learning operation type service;
响应于与终端能力相关的信息中的至少一项信息与相对应的门限比较的结果,确定是否发起人工智能或机器学习操作类型的业务;In response to a result of comparing at least one piece of information related to the terminal capability with a corresponding threshold, determining whether to initiate an artificial intelligence or machine learning operation type service;
响应于直接指示信息,直接确定是否发起人工智能或机器学习操作类型的业务。In response to the direct indication information, it is directly determined whether to initiate an artificial intelligence or machine learning operation type business.
处理模块420可以执行与参照图2描述的终端(例如,AS层)的判决操作相类似的操作,为了简明,在此省略重复的描述。The processing module 420 may perform operations similar to the decision operation of the terminal (eg, the AS layer) described with reference to FIG. 2 , and repeated descriptions are omitted here for brevity.
根据本公开的实施例,处理模块420还可以被配置为:估计即将发起的人工智能或机器学习操作类型的业务所需的资源,并且基于所估计的资源和/或所述第一信息确定是否发起人工智能或机器学习操作类型的业务。According to an embodiment of the present disclosure, the processing module 420 may be further configured to: estimate the resources required for a business of the type of artificial intelligence or machine learning operation to be initiated, and determine whether to Launch an AI or machine learning operation type business.
根据本公开的实施例,处理模块420还可以被配置为:响应于确定不允许发起人工智能或机器学习操作类型的业务并且仅存在发起人工智能或机器学习操作类型的业务,将小区状态标识为“小区禁止”。According to an embodiment of the present disclosure, the processing module 420 may be further configured to: in response to determining that initiation of services of the artificial intelligence or machine learning operation type is not allowed and that there are only services of the initiation artificial intelligence or machine learning operation type, identify the cell status as "Cell Prohibition".
将理解,图4中所示的通信设备400的结构仅是示例性的,本公开的 实施例不限于此,例如,通信设备400还可以包括NAS层,用于从AS层接收确定的结果,并且在AS层确定允许接入时,NAS层可以发起人工智能或机器学习操作类型的业务。再例如,通信设备400还可以包括用于存储各种数据和信息的存储器,和/或向网络节点传送AI/ML操作类型的业务所需的数据的发送模块等。It will be understood that the structure of the communication device 400 shown in FIG. 4 is only exemplary, and embodiments of the present disclosure are not limited thereto, for example, the communication device 400 may further include a NAS layer for receiving the determined result from the AS layer, And when the AS layer determines to allow access, the NAS layer can initiate artificial intelligence or machine learning operations. For another example, the communication device 400 may further 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 network nodes, and the like.
需要说明的是,由于本公开实施例所提供的设备为可以执行本公开实施例中所提供的相应方法的设备,故而基于本公开实施例中所提供的方法,本领域所属技术人员能够了解本公开实施例的设备的具体实施方式以及其各种变化形式,所以在此对于该设备如何实现本公开实施例中的方法不再详细介绍。只要本领域所属技术人员实施本公开实施例中的方法所采用的设备,都属于本公开所欲保护的范围。其中,上述设备中所包含的各模块具体可以通过软件和/或硬件实现。It should be noted that, because the devices provided in the embodiments of the present disclosure are devices that can execute the corresponding methods provided in the embodiments of the present disclosure, those skilled in the art can understand the The specific implementation of the device in the disclosed embodiment and its various modifications are not described in detail here for how the device implements the method in the embodiment of the present disclosure. As long as the devices used by those skilled in the art to implement the methods in the embodiments of the present disclosure fall within the scope of the intended protection of the present disclosure. Wherein, each module included in the above device may be specifically implemented by software and/or hardware.
本公开还提供了一种电子设备,该电子设备可以包括至少一个处理器,该处理器可以被配置为用于执行本公开任一可选实施例中所提供的方法。The present disclosure also provides an electronic device, which may include at least one processor, and the processor may be configured to perform the method provided in any optional embodiment of the present disclosure.
可选的,该电子设备可以包括至少一个存储器,该存储器中存储有计算机程序(或者也可以称为计算机指令或代码),上述至少一个处理器在运行该运行计算机程序时可以执行本公开任一可选实施例所示的通信方法。Optionally, the electronic device may include at least one memory in which a computer program (or may also be referred to as computer instructions or codes) is stored, and the at least one processor may execute any one of the present disclosure when running the computer program. The communication method shown in the optional embodiment.
本公开还提供了一种计算机可读存储介质,该存储介质中存储有计算机程序,计算机程序在被处理器运行时能够执行本公开任一可选实施例所示的通信方法。The present disclosure also provides a computer-readable storage medium, where a computer program is stored, and when the computer program is executed by a processor, the computer program can execute the communication method shown in any optional embodiment of the present disclosure.
作为非限制性示例,图5示出了一种能够适用于本公开所提供的方案的电子设备的结构示意图。如图7所示,该电子设备5000包括:处理器5001和存储器5003。其中,处理器5001和存储器5003相连,如通过总线5002相连。可选地,电子设备5000还可以包括收发器5004。需要说明的是,实际应用中收发器5004不限于一个,该电子设备5000的结构并不构成对本公开实施例的限定。As a non-limiting example, FIG. 5 shows a schematic structural diagram of an electronic device that can be applied to the solution provided by the present disclosure. As shown in FIG. 7 , the electronic device 5000 includes: a processor 5001 and a memory 5003 . The processor 5001 is connected to the memory 5003, for example, through a bus 5002. Optionally, the electronic device 5000 may also include a transceiver 5004 . It should be noted that in practical applications, the transceiver 5004 is not limited to one, and the structure of the electronic device 5000 does not constitute a limitation to the embodiments of the present disclosure.
处理器5001可以是CPU(Central Processing Unit,中央处理器)、通用处理器、DSP(Digital Signal Processor,数据信号处理器)、ASIC (Application Specific Integrated Circuit,专用集成电路)、FPGA(Field Programmable Gate Array,现场可编程门阵列)或者其他可编程逻辑器件、晶体管逻辑器件、硬件部件或者其任意组合。其可以实现或执行结合本公开公开内容所描述的各种示例性的逻辑方框、模块和电路。处理器5001也可以是实现计算功能的组合,例如包含一个或多个微处理器组合,DSP和微处理器的组合等。The processor 5001 can be CPU (Central Processing Unit, central processing unit), general-purpose processor, DSP (Digital Signal Processor, data signal processor), ASIC (Application Specific Integrated Circuit, application-specific integrated circuit), FPGA (Field Programmable Gate Array) , field programmable gate array) or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It may implement or execute the various exemplary logical blocks, modules and circuits described in connection with this disclosure. The processor 5001 may also be a combination that realizes computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, and the like.
总线5002可包括一通路,在上述组件之间传送信息。总线5002可以是PCI(Peripheral Component Interconnect,外设部件互连标准)总线或EISA(Extended Industry Standard Architecture,扩展工业标准结构)总线等。总线5002可以分为地址总线、数据总线、控制总线等。为便于表示,图5中仅用一条粗线表示,但并不表示仅有一根总线或一种类型的总线。The bus 5002 may include a path to transfer information between the components described above. The bus 5002 may be a PCI (Peripheral Component Interconnect, Peripheral Component Interconnect Standard) bus or an EISA (Extended Industry Standard Architecture, Extended Industry Standard Architecture) bus or the like. The bus 5002 can be divided into an address bus, a data bus, a control bus, and the like. For ease of presentation, only one thick line is used in FIG. 5, but it does not mean that there is only one bus or one type of bus.
存储器5003可以是ROM(Read Only Memory,只读存储器)或可存储静态信息和指令的其他类型的静态存储设备,RAM(Random Access Memory,随机存取存储器)或者可存储信息和指令的其他类型的动态存储设备,也可以是EEPROM(Electrically Erasable Programmable Read Only Memory,电可擦可编程只读存储器)、CD-ROM(Compact Disc Read Only Memory,只读光盘)或其他光盘存储、光碟存储(包括压缩光碟、激光碟、光碟、数字通用光碟、蓝光光碟等)、磁盘存储介质或者其他磁存储设备、或者能够用于携带或存储具有指令或数据结构形式的期望的程序代码并能够由计算机存取的任何其他介质,但不限于此。The memory 5003 can be a ROM (Read Only Memory, read only memory) or other types of static storage devices that can store static information and instructions, a RAM (Random Access Memory, random access memory) or other types of storage devices that can store information and instructions. Dynamic storage device, can also be EEPROM (Electrically Erasable Programmable Read Only Memory, electrically erasable programmable read only memory), CD-ROM (Compact Disc Read Only Memory, CD-ROM) or other optical disk storage, optical disk storage (including compressed compact disc, laser disc, compact disc, digital versatile disc, blu-ray disc, etc.), magnetic disk storage medium or other magnetic storage device, or capable of carrying or storing desired program code in the form of instructions or data structures and capable of being accessed by a computer any other medium, but not limited to this.
存储器5003用于存储执行本公开方案的应用程序代码(计算机程序),并由处理器5001来控制执行。处理器5001用于执行存储器5003中存储的应用程序代码,以实现前述任一方法实施例所示的内容。The memory 5003 is used for storing application program codes (computer programs) for executing the solutions of the present disclosure, and the execution is controlled by the processor 5001 . The processor 5001 is configured to execute the application program code stored in the memory 5003, so as to realize the content shown in any of the foregoing method embodiments.
应该理解的是,虽然附图的流程图中的各个步骤按照箭头的指示依次显示,但是这些步骤并不是必然按照箭头指示的顺序依次执行。除非本文中有明确的说明,这些步骤的执行并没有严格的顺序限制,其可以以其他的顺序执行。而且,附图的流程图中的至少一部分步骤可以包括多个子步骤或者多个阶段,这些子步骤或者阶段并不必然是在同一时刻执行完成,而是可以在不同的时刻执行,其执行顺序也不必然是依次进行,而是可以 与其他步骤或者其他步骤的子步骤或者阶段的至少一部分轮流或者交替地执行。It should be understood that although the various steps in the flowchart of the accompanying drawings are sequentially shown in the order indicated by the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless explicitly stated herein, the execution of these steps is not strictly limited to the order and may be performed 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 may be executed at different times, and the execution sequence is also It does not have to be performed sequentially, but may be performed alternately or alternately with other steps or at least a portion of sub-steps or stages of other steps.
以上所述仅是本公开的部分实施方式,应当指出,对于本技术领域的普通技术人员来说,在不脱离本公开原理的前提下,还可以做出若干改进和润饰,这些改进和润饰也应视为本公开的保护范围。The above are only some embodiments of the present disclosure. It should be pointed out that for those skilled in the art, several improvements and modifications can be made without departing from the principles of the present disclosure. It should be regarded as the protection scope of the present disclosure.
Claims (24)
- 一种通信方法,所述通信方法包括:A communication method, the communication method comprising:发送第一信息,其中,所述第一信息用于使得终端确定发起人工智能或机器学习操作类型的业务。Sending first information, where the first information is used to enable the terminal to determine to initiate a service of an artificial intelligence or machine learning operation type.
- 根据权利要求1所述的通信方法,其中,所述第一信息用于使得终端的接入层确定发起人工智能或机器学习操作类型的业务。The communication method according to claim 1, wherein the first information is used to enable the access layer of the terminal to determine to initiate a service of an artificial intelligence or machine learning operation type.
- 根据权利要求1或2所述的通信方法,其中,所述第一信息包括以下至少一项:The communication method according to claim 1 or 2, wherein the first information includes at least one of the following:与网络节点能力相关的信息;Information related to network node capabilities;网络综合能力指示信息;Network comprehensive capability indication information;与终端能力相关的信息;information related to the capabilities of the terminal;用于指示发起人工智能或机器学习操作类型的业务的直接指示信息。Direct indication information for initiating a business of the type of artificial intelligence or machine learning operation.
- 根据权利要求3所述的通信方法,其中,所述与网络节点能力相关的信息包括:至少一项网络节点能力指示信息。The communication method according to claim 3, wherein the information related to the network node capability comprises: at least one item of network node capability indication information.
- 根据权利要求4所述的通信方法,其中,所述网络综合能力指示信息是通过综合考虑所述至少一项网络节点能力指示信息而获得的信息。The communication method according to claim 4, wherein the network comprehensive capability indication information is information obtained by comprehensively considering the at least one item of network node capability indication information.
- 根据权利要求4所述的通信方法,其中,所述与网络节点能力相关的信息还包括:与所述至少一项网络节点能力指示信息中的每一项网络节点能力指示信息相对应的门限。The communication method according to claim 4, wherein the information related to the network node capability further comprises: a threshold corresponding to each item of network node capability indication information in the at least one item of network node capability indication information.
- 根据权利要求5所述的通信方法,其中,所述网络综合能力指示信息还包括:与网络综合能力相对应的门限。The communication method according to claim 5, wherein the network comprehensive capability indication information further comprises: a threshold corresponding to the network comprehensive capability.
- 根据权利要求3所述的通信方法,其中,所述与终端能力相关的信息包括:与至少一项终端能力信息的每一项终端能力信息相对应的门限。The communication method according to claim 3, wherein the information related to the terminal capability comprises: a threshold corresponding to each item of terminal capability information of the at least one item of terminal capability information.
- 根据权利要求1所述的通信方法,其中,所述发送第一信息包括:通过主信息、剩余最小***消息或其他***消息中的至少一项来发送所述第一消息。The communication method according to claim 1, wherein the sending the first information comprises: sending the first message through at least one of master information, remaining minimum system messages or other system messages.
- 根据权利要求9所述的通信方法,其中,所述通信方法还包括:The communication method according to claim 9, wherein the communication method further comprises:通过其他***消息发送所述第一消息时,响应于所述第一信息中包括的至少一项信息发生变更,不变更所述***消息中的***消息值标签。When the first message is sent through other system messages, in response to at least one item of information included in the first information being changed, the system message value label in the system message is not changed.
- 一种通信方法,所述通信方法包括:A communication method, the communication method comprising:获取第一信息;obtain first information;基于所述第一信息确定发起人工智能或机器学习操作类型的业务。Based on the first information, it is determined to initiate a business of an artificial intelligence or machine learning operation type.
- 根据权利要求11所述的通信方法,其中,所述获取和所述确定是通过终端的接入层来执行的,The communication method of claim 11, wherein the acquiring and the determining are performed through an access layer of the terminal,其中,所述通信方法还包括:Wherein, the communication method further includes:向所述终端的非接入层通知所述确定的结果。The determination result is notified to the non-access stratum of the terminal.
- 根据权利要求11或12所述的通信方法,其中,所述第一信息包括以下至少一项:The communication method according to claim 11 or 12, wherein the first information includes at least one of the following:与网络节点能力相关的信息;Information related to network node capabilities;网络综合能力指示信息;Network comprehensive capability indication information;与终端能力相关的信息;information related to the capabilities of the terminal;用于指示发起人工智能或机器学习操作类型的业务的直接指示信息。Direct indication information for initiating a business of the type of artificial intelligence or machine learning operation.
- 根据权利要求13所述的通信方法,其中,所述与网络节点能力相关的信息包括:至少一项网络节点能力指示信息。The communication method according to claim 13, wherein the information related to the network node capability comprises: at least one item of network node capability indication information.
- 根据权利要求14所述的通信方法,其中,所述网络综合能力指示信息是通过综合考虑所述至少一项网络节点能力指示信息而获得的信息。The communication method according to claim 14, wherein the network comprehensive capability indication information is information obtained by comprehensively considering the at least one item of network node capability indication information.
- 根据权利要求14所述的通信方法,其中,所述与网络节点能力相关的信息还包括:与所述至少一项网络节点能力指示信息中的每一项网络节点能力指示信息相对应的门限。The communication method according to claim 14, wherein the information related to the network node capability further comprises: a threshold corresponding to each item of network node capability indication information in the at least one item of network node capability indication information.
- 根据权利要求15所述的通信方法,其中,所述网络综合能力指示信息还包括:与网络综合能力相对应的门限。The communication method according to claim 15, wherein the network comprehensive capability indication information further comprises: a threshold corresponding to the network comprehensive capability.
- 根据权利要求13所述的通信方法,其中,所述与终端能力相关的信息包括:与至少一项终端能力信息的每一项终端能力信息相对应的门限。The communication method according to claim 13, wherein the information related to the terminal capability comprises: a threshold corresponding to each item of terminal capability information of the at least one item of terminal capability information.
- 根据权利要求13所述的通信方法,其中,基于所述第一信息确定发起人工智能或机器学习操作类型的业务,包括以下至少一项:The communication method according to claim 13, wherein determining to initiate a service of an artificial intelligence or machine learning operation type based on the first information comprises at least one of the following:响应于所述与网络节点能力相关的信息中的至少一项信息与相对应的门限比较的结果,确定发起人工智能或机器学习操作类型的业务;In response to a result of comparing at least one piece of 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;响应于所述网络综合能力指示信息与相对应的门限比较的结果,确定发起人工智能或机器学习操作类型的业务;In response to the result of comparing the network comprehensive capability indication information with the corresponding threshold, determine to initiate an artificial intelligence or machine learning operation type service;响应于所述与终端能力相关的信息中的至少一项信息与相对应的门限比较的结果,确定发起人工智能或机器学习操作类型的业务;In response to a result of comparing at least one piece of information related to the terminal capability with a corresponding threshold, determining to initiate a service of an artificial intelligence or machine learning operation type;响应于所述直接指示信息,直接确定发起人工智能或机器学习操作类型的业务。In response to the direct indication information, it is directly determined to initiate a business of the type of artificial intelligence or machine learning operation.
- 根据权利要求11或12所述的通信方法,其中,所述通信方法还包括:估计即将发起的人工智能或机器学习操作类型的业务所需的资源;The communication method according to claim 11 or 12, wherein the communication method further comprises: estimating the resources required for the artificial intelligence or machine learning operation type business to be initiated;基于所述第一信息确定发起人工智能或机器学习操作类型的业务,包括:Based on the first information, it is determined to initiate a business of an artificial intelligence or machine learning operation type, including:基于所估计的资源和/或所述第一信息确定发起人工智能或机器学习操作类型的业务。A business of the type of artificial intelligence or machine learning operation is determined to initiate based on the estimated resources and/or the first information.
- 一种通信设备,所述通信设备包括:A communication device comprising:通信模块,被配置为:发送第一信息,其中,所述第一信息用于使得终端确定发起人工智能或机器学习操作类型的业务。The communication module is configured to: send first information, where the first information is used to enable the terminal to determine to initiate a service of an artificial intelligence or machine learning operation type.
- 一种通信设备,所述通信设备包括:A communication device comprising:通信模块,被配置为:获取第一信息;a communication module, configured to: obtain the first information;处理模块,被配置为:基于所述第一信息确定发起人工智能或机器学习操作类型的业务。The processing module is configured to: determine to initiate a business of an artificial intelligence or machine learning operation type based on the first information.
- 一种电子设备,所述电子设备包括存储器和处理器;An electronic device including a memory and a processor;所述存储器中存储有计算机程序;A computer program is stored in the memory;所述处理器用于在运行所述计算机程序时执行权利要求1至10中任一项、或者权利要求11至20中任一项所述的方法。The processor is configured to perform the method of any one of claims 1 to 10, or any one of claims 11 to 20, when running the computer program.
- 一种计算机可读存储介质,所述存储介质中存储有计算机程序,所述计算机程序在被处理器运行时用于执行权利要求1至10中任一项、或者权利要求11至20中任一项所述的方法。A computer-readable storage medium having a computer program stored therein, the computer program being used to execute any one of claims 1 to 10 or any one of claims 11 to 20 when executed by a processor method described in item.
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202080001172.4A CN114208255A (en) | 2020-06-29 | 2020-06-29 | Communication method and apparatus, electronic apparatus, and computer-readable storage medium |
PCT/CN2020/099051 WO2022000216A1 (en) | 2020-06-29 | 2020-06-29 | Communication method and device, electronic device, and computer-readable storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
PCT/CN2020/099051 WO2022000216A1 (en) | 2020-06-29 | 2020-06-29 | Communication method and device, electronic device, and computer-readable storage medium |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2022000216A1 true WO2022000216A1 (en) | 2022-01-06 |
Family
ID=79317845
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/CN2020/099051 WO2022000216A1 (en) | 2020-06-29 | 2020-06-29 | Communication method and device, electronic device, and computer-readable storage medium |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN114208255A (en) |
WO (1) | WO2022000216A1 (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2023221111A1 (en) * | 2022-05-20 | 2023-11-23 | Oppo广东移动通信有限公司 | Ue capability reporting methods and apparatuses, and device and medium |
WO2024092788A1 (en) * | 2022-11-04 | 2024-05-10 | Shenzhen Tcl New Technology Co., Ltd. | Wireless communication system and method for determining ai/ml model during ue mobility |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20190320489A1 (en) * | 2016-12-30 | 2019-10-17 | Beijing Xiaomi Mobile Software Co., Ltd. | Region configuration method and device |
CN110637502A (en) * | 2019-08-23 | 2019-12-31 | 北京小米移动软件有限公司 | Data processing method and device, electronic equipment and computer readable storage medium |
CN110730954A (en) * | 2019-09-09 | 2020-01-24 | 北京小米移动软件有限公司 | Data processing method and device, electronic equipment and computer readable storage medium |
CN110785984A (en) * | 2019-09-17 | 2020-02-11 | 北京小米移动软件有限公司 | Information acquisition method, information acquisition device and electronic equipment |
CN111212107A (en) * | 2019-12-10 | 2020-05-29 | 中移(杭州)信息技术有限公司 | Service processing method for CDN platform and CDN system |
-
2020
- 2020-06-29 CN CN202080001172.4A patent/CN114208255A/en active Pending
- 2020-06-29 WO PCT/CN2020/099051 patent/WO2022000216A1/en active Application Filing
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20190320489A1 (en) * | 2016-12-30 | 2019-10-17 | Beijing Xiaomi Mobile Software Co., Ltd. | Region configuration method and device |
CN110637502A (en) * | 2019-08-23 | 2019-12-31 | 北京小米移动软件有限公司 | Data processing method and device, electronic equipment and computer readable storage medium |
CN110730954A (en) * | 2019-09-09 | 2020-01-24 | 北京小米移动软件有限公司 | Data processing method and device, electronic equipment and computer readable storage medium |
CN110785984A (en) * | 2019-09-17 | 2020-02-11 | 北京小米移动软件有限公司 | Information acquisition method, information acquisition device and electronic equipment |
CN111212107A (en) * | 2019-12-10 | 2020-05-29 | 中移(杭州)信息技术有限公司 | Service processing method for CDN platform and CDN system |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2023221111A1 (en) * | 2022-05-20 | 2023-11-23 | Oppo广东移动通信有限公司 | Ue capability reporting methods and apparatuses, and device and medium |
WO2024092788A1 (en) * | 2022-11-04 | 2024-05-10 | Shenzhen Tcl New Technology Co., Ltd. | Wireless communication system and method for determining ai/ml model during ue mobility |
Also Published As
Publication number | Publication date |
---|---|
CN114208255A (en) | 2022-03-18 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US9420511B2 (en) | Signaling QoS requirements and UE power preference in LTE-A networks | |
TWI472242B (en) | Methods and apparatus for intelligent wireless technology selection | |
US10887787B2 (en) | Reflective QoS control in wireless communications | |
WO2021253232A1 (en) | Communication method and device, and electronic device and computer-readable storage medium | |
EP3648436A1 (en) | Method for clustering cache servers within a mobile edge computing network | |
WO2022000216A1 (en) | Communication method and device, electronic device, and computer-readable storage medium | |
US20230284295A1 (en) | Method and apparatus for providing an always-on attribute of a pdu session and for providing interworking aspects with respect to an always-on pdu session | |
WO2019174437A1 (en) | Address management method, device and system | |
CN109475011B (en) | UE RRC state determination method and device | |
EP3528525A1 (en) | Communication control apparatus, communication control method, radio communication system and terminal apparatus | |
US20150105081A1 (en) | Method And Apparatus For Triggering Cell Reselection Based On A Resource Suspension | |
KR20230006537A (en) | Tunnel reuse for multicast and broadcast services | |
GB2537623A (en) | Content delivery over D2D links | |
KR20160079835A (en) | Discovery of wi-fi direct services via discovery probe | |
KR102447497B1 (en) | Apparatus and method for resource allocation using mobile base station | |
CN115066008A (en) | Energy-saving control method and device and storage medium | |
CN111343711B (en) | Method, device, equipment and medium for reducing terminal power consumption | |
CN112486310A (en) | Data service control method, device and terminal | |
CN114793353A (en) | Network selection method, configuration method, terminal and network side equipment | |
EP4025003A1 (en) | Redictection method and related device | |
CN110944309B (en) | Control method and device for D2D communication | |
WO2023134332A1 (en) | Communication method and system | |
WO2022261893A1 (en) | Data transmission processing method and apparatus, and terminal and storage medium | |
US20220217699A1 (en) | Control information transmission method, apparatus, and system | |
WO2023202206A1 (en) | Communication method and apparatus |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 20942523 Country of ref document: EP Kind code of ref document: A1 |