Communication method, first device, second device, communication apparatus, system, and medium

Abstract

The present disclosure relates to a communication method, a first device, a second device, a communication apparatus, a system and a medium. The communication method comprises: a first device releasing a first computing resource, the first computing resource being a computing resource that the first device has allocated to a second device. Through the embodiments of the present disclosure, the computing resource can be saved.

Description

Communication method, first device, second device, communication apparatus, system and medium TECHNICAL FIELD

[0001] The present disclosure relates to the technical field of communication, and particularly relates to a communication method, a first device, a second device, a communication apparatus, a system and a medium. BACKGROUND

[0002] With the rapid development of artificial intelligence (AI) technology, the application of AI models is becoming more and more widespread. AI models are used to perform tasks such as image recognition, speech recognition, natural language processing, and replacing traditional wireless communication algorithms. However, training and reasoning these AI models usually require a large amount of computing resources.

[0003] Computing power sharing refers to opening idle computing power of multiple computing resources to other devices for use to perform related tasks of AI models.

[0004] SUMMARY

[0005] How to handle the allocated computing power resources is a problem to be solved.

[0006] Embodiments of the present disclosure provide a communication method, a first device, a second device, a communication apparatus, a system and a medium.

[0007] According to a first aspect of an embodiment of the present disclosure, a communication method is provided, and the method comprises: a first device releasing a first computing power resource, the first computing power resource being a computing power resource allocated by the first device to a second device.

[0008] According to a second aspect of an embodiment of the present disclosure, a communication method is provided, and the method comprises: a second device determining a first computing power resource, the first computing power resource being a computing power resource allocated by a first device to the second device.

[0009] According to a third aspect of an embodiment of the present disclosure, a terminal is provided, comprising: a processing module configured to release a first computing power resource, the first computing power resource being a computing power resource allocated by the first device to a second device.

[0010] According to a fourth aspect of an embodiment of the present disclosure, a network device is provided, comprising: a processing module configured to determine, by a second device, a first computing power resource, the first computing power resource being a computing power resource allocated by a first device to the second device.

[0011] According to a fifth aspect of an embodiment of the present disclosure, a communication apparatus is provided, comprising: one or more processors; and wherein the processor is configured to execute the communication method of the first aspect.

[0012] According to a sixth aspect of the embodiments of the present disclosure, a communication apparatus is provided, comprising: one or more processors; wherein the processor is configured to execute the communication method of the second aspect.

[0013] According to a seventh aspect of the embodiments of the present disclosure, a communication system is provided, comprising a first device and a second device, wherein the first device is configured to implement the communication method of the first aspect, and the second device is configured to implement the communication method of the second aspect.

[0014] According to an eighth aspect of the embodiments of the present disclosure, a storage medium is provided, the storage medium stores instructions, and the instructions, when executed on a communication device, cause the communication device to execute the method of the first aspect or the second aspect.

[0015] According to a ninth aspect of the embodiments of the present disclosure, a computer program is provided, and the computer program, when executed on a communication device, causes the communication device to execute the communication method of the first aspect or the second aspect.

[0016] By the embodiments of the present disclosure, the first device releases the first computing resource allocated to the second device, and the computing resource can be saved. BRIEF DESCRIPTION OF DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the embodiments of the present disclosure, the following describes the drawings required for the embodiments, and the following drawings are only some embodiments of the present disclosure, and do not specifically limit the protection scope of the present disclosure.

[0018] FIG. 1 is an exemplary schematic diagram of an architecture of a communication system according to an embodiment of the present disclosure.

[0019] FIG. 2A is an interaction schematic diagram of a communication method according to an embodiment of the present disclosure.

[0020] FIG. 2B is an interaction schematic diagram of a communication method according to an embodiment of the present disclosure.

[0021] FIG. 2C is an interaction schematic diagram of a communication method according to an embodiment of the present disclosure.

[0022] FIG. 3A is a flow schematic diagram of a communication method according to an embodiment of the present disclosure.

[0023] FIG. 3B is a flow schematic diagram of a communication method according to an embodiment of the present disclosure.

[0024] FIG. 3C is a flow schematic diagram of a communication method according to an embodiment of the present disclosure.

[0025] FIG. 4A is a flow schematic diagram of a communication method according to an embodiment of the present disclosure.

[0026] FIG. 4B is a flow diagram of a communication method, according to an embodiment of the present disclosure.

[0027] FIG. 4C is a flow diagram of a communication method, according to an embodiment of the present disclosure.

[0028] FIG. 5A is an interaction diagram of a communication method, according to an embodiment of the present disclosure.

[0029] FIG. 5B is an interaction diagram of a communication method, according to an embodiment of the present disclosure.

[0030] FIG. 6A is a structural diagram of a first device, according to an embodiment of the present disclosure.

[0031] FIG. 6B is a structural diagram of a second device, according to an embodiment of the present disclosure.

[0032] FIG. 7A is a structural diagram of a communication device, according to an embodiment of the present disclosure.

[0033] FIG. 7B is a structural diagram of a chip, according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0034] Embodiments of the present disclosure provide a communication method, a first device, a second device, a communication apparatus, a system, and a medium.

[0035] In a first aspect, embodiments of the present disclosure provide a communication method, which includes: a first device releasing a first computing resource, the first computing resource being a computing resource allocated to a second device by the first device.

[0036] In the above embodiments, the first device releases the first computing resource allocated to the second device, which can save computing resources.

[0037] In combination with some embodiments of the first aspect, in some embodiments, the method further includes: the first device receiving first information sent by the second device, the first information being used to request to release the first computing resource.

[0038] In the above embodiments, the second device sends the first information used to request to release the first computing resource to the first device, and the first device releases the first computing resource according to the first information, which realizes the release of computing resources and saves computing resources.

[0039] In combination with some embodiments of the first aspect, in some embodiments, the first information includes a first computing resource identifier, and the first computing resource identifier is associated with the first computing resource.

[0040] In the above embodiment, the first information sent by the second device to the first device includes the first computing resource identifier, and the first computing resource associated with the first computing resource identifier is released by the first device, so as to realize computing resource release and save computing resources.

[0041] In combination with some embodiments of the first aspect, in some embodiments, the method further includes: sending, by the first device, second information to the second device, the second information being used to indicate release of computing resources.

[0042] In combination with some embodiments of the first aspect, in some embodiments, the second information is sent based on an event trigger, and the second information includes a second computing resource identifier and / or an event identifier, the second computing resource identifier being used to identify the computing resources indicated by the first device to release.

[0043] In the above embodiment, the first device sends the second information used to indicate release of computing resources to the second device based on an event trigger, so as to release the computing resources according to the third information sent by the second device.

[0044] In combination with some embodiments of the first aspect, in some embodiments, the event includes at least one of the following: the computing service time has ended; the computing resources are insufficient; the computing fee is used up; and the computing service is switched.

[0045] In combination with some embodiments of the first aspect, in some embodiments, the second information is further used to indicate a third device providing computing resources.

[0046] In combination with some embodiments of the first aspect, in some embodiments, the event includes that the computing resources are insufficient or the computing service is switched, and the second information is further used to indicate the third device providing computing resources.

[0047] In the above embodiment, the first device sends the second information further indicating the third device providing computing resources to the second device when the computing resources are insufficient or the computing service is switched, so that the second device can select the third device to continue to provide computing resources.

[0048] In combination with some embodiments of the first aspect, in some embodiments, the method further includes: receiving, by the first device, third information sent by the second device, the third information including a third computing resource identifier, the third computing resource identifier including one or more computing resource identifiers, each computing resource identifier corresponding to a priority of computing resources, and the third computing resource identifier being used to identify the computing resources determined by the second device to release based on the second information.

[0049] In combination with some embodiments of the first aspect, in some embodiments, the method further includes: releasing, by the first device, the first computing resources based on the third information.

[0050] In some embodiments of the first aspect, in some embodiments, the first computing resource is released according to a corresponding priority of each computing resource identifier, and the first computing resource is all or part of the computing resources allocated by the first device to the second device.

[0051] In the above-mentioned embodiments, the second device sends third information to the first device, the third information includes a third computing resource identifier, and the first device releases the computing resource according to a corresponding priority of the third computing resource identifier, so as to save resources and ensure the efficiency of computing resource sharing.

[0052] In some embodiments of the first aspect, in some embodiments, the method further includes: the first device receiving fourth information sent by the second device, the fourth information being used to request the third device to provide computing resources for the second device.

[0053] In the above-mentioned embodiments, the second device can send information to the first device to request the third device to provide computing resources, and the first device can make the third device continue to provide computing resources for the second device according to the information, so as to ensure the sharing of computing resources.

[0054] In some embodiments of the first aspect, in some embodiments, the third information is used to indicate at least one of the following: whether the second device renews the subscription; whether the second device continues to provide computing resources through the first device.

[0055] In the above-mentioned embodiments, the first device can determine whether to continue to provide computing resources for the second device according to whether the second device renews the subscription or whether the second device continues to provide computing resources through the first device, so as to ensure the sharing of computing resources.

[0056] In some embodiments of the first aspect, in some embodiments, the method further includes: the first device sending fifth information to the second device, the fifth information being used to indicate that the first device has released the first computing resource.

[0057] In some embodiments of the first aspect, in some embodiments, the fifth information includes a first computing resource identifier and / or an event identifier, the first computing resource identifier is associated with the first computing resource, and the first computing resource is a computing resource shared between the first device and the second device; and the fifth information is used by the second device to determine whether to release a second computing resource, the second computing resource is a computing resource shared between the first device and the second device, and the second computing resource is associated with the first computing resource identifier.

[0058] In the above embodiments, the first device and the second device share computing power, and after the first device releases the first computing power resource, the second device can release a corresponding second computing power resource according to the first computing power resource identifier, thereby saving computing power resources.

[0059] In some embodiments of the first aspect, the method further includes: receiving, by the first device, sixth information sent by the second device, the sixth information being used to indicate that the second device has confirmed that the first device has released the first computing power resource.

[0060] In a second aspect, the embodiments of the present disclosure provide a communication method, which includes: determining, by a second device, a first computing power resource, the first computing power resource being a computing power resource allocated to the second device by a first device.

[0061] In some embodiments of the second aspect, the method includes: sending, by the second device, first information to the first device, the first information being used to request release of the first computing power resource.

[0062] In some embodiments of the second aspect, the method further includes: receiving, by the second device, second information sent by the first device, the second information being used to indicate release of the computing power resource.

[0063] In some embodiments of the second aspect, the method further includes: receiving, by the second device, fifth information sent by the first device, the fifth information being used to indicate that the first device has released the first computing power resource.

[0064] In some embodiments of the second aspect, the first information includes a first computing power resource identifier, the first computing power resource identifier being associated with the first computing power resource.

[0065] In some embodiments of the second aspect, the second information is sent based on an event trigger, the second information including a second computing power resource identifier and / or an event identifier, the second computing power resource identifier being used to identify the computing power resource indicated by the first device to release.

[0066] In some embodiments of the second aspect, the event includes at least one of: an end of a computing power service time; a lack of computing power resources; an end of computing power fees; and a computing power service switch.

[0067] In some embodiments of the second aspect, the second information is further used to indicate a third device providing the computing power resource.

[0068] In some embodiments of the second aspect, in some embodiments, the event comprises that the computing resource has been insufficient or a computing resource service switching, and the second information is further used to indicate a third device providing the computing resource.

[0069] In some embodiments of the second aspect, in some embodiments, the method further comprises: sending, by the second device, third information to the first device, the third information comprising a third computing resource identifier, the third computing resource identifier comprising one or more computing resource identifiers, each computing resource identifier corresponding to a priority of a computing resource, the third computing resource identifier being used to indicate the computing resource determined by the second device to be released based on the second information.

[0070] In some embodiments of the second aspect, in some embodiments, the method further comprises: releasing, by the first device, the first computing resource based on the third information.

[0071] In some embodiments of the second aspect, in some embodiments, the first computing resource is released according to the priority corresponding to each computing resource identifier, and the first computing resource is all or part of the computing resource allocated by the first device to the second device.

[0072] In some embodiments of the second aspect, in some embodiments, the method further comprises: sending, by the second device, fourth information to the first device, the fourth information being used to request the third device to provide the computing resource for the second device.

[0073] In some embodiments of the second aspect, in some embodiments, the third information is used to indicate at least one of the following: whether the second device renews the subscription; whether the second device continues to provide the computing resource through the first device.

[0074] In some embodiments of the second aspect, in some embodiments, the fifth information comprises a first computing resource identifier and / or an event identifier, the first computing resource identifier being associated with the first computing resource, the first computing resource being a computing resource shared between the first device and the second device, and the fifth information being used by the second device to determine whether to release a second computing resource, the second computing resource being a computing resource shared between the first device and the second device, the second computing resource being associated with the first computing resource identifier.

[0075] In some embodiments of the second aspect, in some embodiments, the method further comprises: sending, by the second device, sixth information to the first device, the sixth information being used to indicate that the second device has confirmed that the first device has released the first computing resource.

[0076] In a third aspect, the embodiments of the present disclosure provide a first device, comprising: a processing module configured to release a first computing resource, the first computing resource being a computing resource allocated by the first device to a second device.

[0077] In a fourth aspect, the embodiments of the present disclosure provide a second device, comprising: a processing module configured to determine, by the second device, a first computing resource, the first computing resource being a computing resource allocated by a first device to the second device.

[0078] In a fifth aspect, the embodiments of the present disclosure provide a communication apparatus, comprising: one or more processors; wherein the processor is configured to execute the communication method of the first aspect.

[0079] In a sixth aspect, the embodiments of the present disclosure provide a communication apparatus, comprising: one or more processors; wherein the processor is configured to execute the communication method of the second aspect.

[0080] In a seventh aspect, the embodiments of the present disclosure provide a communication system, comprising a first device and a second device, wherein the first device is configured to implement the communication method of the first aspect, and the second device is configured to implement the communication method of the second aspect.

[0081] In an eighth aspect, the embodiments of the present disclosure provide a storage medium, the storage medium storing instructions, characterized in that when the instructions are executed on a communication device, the communication device executes the method of the first aspect or the second aspect.

[0082] In a ninth aspect, the embodiments of the present disclosure provide a program product, when the program product is executed by a communication device, the communication device executes the method as described in the optional implementation manner of the first aspect or the second aspect.

[0083] In a tenth aspect, the embodiments of the present disclosure provide a computer program, when the computer program is executed by a communication device, the communication device executes any of the above communication methods.

[0084] In an eleventh aspect, the embodiments of the present disclosure provide a chip or chip system. The chip or chip system comprises a processing circuit configured to execute the method as described in the optional implementation manner of the first aspect or the second aspect.

[0085] It can be understood that the above-mentioned first device, second device, communication apparatus, communication system, storage medium, program product, computer program, chip or chip system are all used to execute the method proposed by the embodiments of the present disclosure. Therefore, the beneficial effects they can achieve can refer to the beneficial effects in the corresponding method, which will not be repeated here.

[0086] The embodiments of the present disclosure provide a communication method, a first device, a second device, a communication apparatus, a communication system and a storage medium. In some embodiments, the communication method and the information sending method, information receiving method and other terms can be replaced with each other.

[0087] The embodiments of the present disclosure are not exhaustive, but only illustrate some embodiments, and are not specific limitations on the protection scope of the present disclosure. In the case of no contradiction, each step in an embodiment can be implemented as an independent embodiment, and the steps can be combined arbitrarily, for example, the scheme after removing some steps in an embodiment can also be implemented as an independent embodiment, and the order of the steps in an embodiment can be exchanged arbitrarily, in addition, the optional implementation manners in an embodiment can be combined arbitrarily; in addition, the embodiments can be combined arbitrarily, for example, the steps of different embodiments can be combined arbitrarily, an embodiment can be combined with the optional implementation manners of other embodiments.

[0088] In each embodiment of the present disclosure, the terms and / or descriptions between the embodiments are consistent if there is no special description and logical conflict, and can be referred to each other, and the technical features in different embodiments can be combined to form a new embodiment according to their inherent logical relationship.

[0089] The terms used in the embodiments of the present disclosure are only for the purpose of describing the specific embodiments, and not as a limitation on the present disclosure.

[0090] In the embodiments of the present disclosure, unless otherwise specified, the elements expressed in singular form, such as "one", "a", "the", "above", "said", "preceding", "this" and the like, can represent "one and only one", or "one or more", "at least one" and the like. For example, in the case of using articles such as "a", "an", "the" and the like in English, the noun after the article can be understood as singular expression, or can be understood as plural expression.

[0091] In the embodiments of the present disclosure, "a plurality of" means two or more.

[0092] In some embodiments, the terms "at least one of", "one or more", "a plurality of", "multiple" and the like can be replaced with each other.

[0093] In some embodiments, "at least one of A, B", "A and / or B", "in one case A, in another case B", "responsive to case A, responsive to case B" and the like, can be interpreted to include both cases, A and B, in some embodiments, A (A is performed regardless of B), in some embodiments, B (B is performed regardless of A), in some embodiments, selected from the group consisting of A and B (the selection between A and B is an option), in some embodiments, A and B (both A and B are performed).

[0094] In some embodiments, "A or B" and the like, can be interpreted to include both cases, A and B, in some embodiments, A (A is performed regardless of B), in some embodiments, B (B is performed regardless of A), in some embodiments, selected from the group consisting of A and B (the selection between A and B is an option).

[0095] In some embodiments, the prefix words "first", "second" and the like in the disclosure do not limit the position, order, priority, number or content of the described objects, and the description of the described objects should be referred to the context of the claims or embodiments, and should not be construed as redundant limitations. For example, the described objects are "fields", and the ordinal words before "fields" in "first field" and "second field" do not limit the position or order between "fields", and "first" and "second" do not limit whether the "fields" modified by them are in the same message or not, nor limit the order of "first field" and "second field". For another example, the described objects are "levels", and the ordinal words before "levels" in "first level" and "second level" do not limit the priority between "levels". For another example, the number of the described objects is not limited by the ordinal words, and can be one or more. For example, "first device", where the number of "devices" can be one or more. In addition, the objects modified by different prefix words can be the same or different, for example, the described objects are "devices", and "first device" and "second device" can be the same device or different devices, and their types can be the same or different. For another example, the described objects are "information", and "first information" and "second information" can be the same information or different information, and their contents can be the same or different.

[0096] In some embodiments, "including A", "containing A", "for indicating A", "carrying A" can be interpreted as directly carrying A, or indirectly indicating A.

[0097] In some embodiments, the terms "in response to", "in response to determining", "in the case of", "when", "when", "if", "if" and the like can be replaced with each other.

[0098] In some embodiments, the terms "greater than", "greater than or equal to", "not less than", "more than", "more than or equal to", "not less than", "higher than", "higher than or equal to", "not lower than", "above", and the like can be replaced with each other, and the terms "less than", "less than or equal to", "not greater than", "fewer than", "fewer than or equal to", "not more than", "lower than", "lower than or equal to", "not higher than", "below", and the like can be replaced with each other.

[0099] In some embodiments, an apparatus and the like can be interpreted as an entity, and can also be interpreted as virtual, and the name thereof is not limited to the name recited in the embodiments, and the terms "apparatus", "equipment", "device", "circuit", "network element", "node", "function", "unit", "section", "system", "network", "chip", "chip system", "entity", "subject", and the like can be replaced with each other.

[0100] In some embodiments, "network" can be interpreted as an apparatus (for example, an access network device, a core network device, and the like) included in the network.

[0101] In some embodiments, the terms “access network device (AN device),” “radio access network device (RAN device),” “base station (BS),” “radio base station,” “fixed station,” “node,” “access point,” “transmission point (TP),” “reception point (RP),” “transmission / reception point (TRP),” “panel,” “antenna panel,” “antenna array,” “cell,” “macro cell,” “small cell,” “femto cell,” “pico cell,” “sector,” “cell group,” “serving cell,” “carrier,” “component carrier,” “bandwidth part (BWP),” and the like can be used interchangeably.

[0102] In some embodiments, the terms "terminal," "terminal device," "user equipment (UE)," "user terminal," "mobile station (MS)," "mobile terminal (MT)," "subscriber station," "mobile unit," "subscriber unit," "wireless unit," "remote unit," "mobile device," "wireless device," "wireless communication device," "remote device," "mobile subscriber station," "access terminal," "mobile terminal," "wireless terminal," "remote terminal," "handset," "user agent," "mobile client," "client," and so on can be replaced with each other.

[0103] In some embodiments, the access network device, the core network device, or the network device can be replaced with a terminal. For example, the embodiments of the present disclosure can also be applied to a structure in which communication between the access network device, the core network device, or the network device and the terminal is replaced with communication between a plurality of terminals (e.g., device-to-device (D2D), vehicle-to-everything (V2X), etc.). In this case, the terminal can also be configured to have all or part of the functions of the access network device. In addition, the terms "uplink," "downlink," and the like can also be replaced with terms corresponding to the inter-terminal communication (e.g., "side"). For example, the uplink channel, the downlink channel, and the like can be replaced with the side channel, and the uplink, the downlink, and the like can be replaced with the sidelink.

[0104] In some embodiments, the terminal can be replaced with the access network device, the core network device, or the network device. In this case, the access network device, the core network device, or the network device can also be configured to have all or part of the functions of the terminal.

[0105] In some embodiments, obtaining data, information, etc. can comply with the laws and regulations of the country where the location is located.

[0106] In some embodiments, data, information, etc. can be obtained after obtaining the consent of the user.

[0107] In addition, each element, each row, or each column in the table of the embodiments of the present disclosure can be implemented as an independent embodiment, and any combination of any element, any row, or any column can also be implemented as an independent embodiment.

[0108] With the rapid development of AI technology, more and more organizations and individuals begin to use AI models for various tasks, such as image recognition, speech recognition, natural language processing, and replacing traditional wireless communication algorithms. However, training and reasoning these AI models usually require a large amount of computing resources.

[0109] In this case, computing power sharing has become a topic of concern. Computing power sharing refers to opening the idle computing power of multiple computing resources (such as servers, graphics processing units (GPUs), tensor processing units (TPUs), etc.) to other organizations or individuals for use in AI model inference tasks. Computing power sharing provides a flexible and efficient solution for AI model inference tasks, which helps to promote the development and application of AI technology.

[0110] In wireless communication, computing power sharing can be applied to the following four scenarios:

[0111] Scenario 1: Network device opens computing power to terminal;

[0112] The network device provides computing power services for the terminal, such as using the model deployed on the network side to provide AI / Machine Learning (ML) model inference or model training computing power services for the terminal.

[0113] Scenario 2: Terminal opens computing power to network device;

[0114] The terminal provides computing power services for the network device, such as participating in network-initiated federated learning according to the requirements of the network side device, providing AI / ML model training and model inference tasks for the network device.

[0115] Scenario 3: Computing power sharing / collaboration between terminals;

[0116] Due to the limitation of hardware resources or other limitations, some terminals cannot apply AI / ML models. However, other terminals can provide the application of AI / ML models. In this case, a terminal with strong computing power can provide computing power services for a terminal with weak computing power. For example, a terminal with strong computing power such as a mobile phone or a car provides inference services of AI / ML models for a terminal with weak computing power such as a watch and the like.

[0117] Scenario 4: terminals and network devices perform computing power collaboration

[0118] Some service types need to be completed by terminals and network devices in collaboration, for example, AI / ML-based channel state information (CSI) compression feedback includes part of the model of the terminal and part of the model of the network device, and the training or inference of the model needs the collaboration of both.

[0119] In the above scenarios, if a network device or a terminal provides computing power services for other devices, it needs to provide certain computing power resources for the inference or training of AI / ML models. When the device does not need the service, or the service time is up, or for other reasons, the network device or the terminal needs to release the computing power resources allocated for the previous computing power services. How to release the allocated computing power resources is a problem to be solved.

[0120] FIG. 1 is an architecture schematic diagram of a communication system according to an embodiment of the present disclosure.

[0121] As shown in FIG. 1, the communication system 100 includes at least one of a first device 101 and a second device 102.

[0122] In some embodiments, the first device 101 can be a device providing computing power resources, or the first device 101 can also be a node controlling the provision of computing power services, such as a control network node; and the second device 102 is a device using computing power resources.

[0123] In some embodiments, the first device 101 is a network device, and the second device 102 is a terminal, that is, the network device provides computing power resources to the terminal.

[0124] In some embodiments, the first device 101 is a terminal, and the second device 102 is a network device, that is, the terminal provides computing power resources to the network device.

[0125] In some embodiments, the first device 101 is a network device or a terminal, and the second device 102 is a terminal or a network device, that is, the network device and the terminal perform computing power collaboration, the network device provides computing power resources to the terminal, and the terminal also provides computing power resources to the network device.

[0126] In some embodiments, the terminal can be a user equipment (UE), including at least one of a mobile phone, a wearable device, an Internet of Things (IoT) device, a communication-capable automobile, a smart automobile, a tablet (Pad), a computer with wireless transceiver function, a virtual reality (VR) terminal device, an augmented reality (AR) terminal device, a wireless terminal device in industrial control, a wireless terminal device in self-driving, a wireless terminal device in remote medical surgery, a wireless terminal device in smart grid, a wireless terminal device in transportation safety, a wireless terminal device in smart city, a wireless terminal device in smart home, and the like, but is not limited thereto.

[0127] In some embodiments, the network device can be one functional network element in a core network device, which can be one device including all or part of the first network element, the second network element, and the like, or a plurality of devices or device groups including all or part of the first network element, the second network element, and the like, respectively. The network element can be virtual or physical. The core network includes at least one of an evolved packet core (EPC), a 5G core network (5GCN), a next generation core (NGC), and the like.

[0128] In some embodiments, the network device can include at least one of an access network device and a core network device.

[0129] In some embodiments, the access network device is, for example, a node or device that accesses a terminal to a wireless network, and can include at least one of an evolved NodeB (eNB) in a 5G communication system, a next generation eNB (ng-eNB), a next generation NodeB (gNB), a node B (NB), a home node B (HNB), a home evolved node B (HeNB), a wireless backhaul device, a radio network controller (RNC), a base station controller (BSC), a base transceiver station (BTS), a base band unit (BBU), a mobile switching center, a base station in a 6G communication system, an open base station (Open RAN), a cloud base station (Cloud RAN), a base station in other communication systems, an access node in a Wi-Fi system, but is not limited thereto.

[0130] In some embodiments, the technical solutions of the present disclosure can be applied to an Open RAN architecture, at which time the interfaces between or within the access network devices involved in the embodiments of the present disclosure can become internal interfaces of the Open RAN, and the processes and information interactions between these internal interfaces can be realized through software or programs.

[0131] In some embodiments, the access network device can be composed of a central unit (CU) and a distributed unit (DU), where the CU can also be referred to as a control unit. The CU-DU structure can split the protocol layers of the access network device, with part of the protocol layer functions being controlled by the CU, and the remaining part or all of the protocol layer functions being distributed in the DU and controlled by the CU, but is not limited thereto.

[0132] In some embodiments, the core network device can be one device including one or more network elements, or a plurality of devices or device groups including all or part of the above one or more network elements. The network element can be virtual or physical. The core network includes, for example, at least one of an evolved packet core (EPC), a 5G core network (5GCN), and a next generation core (NGC).

[0133] It can be understood that the communication system described in the embodiments of the present disclosure is for more clearly illustrating the technical solutions of the embodiments of the present disclosure, and does not constitute a limitation on the technical solutions proposed by the embodiments of the present disclosure. Those skilled in the art can know that, with the evolution of system architecture and the appearance of new business scenarios, the technical solutions proposed by the embodiments of the present disclosure are also applicable to similar technical problems.

[0134] The following embodiments of the present disclosure can be applied to the communication system 100 shown in FIG. 1 or part of the subjects, but are not limited thereto. The subjects shown in FIG. 1 are exemplary, and the communication system can include all or part of the subjects in FIG. 1, or other subjects other than FIG. 1. The number and form of each subject is arbitrary, each subject can be physical or virtual, the connection relationship between each subject is exemplary, each subject can not be connected or can be connected, the connection can be in any way, can be direct connection or indirect connection, can be wired connection or wireless connection.

[0135] Embodiments of the present disclosure can be applied to Long Term Evolution (LTE), LTE-Advanced (LTE-A), LTE-Beyond (LTE-B), SUPER 3G, IMT-Advanced, 4th generation mobile communication system (4G), 5th generation mobile communication system (5G), 5G new radio (NR), Future Radio Access (FRA), New-Radio Access Technology (RAT), New Radio (NR), New radio access (NX), Future generation radio access (FX), Global System for Mobile communications (GSM (registered trademark)), CDMA2000, Ultra Mobile Broadband (UMB), IEEE 802.11 (Wi-Fi (registered trademark)), IEEE 802.16 (WiMAX (registered trademark)), IEEE 802.20, Ultra-WideBand (UWB), Bluetooth (Bluetooth (registered trademark)), Public Land Mobile Network (PLMN) network, Device-to-Device (D2D) system, Machine to Machine (M2M) system, Internet of Things (IoT) system, Vehicle-to-Everything (V2X), system using other communication methods, next-generation system expanded based on them, and the like. Further, a plurality of systems can be combined (for example, combination of LTE or LTE-A and 5G, and the like).

[0136] FIG. 2A is an interaction diagram of a communication method according to an embodiment of the present disclosure.

[0137] In some embodiments, the communication method illustrated in FIG. 2A can be applied to a communication scenario in which the first device provides computing power resources to the second device.

[0138] In some embodiments, the first device can be a device providing computing power resources, such as a network device or a terminal.

[0139] In some embodiments, the first device can be a node controlling the provision of computing power resources, such as a control network node.

[0140] In some embodiments, the second device can be a device using computing power resources, such as a network device or a terminal.

[0141] In some embodiments, the provision of computing power resources can also be referred to as the provision of computing power services, which is not limited in the present disclosure.

[0142] In some embodiments, the first device allocates computing power resources of the first device to the second device for use by the second device.

[0143] For example, a network device provides computing power resources to a terminal; for another example, a terminal provides computing power resources to a network device; for another example, a network device and a terminal provide computing power resources to each other.

[0144] It can be understood that in the case where the network device provides computing power resources to the terminal, the first device is the network device and the second device is the terminal; in the case where the terminal provides computing power resources to the network device, the first device is the terminal and the second device is the network device; in the case where the network device and the terminal provide computing power resources to each other, the first device can be the network device or the terminal, and the second device can be the network device or the terminal.

[0145] As shown in FIG. 2A, the embodiments of the present disclosure relate to a communication method, and the above method comprises:

[0146] In step S2101, the second device sends first information to the first device.

[0147] In some embodiments, the second device can send the first information to the first device through signaling.

[0148] In some embodiments, the first device receives the first information sent by the second device.

[0149] In some embodiments, the first information is used to request the release of the first computing power resource.

[0150] For example, the second device no longer needs the first device to provide computing power resources, and the second device can send the first information to the first device to request the first device to release the computing power resources allocated to the second device.

[0151] In some embodiments, the first information includes a first computing power resource identifier, and the first computing power resource identifier is associated with the first computing power resource.

[0152] In some embodiments, the first information can include one or more computing resource identifiers, and for the purpose of description, the computing resource identifier included in the first information is referred to as the first computing resource identifier. The first computing resource identifier can be the computing resource identifier corresponding to the computing resource to be released indicated by the second device.

[0153] In some embodiments, the first computing resource is a computing resource allocated by the first device to the second device.

[0154] In some embodiments, the first device can release the computing resource based on the first computing resource identifier indicated by the second device. For example, the first computing resource identifier is associated with the first computing resource, and the second device releases the first computing resource.

[0155] For example, the first device provides the second device with both inference of model 1 and inference of model 2 computing power services, and allocates two computing resources for the two computing power services, which correspond to computing resource ID 1 and computing resource ID 2 respectively. Assuming that the second device no longer needs the first device to provide the inference service of model 2, i.e., the second device no longer needs the computing resource corresponding to computing resource ID 2 provided by the first device, the second device can send the first information to the first device, the first information including computing resource ID 2, so that the first device releases the computing resource corresponding to computing resource ID 2.

[0156] Step S2102, the first device sends seventh information to the second device.

[0157] In some embodiments, the seventh information is a response message of the first device receiving the first information.

[0158] In some embodiments, the seventh information can be a response message of the computing resource release request, i.e., the first device sends a response message to the second device, indicating that it has received the information sent by the second device to request the release of the computing resource.

[0159] In some embodiments, step S2102 is optional, and this step can be omitted in different embodiments.

[0160] Step S2103, the first device releases the first computing resource.

[0161] In some embodiments, the first computing resource is a computing resource allocated by the first device to the second device.

[0162] In some embodiments, the first computing resource can be all computing resources allocated by the first device to the second device, or can be part of the computing resources allocated by the first device to the second device.

[0163] In some embodiments, the first device can release the computing resource based on the first information sent by the second device.

[0164] In some embodiments, the first information comprises a first computing resource identifier, and the second device releases the first computing resource associated with the first computing resource identifier.

[0165] For example, the first information comprises a computing resource ID2, and the first device releases the computing resource corresponding to the computing resource ID2.

[0166] The communication method provided by the embodiments of the present disclosure can save computing resources and improve resource utilization by the first device releasing the first computing resource allocated to the second device.

[0167] In step S2104, the first device sends fifth information to the second device.

[0168] In some embodiments, the second device receives the fifth information sent by the first device.

[0169] In some embodiments, the second device determines the first computing resource.

[0170] In some embodiments, the second device determines the first computing resource by receiving the fifth information sent by the first device.

[0171] In some embodiments, the fifth information is used to indicate that the first device has released the first computing resource.

[0172] In some embodiments, after releasing the first computing resource, the first device can send indication information of the released first computing resource to the second device, to indicate to the second device that the first device has released the first computing resource.

[0173] For example, the first device releases the computing resource corresponding to the computing resource ID2, and the first device sends the fifth information to the second device, which indicates that the first device has released the computing resource corresponding to the ID2.

[0174] In some embodiments, step S2104 is optional and can be omitted in different embodiments.

[0175] In step S2105, the second device sends sixth information to the first device.

[0176] In some embodiments, the first device receives the sixth information sent by the second device.

[0177] In some embodiments, the sixth information is used to indicate that the second device has confirmed that the first device has released the first computing resource.

[0178] In some embodiments, after receiving the indication information sent by the first device that the first computing resource has been released, the second device can return a response message to the second device confirming that the first device has released the first computing resource, indicating that the second device already knows that the first device has released the first computing resource.

[0179] For example, the second device receives the fifth information that the first device has released the computing resource corresponding to ID2, and the second device sends the sixth information to the first device, which indicates that the second device has confirmed that the first device has released the computing resource corresponding to ID2.

[0180] In some embodiments, step S2105 is optional and can be omitted in different embodiments.

[0181] The communication method provided by the embodiments of the present disclosure can be used to realize the release of computing resources, thereby saving computing resources.

[0182] The following will be illustrated in the scenario of a network device providing computing resources to a terminal, i.e., taking the first device as a network device and the second device as a terminal for example, but the present disclosure is not limited thereto.

[0183] In some embodiments, the terminal sends the first information to the network device through signaling, indicating a computing release request.

[0184] The first information at least includes computing resource ID information, and the computing resource ID is associated with an allocated computing resource.

[0185] For example, the network device (e.g., gNB) provides a terminal with two computing services of model 1 inference and model 2 inference, and assumes that two computing resources are allocated for the two computing services, which are represented as computing resource ID1 and computing resource ID2 respectively. If the terminal does not want the network device to continue to provide the model 2 inference service, the terminal can send the first information to the network device to request the network device to release the computing resource, and the first information can include the computing resource ID2.

[0186] In some embodiments, the network device releases the computing resource allocated to the terminal according to the received first information.

[0187] For example, the network device releases the computing resource corresponding to the computing resource ID2 included in the first information.

[0188] In some embodiments, after receiving the first information, the network device can send a response message to the terminal, and the response message is used to indicate that the network device has received the first information.

[0189] In some embodiments, the network device can send a response message to the terminal after releasing the computing resource, where the response message is used to indicate that the network device has released the computing resource.

[0190] In some embodiments, the terminal can send a confirmation message to the network device after receiving the response message sent by the network device, where the confirmation message is used to indicate that the terminal has received the indication that the network device has released the computing resource.

[0191] The following is an example of a scenario in which the terminal provides the computing resource to the network device, i.e., taking the first device as the terminal and the second device as the network device as an example, but the present disclosure is not limited thereto.

[0192] In some embodiments, the network device (e.g., gNB) may need many terminals to provide a training data set for model training. Considering the privacy of the data set, part of the data set is not suitable for sending to the network device. In order to solve this problem, the training of the model is distributed in the form of federated learning, i.e., each terminal participates in the training process of the model, which requires the terminal to provide computing services for the network device.

[0193] Suppose the network device (e.g., gNB) has informed the UE to provide computing services through signaling broadcast, then the UE providing computing services will allocate a certain computing resource. Different computing requests can be associated with different computing resource IDs. Suppose the computing ID is included in the broadcast message sent by the gNB to the UE.

[0194] In some embodiments, the network sends first information to the terminal through signaling, where the first information is used to indicate a computing resource release request. The signaling can be signaling sent to each terminal individually, or signaling sent to multiple terminals through broadcast.

[0195] In some embodiments, the first information at least includes computing resource ID information, where the computing resource ID is associated with an allocated computing resource.

[0196] In some embodiments, if the model training is completed and the terminal no longer needs to provide computing services, the network device can inform each terminal to release the computing resource through a broadcast message. The broadcast message can include the computing resource ID.

[0197] In some embodiments, the terminal releases the computing resource allocated to the network device according to the received first information. Optionally, the terminal sends a response message to the network device, indicating that the indication message to release the computing resource has been received.

[0198] In some embodiments, the terminal releases the computing resource corresponding to the computing resource ID according to the received broadcast message, and sends a response message to the network device that the release of the computing resource has been completed. Optionally, the network device also sends a confirmation message to the terminal that the release of the computing resource has been received.

[0199] The gNB request for releasing computing power is described below.

[0200] If the model training is completed, the UE no longer needs to provide computing power services. At this time, the gNB can notify each UE to release the computing power resources by sending a broadcast message. The broadcast message includes the relevant computing power resource ID. The UE releases the computing power resource corresponding to the computing power resource ID according to the received broadcast message, and sends a response message to the gNB that the release of the computing power resource has been completed. Optionally, the gNB also sends a confirmation message to the UE that the release of the computing power resource has been received.

[0201] The communication method related to the embodiments of the present disclosure can include at least one of steps S2101-S2105. For example, step S2101 can be implemented as an independent embodiment, step S2103 can be implemented as an independent embodiment, step S2101+step S2103 can be implemented as an independent embodiment, but not limited thereto.

[0202] In some embodiments, step S2102 is optional, and one or more of these steps can be omitted or replaced in different embodiments.

[0203] In some embodiments, step S2104 is optional, and one or more of these steps can be omitted or replaced in different embodiments.

[0204] In some embodiments, step S2105 is optional, and one or more of these steps can be omitted or replaced in different embodiments.

[0205] In some embodiments, other optional implementations described before or after the description corresponding to FIG. 2A can be referred to.

[0206] FIG. 2B is an interaction schematic diagram of a communication method according to an embodiment of the present disclosure.

[0207] In some embodiments, the communication method shown in FIG. 2B can be applied to a communication scenario in which the first device provides computing power resources to the second device.

[0208] As shown in FIG. 2B, the embodiments of the present disclosure relate to a communication method, and the above method comprises:

[0209] Step S2201, the first device sends second information to the second device.

[0210] The second information is used to indicate the release of the computing power resource.

[0211] In some embodiments, the first device can actively initiate the computing power resource release process.

[0212] In some embodiments, the first device can send the second information to the second device when a computing resource release is needed.

[0213] In some embodiments, the second information is sent based on an event trigger.

[0214] In some embodiments, the first device sends the second information to the second device based on an event trigger.

[0215] In some embodiments, the event includes at least one of: an end of a computing service time; a shortage of computing resources; an exhaustion of a computing fee; a computing service switching.

[0216] Wherein, the computing service time refers to the time during which the first device provides computing service to the second device, and the end of the computing service time refers to the time during which the first device provides computing service to the second device has passed.

[0217] Wherein, the shortage of computing resources refers to that the available computing resources in the first device are less than a computing resource threshold, and the computing resource threshold can be set according to actual conditions.

[0218] Wherein, the computing fee refers to the fee paid by the second device to the first device for using the computing resources.

[0219] Wherein, the computing service switching refers to that, when the second device needs computing service provided by a device other than the first device, the computing service provided by the first device to the second device is switched to the computing service provided by the other device to the second device.

[0220] For example, when the time during which the first device provides computing service to the second device has ended, the first device sends the second information to the second device.

[0221] For another example, when the computing resources of the first device are insufficient, the first device sends the second information to the second device.

[0222] For another example, when the computing fee of the second device has been exhausted, the first device sends the second information to the second device.

[0223] For another example, when a computing service switching event occurs, the first device sends the second information to the second device.

[0224] In some embodiments, the second information includes a second computing resource identifier and / or an event identifier, and the second computing resource identifier is used to identify the computing resources indicated by the first device to be released.

[0225] In some embodiments, the second information can include one or more computing resource identifiers. For ease of description, the computing resource identifiers included in the second information are referred to as second computing resource identifiers. The computing resource identifiers included in the second information can be the computing resource identifiers associated with the computing resources that the network device wants to release.

[0226] In some embodiments, the second information can include one or more event identifiers, the event identifiers being associated with events for notifying the second device to trigger the computing resource release.

[0227] In some embodiments, the second information can include both the second computing resource identifiers and the event identifiers.

[0228] In some embodiments, the second information is also used to indicate a third device providing the computing resources.

[0229] The third device can be any one or more devices other than the first device and the second device.

[0230] Optionally, in the case where the event includes that the computing resources have been insufficient or the computing service switching, the second information is also used to indicate the third device providing the computing resources.

[0231] In some embodiments, if the triggered event is the computing resource insufficiency or the computing service switching event, the second information sent by the network further includes other indication information of the computing resource sharing service, such as indicating that other network devices can provide the computing service, or suggesting the terminal to send a computing request to other networks, or directly allocating the computing resources that can be provided by other networks to the terminal.

[0232] In some embodiments, if the second information is also used to indicate the third device providing the computing resources, that is, the second information includes the indication information of the other network that can provide the computing service, the second device can send a computing resource sharing service request to the corresponding third device according to the indication information, so that the third device continues to provide the computing service for the second device, thereby ensuring that the computing service is continuously provided for the second device.

[0233] In some embodiments, the first device can also be a control unit for controlling the computing resource sharing service.

[0234] In some embodiments, after receiving the second information sent by the first device, the second device can return a response message to the first device to indicate that the second information has been received.

[0235] In step S2202, the second device sends third information to the first device.

[0236] In some embodiments, the first device receives the third information sent by the second device

[0237] The third information includes a third computing resource identifier, and the third computing resource identifier includes one or more computing resource identifiers. Each computing resource identifier corresponds to a priority of a computing resource, and the third computing resource identifier is used to identify a computing resource that needs to be released by the second device based on the second information.

[0238] In some embodiments, the second device can send the third information to the first device based on the first information.

[0239] In some embodiments, the third information can include one or more computing resource identifiers. For ease of description, the computing resource identifier included in the third information is referred to as a third computing resource identifier.

[0240] In some embodiments, the third computing resource identifier is a computing resource identifier corresponding to a computing resource recommended to be released by the second device.

[0241] In some embodiments, the third computing resource identifier can be the same as or different from the second computing resource identifier.

[0242] In some embodiments, each computing resource identifier corresponds to a priority of a computing resource, and the priority of different computing resources can be determined according to the computing resource identifier. The correspondence between the computing resource identifier and the priority can be pre-set.

[0243] In some embodiments, the third information is used to indicate at least one of the following: whether the second device renews the subscription; and whether the second device continues to provide the computing resource through the first device.

[0244] In some embodiments, if the triggered event includes that the computing resource fee has been used up, the third information can further indicate whether the second device renews the subscription and / or whether the second device continues to provide the computing resource through the first device.

[0245] In some embodiments, the second device determines whether to continue to renew the subscription according to the received second information, and provides the first device with a computing resource service fee if necessary, and instructs the first device to continue to provide the computing resource service. The first device determines whether to continue to provide the computing resource service for the second device according to the received message. If the first device continues to provide the computing resource service for the second device, the first device can send indication information to the second device, indicating that the first device continues to provide the computing resource and service for the second device.

[0246] In step S2203, the second device sends fourth information to the first device.

[0247] In some embodiments, the first device receives the fourth information sent by the second device.

[0248] The fourth information is used to request the third device to provide the computing resource for the second device.

[0249] In some embodiments, if the triggered event is that the computing resource has been insufficient or the computing service switching event, the second device can send fourth information to the first device for requesting other devices except the first device to provide computing resource.

[0250] In some embodiments, the third information and the fourth information can be carried in the same signaling or in different signaling.

[0251] In some embodiments, after receiving the fourth information, the first device can allocate the computing resource of the third device to the second device, so that the third device continues to provide the computing service and the computing resource for the first device.

[0252] In some embodiments, step S2203 is optional and can be omitted in different embodiments.

[0253] In step S2204, the first device releases the first computing resource.

[0254] In some embodiments, the first device releases the first computing resource based on the third information.

[0255] In some embodiments, the first device releases the computing resource based on the third computing resource identifier included in the third information.

[0256] In some embodiments, the first computing resource is released according to the priority corresponding to each computing resource identifier, and the first computing resource is all or part of the computing resource allocated by the first device to the second device.

[0257] In some embodiments, the first device releases the computing resource identifier corresponding to the third computing resource identifier according to the priority corresponding to the third computing resource identifier, and after releasing the computing resource each time, it can be judged whether the current computing resource release meets the condition, and if it meets the condition, it is not necessary to continue to release the computing resource, and if it does not meet the condition, it continues to release the computing resource according to the priority.

[0258] For example, the first device provides the second device with both inference of model 1 and inference of model 2, and allocates two computing resource to the two computing resource services, which correspond to computing resource ID 1 and computing resource ID 2 respectively. Assuming that the third information sent by the second device to the first device includes computing resource ID 1 and computing resource ID 2, and the priority of computing resource ID 2 is lower than that of computing resource ID 1. After receiving the third information, the second device determines the priority according to the computing resource ID, and releases the computing resource with lower priority first, that is, the computing resource corresponding to computing resource ID 2 is released first. If the released resource meets the demand of the first device, the first device does not need to release the computing resource corresponding to computing resource ID 1. If the released resource still cannot meet the demand of the first device, the first device continues to release the computing resource corresponding to computing resource ID 1.

[0259] In step S2205, the first device sends fifth information to the second device.

[0260] In some embodiments, the second device receives the fifth information sent by the first device.

[0261] In some embodiments, the fifth information is used to indicate that the first device has released the first computing resource.

[0262] In some embodiments, the fifth information can indicate whether the first device has released all or part of the computing resource allocated to the second device.

[0263] For example, the first device releases the computing resource corresponding to computing resource ID 2, and sends the fifth information to the second device, which indicates that the first device has released the computing resource corresponding to ID 2.

[0264] In some embodiments, step S2205 is optional and can be omitted in different embodiments.

[0265] In step S2206, the second device sends sixth information to the first device.

[0266] In some embodiments, the first device receives the sixth information sent by the second device.

[0267] In some embodiments, the sixth information is used to indicate that the second device has confirmed that the first device has released the first computing resource.

[0268] In some embodiments, after receiving the indication information of the first computing resource released by the first device, the second device can return a response message to the second device confirming that the first device has released the first computing resource, indicating that the second device knows that the first device has released the first computing resource.

[0269] For example, the second device receives the fifth information that the first device has released the computing resource corresponding to ID2, and the second device sends the sixth information to the first device, where the sixth information indicates that the second device has confirmed that the first device has released the computing resource corresponding to ID2.

[0270] In some embodiments, step S2206 is optional, and can be omitted in different embodiments.

[0271] The communication method provided by the embodiments of the present disclosure can save computing resources, by the first device sending second information for indicating release of computing resources to the second device based on an event trigger, and releasing the computing resources according to third information sent by the second device.

[0272] The following is an example of a scenario in which a network device provides computing resources to a terminal, i.e., taking the first device as a network device and the second device as a terminal as an example, but the present disclosure is not limited thereto.

[0273] In some embodiments, the network device sends second information for releasing computing resources to the terminal based on an event trigger. Possible events include, for example, that the computing service time has ended, that the network computing resources are insufficient, and the like.

[0274] In some embodiments, the second information can include computing resource ID information.

[0275] In some embodiments, if the computing resources of the network device are insufficient, the second information sent by the network device can further include other indication information of the computing resource sharing service, such as indicating that other network devices can provide computing services, suggesting the terminal to send a computing request to other network devices, or directly allocating computing resources provided by other network devices to the terminal.

[0276] In some embodiments, the network device or the terminal described above can also be a control unit for controlling the computing resource sharing service.

[0277] In some embodiments, the terminal sends third information to the network according to the received second information. The third information can include one or more computing resource IDs, and the priority of different computing resources can be determined according to the computing resource ID.

[0278] Optionally, the third information is a response message sent by the terminal to the network side to indicate that the computing release indication has been received, or a new request message requesting the network device to send a computing resource sharing service to other network devices to provide continuous computing services for the terminal.

[0279] In some embodiments, if the second information includes indication information of other network devices that can provide computing services, the terminal sends a computing resource sharing service request to the corresponding network device according to the indication information.

[0280] In some embodiments, the network device releases the computing power according to the received third information, and sends a response message of the computing power release to the terminal. The response message can be a release of all computing power resources or a release of part of the computing power resources.

[0281] The following illustrates the scenario of the terminal providing computing power resources to the network device, i.e., taking the first device as the terminal and the second device as the network device as an example, but the present disclosure is not limited thereto.

[0282] In some embodiments, the terminal sends the second information of the computing power release to the network device based on an event trigger. Possible events include, for example, the end of the computing power service time, the exhaustion of the computing power fee, the shortage of the computing power resources of the terminal itself, etc. Optionally, different events define different event IDs. The terminal also sends the event ID to the network device to indicate the event causing the release of the computing power resources.

[0283] In some embodiments, the second information indicates at least one or both of the computing power resource ID and the event ID.

[0284] In some embodiments, the network device initiates a new computing power sharing request to other terminals capable of providing computing power according to the received second information of the computing power release. Optionally, the network device sends a response message to the terminal after receiving the second information, indicating that the computing power release message has been received.

[0285] In some embodiments, the terminal receives the response message sent by the network side and confirms the corresponding execution action. Optionally, the terminal also sends the indication information of the execution action to the network.

[0286] In some embodiments, the above network device or terminal can also be a control unit for controlling the computing power resource sharing service.

[0287] The following illustrates the UE indicating the computing power release.

[0288] In some embodiments, for the computing power resources allocated by the UE, the UE can send an indication message of the computing power release to the gNB due to various events such as the end of the service time, the shortage of the computing power of the UE itself, etc. Different events can define different event IDs for the gNB to confirm the cause of the computing power release.

[0289] For example, the following events and corresponding event IDs are defined.

[0290] Event ID1: the end of the computing power service time;

[0291] Event ID2: the exhaustion of the computing power fee;

[0292] Event ID3: the shortage of the computing power resources of the UE;

[0293] Event ID 4: Other.

[0294] If event ID2 occurs, the UE sends second information to the gNB, the second information including the two messages of the computing resource ID and the event ID2. The gNB confirms whether to continue the fee according to the received second information, and lets the UE provide the computing power service. If necessary, the gNB provides the UE with the computing power service fee and indicates the UE to continue to provide the computing power service response message. The UE determines whether to continue to provide the computing power service for the gNB according to the received response message, and if the computing power service for the gNB is continued, the UE sends an indication information to the gNB, indicating that the UE continues to provide the computing power resource and service for the gNB.

[0295] The communication method related to the embodiments of the present disclosure can include at least one of steps S2201-S2206. For example, step S2204 can be implemented as an independent embodiment, and steps S2201+S2202+S2204 can be implemented as an independent embodiment, but are not limited thereto.

[0296] In some embodiments, step S2203 is optional, and one or more of these steps can be omitted or replaced in different embodiments.

[0297] In some embodiments, step S2205 is optional, and one or more of these steps can be omitted or replaced in different embodiments.

[0298] In some embodiments, step S2206 is optional, and one or more of these steps can be omitted or replaced in different embodiments.

[0299] In some embodiments, other optional implementations described before or after the corresponding description of FIG. 2B can be referred to.

[0300] FIG. 2C is an interaction diagram of a communication method according to an embodiment of the present disclosure.

[0301] In some embodiments, the communication method shown in FIG. 2C can be applied to a communication scenario in which the first device and the second device provide computing power resources to each other. For example, the first device allocates the first computing power resource of the first device to the second device, and the second device allocates the second computing power resource of the second device to the first device, wherein the first computing power resource and the second computing power resource can be associated through a first computing power resource identifier.

[0302] As shown in FIG. 2C, the embodiments of the present disclosure relate to a communication method, and the method includes:

[0303] Step S2301, the first device releases the first computing power resource.

[0304] In some embodiments, the first computing resource is a computing resource allocated by the first device to the second device.

[0305] In some embodiments, the first device can actively release the first computing resource.

[0306] In some embodiments, the first device can release the first computing resource based on an event trigger.

[0307] Step S2302, the first device sends fifth information to the second device.

[0308] The fifth information is used to indicate that the first device has released the first computing resource.

[0309] In some embodiments, the first device sends the fifth information to the second device after releasing the first computing resource, indicating to the second device that the first device has released the first computing resource.

[0310] In some embodiments, the fifth information includes a first computing resource identifier and / or an event identifier.

[0311] In some embodiments, the first computing resource identifier is associated with the first computing resource, and the first computing resource is a computing resource shared between the first device and the second device.

[0312] In some embodiments, the fifth information is used by the second device to determine whether to release a second computing resource, the second computing resource being a computing resource shared between the first device and the second device, and the second computing resource being associated with the first computing resource identifier.

[0313] In some embodiments, the first computing resource is a computing resource allocated by the first device to the second device, and the second computing resource is a computing resource allocated by the second device to the first device. That is, the first device and the second device share the first computing resource of the first device and the second computing resource of the second device.

[0314] In some embodiments, the fifth information includes a first computing resource identifier, and the first computing resource identifier is respectively associated with the first computing resource and the second computing resource. After receiving the fifth information, the second device can determine the second computing resource according to the first computing resource identifier, and thus determine whether to release the second computing resource.

[0315] In some embodiments, the fifth information includes an event identifier, which can indicate to the second device an event that triggers the first device to release the first computing resource.

[0316] Step S2303, the second device sends sixth information to the first device.

[0317] In some embodiments, the first device receives the sixth information sent by the second device.

[0318] The sixth information is used to indicate that the second device has confirmed that the first device has released the first computing resource.

[0319] In some embodiments, after receiving the indication information sent by the first device that the first computing resource has been released, the second device can return a response message to the second device indicating that the first device has released the first computing resource, indicating that the second device has known that the first device has released the first computing resource.

[0320] In some embodiments, step S2303 is optional and can be omitted in different embodiments.

[0321] In step S2304, the second device releases or does not release the second computing resource.

[0322] In some embodiments, the second computing resource is a computing resource allocated by the second device to the first device, and the second computing resource is associated with the first computing resource identifier.

[0323] In some embodiments, the second device can release the second computing resource to save computing resources and improve the utilization rate of computing resources.

[0324] In some embodiments, the second device can not release the second computing resource for other devices to continue using.

[0325] The execution order of steps S2303 and S2304 is not limited in the embodiments of the present disclosure. For example, step S2303 can be executed first and then step S2304 can be executed, or step S2304 can be executed first and then step S2303 can be executed.

[0326] In some embodiments, if the computing resource of the terminal or the network side is released, the corresponding computing resource of the opposite network or terminal is also released accordingly. The terminal or the network sends third information to the opposite side to indicate that the terminal computing resource has been released, and the opposite side releases the corresponding computing resource according to the received third information.

[0327] In some embodiments, the computing resources of the terminal side and the network side are associated by a computing resource ID.

[0328] In some embodiments, the third information at least includes the computing resource ID.

[0329] Optionally, the network or the terminal sends a response message to the opposite side to indicate that the computing resource release request has been received.

[0330] In some embodiments, if the computing resource of the terminal or the network side is released, the corresponding computing resource of the opposite network or terminal is not released accordingly. The terminal or the network sends third information to the opposite side to indicate that the computing resource has been released. Optionally, the third information further includes event ID indication information, and the event ID is associated with the event causing the release of the computing resource.

[0331] The first device is a network device and the second device is a terminal as an example, but the present disclosure is not limited thereto.

[0332] In some embodiments, if the computing resource of the network device is released, the terminal also releases the computing resource accordingly. The network device sends third information to the terminal to indicate that the computing resource of the terminal has been released, and the terminal releases the corresponding computing resource according to the received third information.

[0333] In some embodiments, the computing resources of the terminal and the network device are associated through a computing resource ID.

[0334] In some embodiments, the third information at least includes the computing resource ID.

[0335] Optionally, the network device sends a response message to the terminal to indicate that the computing resource release request has been received.

[0336] In other embodiments, if the computing resource of the network device is released, the network device can not release the computing resource accordingly. The network device sends third information to the terminal to indicate that the computing resource has been released. Optionally, the third information also includes an event ID associated with the event causing the release of the computing resource.

[0337] The first device is a terminal and the second device is a network device as an example, but the present disclosure is not limited thereto.

[0338] In some embodiments, if the computing resource of the terminal is released, the network device also releases the computing resource accordingly. The terminal sends third information to the network device to indicate that the computing resource of the terminal has been released, and the network device releases the corresponding computing resource according to the received third information.

[0339] In some embodiments, the computing resources of the terminal and the network device are associated through a computing resource ID.

[0340] In some embodiments, the third information at least includes the computing resource ID.

[0341] Optionally, the terminal sends a response message to the network device to indicate that the computing resource release request has been received.

[0342] In other embodiments, if the computing resource of the terminal is released, the network device can not release the computing resource accordingly. The terminal sends third information to the network device to indicate that the computing resource has been released. Optionally, the third information also includes an event ID associated with the event causing the release of the computing resource.

[0343] The communication method provided in the embodiments of the present disclosure relates to a computing resource release workflow, which can flexibly notify the opposite end about the computing resource release situation and avoid waste of computing resources.

[0344] The communication method provided in the embodiments of the present disclosure can include at least one of steps S2301-S2304. For example, step S2301 can be implemented as an independent embodiment, and steps S2301+S2302 can be implemented as an independent embodiment, but are not limited thereto.

[0345] In some embodiments, step S2303 is optional, and one or more of these steps can be omitted or replaced in different embodiments.

[0346] In some embodiments, step S2304 is optional, and one or more of these steps can be omitted or replaced in different embodiments.

[0347] In some embodiments, other optional implementations described before or after the corresponding description of FIG. 2C can be referred to.

[0348] In some embodiments, the names of information, etc. are not limited to the names described in the embodiments, and the terms of “information”, “message”, “signal”, “signaling”, “report”, “configuration”, “indication”, “instruction”, “command”, “channel”, “parameter”, “domain”, “field”, “symbol”, “symbol”, “codebook”, “codeword”, “codepoint”, “bit”, “data”, “program”, “chip”, etc. can be replaced with each other.

[0349] In some embodiments, the terms of “time”, “time point”, “time”, “time position”, etc. can be replaced with each other, and the terms of “time length”, “time period”, “time window”, “window”, “time”, etc. can be replaced with each other.

[0350] In some embodiments, “acquire”, “obtain”, “get”, “receive”, “transmit”, “bidirectional transmission”, “send and / or receive” can be replaced with each other, which can be interpreted as receiving from other subjects, obtaining from protocols, obtaining from high layers, obtaining by self-processing, independently implementing, and other meanings.

[0351] In some embodiments, the terms “sending”, “transmitting”, “reporting”, “issuing”, “transferring”, “bidirectional transferring”, “sending and / or receiving”, and the like can be replaced by each other.

[0352] In some embodiments, the terms “certain”, “preseted”, “preset”, “set”, “indicated”, “certain”, “arbitrary”, “first”, and the like can be replaced by each other, and “certain A”, “preset A”, “preset A”, “set A”, “indicated A”, “certain A”, “arbitrary A”, “first A” can be interpreted as A specified in advance in a protocol or the like, or A obtained by setting, configuration, or indication, or A specific, certain, arbitrary, or first, but not limited thereto.

[0353] In some embodiments, determination or judgment can be made by a value represented by 1 bit (0 or 1), or by a true or false value (Boolean value) represented by true or false, or by comparison of numerical values (for example, comparison with a predetermined value), but not limited thereto.

[0354] In some embodiments, “not expecting to receive” can be interpreted as not receiving on time domain resources and / or frequency domain resources, or as not performing subsequent processing on the data or the like after receiving the data or the like; “not expecting to send” can be interpreted as not sending, or as sending but not expecting the receiving party to respond to the content of the sending.

[0355] FIG. 3A is a flow diagram of a communication method according to an embodiment of the present disclosure. As shown in FIG. 3A, the present disclosure relates to a communication method, and the above method comprises:

[0356] Step S3101, the first device receives the first information sent by the second device.

[0357] The optional implementation of step S3101 can refer to the optional implementation of step S2101 of FIG. 2A and other associated parts in the embodiments involved in FIG. 2A, which will not be repeated here.

[0358] Step S3102, the first device releases the first computing resource.

[0359] The optional implementation of step S3102 can refer to the optional implementation of step S2103 of FIG. 2A and other associated parts in the embodiments involved in FIG. 2A, which will not be repeated here.

[0360] The communication method related to the embodiments of the present disclosure can include at least one of steps S3101-S3102. For example, step S3102 can be implemented as an independent embodiment.

[0361] In some embodiments, step S3101 is optional, and one or more of these steps can be omitted or replaced in different embodiments.

[0362] FIG. 3B is a flow diagram of a communication method according to an embodiment of the present disclosure. As shown in FIG. 3B, the embodiments of the present disclosure relate to a communication method, and the above method includes:

[0363] In step S3201, the first device sends second information to the second device.

[0364] Optional implementation of step S3201 can refer to optional implementation of step S2201 in FIG. 2B and other associated parts in the embodiments related to FIG. 2B, which will not be described here.

[0365] In step S3202, the first device receives third information sent by the second device.

[0366] Optional implementation of step S3202 can refer to optional implementation of step S2202 in FIG. 2B and other associated parts in the embodiments related to FIG. 2B, which will not be described here.

[0367] In step S3203, the first device releases the first computing resource.

[0368] Optional implementation of step S3203 can refer to optional implementation of step S2204 in FIG. 2B and other associated parts in the embodiments related to FIG. 2B, which will not be described here.

[0369] The communication method related to the embodiments of the present disclosure can include at least one of steps S3201-S3203. For example, step S3203 can be implemented as an independent embodiment.

[0370] In some embodiments, step S3201 is optional, and one or more of these steps can be omitted or replaced in different embodiments.

[0371] In some embodiments, step S3203 is optional, and one or more of these steps can be omitted or replaced in different embodiments.

[0372] FIG. 3C is a flow diagram of a communication method according to an embodiment of the present disclosure. As shown in FIG. 3C, the embodiments of the present disclosure relate to a communication method, and the above method includes:

[0373] The first device releases the first computing resource, in step S3301.

[0374] The optional implementation of step S3301 can refer to the optional implementation of step S2301 in FIG. 2C and other associated parts in the embodiments involved in FIG. 2C, which will not be repeated here.

[0375] The first device sends fifth information to the second device, in step S3302.

[0376] The optional implementation of step S3302 can refer to the optional implementation of step S2302 in FIG. 2C and other associated parts in the embodiments involved in FIG. 2C, which will not be repeated here.

[0377] The communication method involved in the embodiments of the present disclosure can include at least one of steps S3301-S3302. For example, step S3301 can be implemented as an independent embodiment.

[0378] In some embodiments, step S3302 is optional, and one or more of these steps can be omitted or replaced in different embodiments.

[0379] FIG. 4A is a flow diagram of a communication method according to the embodiments of the present disclosure. As shown in FIG. 4A, the embodiments of the present disclosure involve a communication method, and the above method includes:

[0380] The second device sends first information to the first device, in step S4101.

[0381] The optional implementation of step S4101 can refer to the optional implementation of step S2101 in FIG. 2A and other associated parts in the embodiments involved in FIG. 2A, which will not be repeated here.

[0382] The second device sends sixth information to the first device, in step S4102.

[0383] The optional implementation of step S4102 can refer to the optional implementation of step S2105 in FIG. 2A and other associated parts in the embodiments involved in FIG. 2A, which will not be repeated here.

[0384] The communication method involved in the embodiments of the present disclosure can include at least one of steps S4101-S4102. For example, step S4101 can be implemented as an independent embodiment.

[0385] In some embodiments, step S4102 is optional, and one or more of these steps can be omitted or replaced in different embodiments.

[0386] FIG. 4B is a flow diagram of a communication method according to some embodiments of the present disclosure. As shown in FIG. 4B, the embodiments of the present disclosure relate to a communication method, which includes the following steps.

[0387] At step S4201, the second device receives the second information sent by the first device.

[0388] Optional implementation of step S4201 can refer to optional implementation of step S2201 in FIG. 2B and other associated parts in embodiments related to FIG. 2B. Here, no longer be repeated.

[0389] At step S4202, the second device sends the third information to the first device.

[0390] Optional implementation of step S4202 can refer to optional implementation of step S2202 in FIG. 2B and other associated parts in embodiments related to FIG. 2B. Here, no longer be repeated.

[0391] The communication method related to the embodiments of the present disclosure can include at least one of steps S4201-S4202. For example, step S4202 can be implemented as an independent embodiment.

[0392] In some embodiments, step S4201 is optional, and one or more of these steps can be omitted or replaced in different embodiments.

[0393] FIG. 4C is a flow diagram of a communication method according to some embodiments of the present disclosure. As shown in FIG. 4C, the embodiments of the present disclosure relate to a communication method, which includes the following steps.

[0394] At step S4301, the second device receives the fifth information sent by the first device.

[0395] Optional implementation of step S4301 can refer to optional implementation of step S2302 in FIG. 2C and other associated parts in embodiments related to FIG. 2C. Here, no longer be repeated.

[0396] At step S4302, the second device sends the sixth information to the first device.

[0397] Optional implementation of step S4302 can refer to optional implementation of step S2303 in FIG. 2C and other associated parts in embodiments related to FIG. 2C. Here, no longer be repeated.

[0398] At step S4303, the second device releases / does not release the second computing resource.

[0399] Optional implementation of step S4303 can refer to optional implementation of step S2304 in FIG. 2C and other associated parts in embodiments related to FIG. 2C. Here, no longer be repeated.

[0400] The communication method related to the embodiments of the present disclosure can include at least one of steps S4301-S4303. For example, step S4303 can be implemented as an independent embodiment, and steps S4301+S4303 can be implemented as an independent embodiment.

[0401] In some embodiments, step S4302 is optional, and one or more of these steps can be omitted or replaced in different embodiments.

[0402] FIG. 5A is an interaction diagram of a communication method according to an embodiment of the present disclosure.

[0403] In some embodiments, the communication method shown in FIG. 5A can be applied to a communication scenario in which a first device provides computing resource to a second device.

[0404] In some embodiments, the first device can be a gNB, and the second device can be a terminal.

[0405] As shown in FIG. 5A, the embodiments of the present disclosure relate to a communication method, and the method includes:

[0406] Step S5101, the UE sends first information to the gNB.

[0407] In some embodiments, it is assumed that the gNB has provided the UE with both inference of model 1 and inference of model 2 computing services, and that two computing resources are allocated for these two computing services, denoted as computing resource ID1 and computing resource ID2.

[0408] In some embodiments, if the UE does not want the gNB to provide inference service of model 2, the UE sends a first message to the gNB to request the gNB to release the computing resource, and the first message can include the computing resource ID.

[0409] Step S5102, the gNB sends a computing resource release response message to the UE.

[0410] In some embodiments, after receiving the first message, the gNB can send a response message to the UE indicating that the UE has released the computing service.

[0411] Optionally, the UE can also send a confirmation message to the gNB that the gNB has completed the release of the service.

[0412] FIG. 5B is an interaction diagram of a communication method according to an embodiment of the present disclosure.

[0413] In some embodiments, the communication method shown in FIG. 5B can be applied to a communication scenario in which a first device provides computing resource to a second device.

[0414] In some embodiments, the first device can be a gNB, and the second device can be a terminal.

[0415] As shown in FIG. 5B, the embodiments of the present disclosure relate to a communication method, and the method comprises:

[0416] In step S5201, the gNB sends second information to the UE.

[0417] In some embodiments, it is assumed that the gNB has provided the UE with both inference of Model 1 and inference of Model 2, and it is assumed that two computing resource resources are allocated for the two computing resource services, which are represented as computing resource resource ID 1 and computing resource resource ID 2.

[0418] In some embodiments, the priority of the computing resource resource ID 1 is higher than the priority of the computing resource resource ID 2.

[0419] In some embodiments, if the computing resource resources of the gNB have been exhausted, the UE needs to be instructed to release part of the computing resource resources. The gNB will send a second message to the UE to indicate the request for computing resource release.

[0420] In step S5202, the UE sends third information to the gNB.

[0421] In some embodiments, after receiving the second information, the UE sends third information to the gNB, and the third information can include the computing resource resource ID 1 and the computing resource resource ID 2.

[0422] In step S5203, the gNB releases according to the priority of the computing resource resource.

[0423] In some embodiments, after receiving the third information, the gNB releases the computing resource resource with a lower priority according to the priority determined by the computing resource resource ID, that is, the computing resource resource ID 2 is released first. If the released resource still cannot meet the demand of the gNB, the gNB can further release the computing resource resource corresponding to the computing resource resource ID 1.

[0424] In step S5204, the gNB sends a computing resource release response message to the UE.

[0425] In some embodiments, after completing the release of the computing resource resource, the gNB sends a response message to the UE, which can indicate that the gNB has released the computing resource resource ID 2. The gNB can still provide the UE with the computing resource service of the computing resource resource ID 1.

[0426] Optionally, the UE can send a confirmation message to the gNB to confirm that the gNB has released the computing resource resource corresponding to the computing resource resource ID 2.

[0427] The embodiments of the present disclosure propose a method and working signaling process for how to release the allocated computing power, so as to realize flexible computing power release between the providers of computing power service and the receivers of computing power service.

[0428] In some embodiments, the network side provides the computing power service.

[0429] In some embodiments, the terminal sends the first information to the network side through signaling to indicate the computing power release request.

[0430] In some embodiments, the first information at least contains the computing power resource ID information, which is associated with the allocated computing power resource.

[0431] In some embodiments, the terminal sends the third information to the network side according to the received second information. The third information contains one or more computing power resource IDs, and the priority of different computing power resources can be determined according to the computing power resource ID. Alternatively, the third information is a response message sent by the terminal to the network side to indicate that the computing power release indication is received, or a new request message to request the network to send the computing power sharing service to other networks to provide the terminal with continuous computing power service.

[0432] In some embodiments, if the second indication information contains the indication information of other networks that can provide the computing power service, the terminal sends the computing power sharing service request to the corresponding network according to the indication information.

[0433] In some embodiments, the network releases the computing power resource allocated to the terminal according to the received first information. Alternatively, the network side sends a response message to the terminal to indicate that the computing power resource is released.

[0434] In some embodiments, the network sends the second information to the terminal to release the computing power resource based on an event trigger. For example, the possible events include that the computing power service time has ended, the network computing power resource is insufficient, etc.

[0435] In some embodiments, the second information indication at least contains the computing power resource ID information.

[0436] In some embodiments, if the network computing power resource is insufficient, the second indication information sent by the network further includes other indication information of the computing power sharing service, such as indicating that other networks can provide the computing power service, suggesting the terminal to send the computing power request to other networks, or directly allocating the computing power provided by other networks to the terminal.

[0437] In some embodiments, the network side releases the computing power according to the received third information, and sends a response message of the computing power release to the terminal, such as releasing all the computing power resources or releasing part of the computing power resources.

[0438] In some embodiments, the terminal side provides the computing power service.

[0439] In some embodiments, the network sends the first information to the terminal through signaling to indicate the request for releasing the computing power. The signaling can be sent to each terminal individually or through broadcasting to multiple terminals.

[0440] In some embodiments, the first information at least contains the computing power resource ID information, which is associated with the allocated computing power resource.

[0441] In some embodiments, the network initiates a new computing power sharing request to other terminals that can provide computing power after receiving the second information for releasing the computing power. Optionally, the network sends a response information to the terminal after receiving the second indication information, indicating that the message for releasing the computing power resource has been received.

[0442] In some embodiments, the terminal releases the computing power resource allocated to the network according to the received first information. Optionally, the terminal sends a response message to the network indicating that the indication message for releasing the computing power resource has been received.

[0443] In some embodiments, the terminal sends the second information for releasing the computing power resource to the network based on an event trigger. For example, the possible events include that the computing power service time has ended or the computing power fee has been used up, or the computing power resource of the terminal itself is insufficient, etc. Optionally, different events define different event IDs, and the terminal also sends an event ID to the network to indicate the event causing the release of the computing power resource.

[0444] In some embodiments, the second information at least contains one or both of the computing power resource ID or the event ID information.

[0445] In some embodiments, the terminal receives the response message sent by the network side to confirm the corresponding execution action. Optionally, the terminal also sends the indication information of the execution action to the network.

[0446] Note: The network side or terminal side mentioned above can also be a control unit for controlling the computing power resource sharing service.

[0447] In some embodiments, the computing power is shared between the terminal and the network.

[0448] In some embodiments, if the computing power resource of the terminal or the network side is released, the corresponding computing power resource of the opposite network or terminal is also released accordingly. The terminal or the network sends the third information to the opposite side to indicate that the computing power resource of the terminal has been released, and the opposite side releases the corresponding computing power resource according to the received third information.

[0449] In some embodiments, the computing power resources of the terminal side and the network side are associated through a computing power resource ID.

[0450] In some embodiments, the third information at least contains the computing power resource ID.

[0451] Optionally, the network or the terminal re-sends a response message to the opposite end indicating that the computing power release request has been received.

[0452] In some embodiments, if the computing power resources of the terminal or the network side are released, the opposite end network or terminal accordingly does not release the computing power resources. The terminal or the network sends third information to the opposite end indicating that the computing power resources have been released. Optionally, the third information also includes event ID indication information, and the event ID is associated with the event causing the release of the computing power resources.

[0453] In some embodiments, the network side provides computing power services:

[0454] Suppose that a gNB has provided a UE with both model 1 inference and model 2 inference computing power services, and suppose that two computing power resources are allocated for these two computing power services, denoted as computing power resource ID 1 and computing power resource ID 2. Without loss of generality, it is defined that the priority of computing power resource ID 1 is higher than that of computing power resource ID 2.

[0455] In some embodiments, the UE sends a request for computing power release.

[0456] If the UE does not want the gNB to provide model 2 inference services, the UE sends a first message to the network requesting the gNB to release the computing power, and the first message can include the computing power resource ID. After receiving the first message, the gNB sends a response message to the UE indicating that the UE has released the computing power service. Optionally, the UE also sends a confirmation message to the gNB confirming that the gNB has completed the release of the service.

[0457] In some embodiments, the gNB indicates computing power release.

[0458] If the computing power resources of the gNB have been exhausted, the gNB needs to indicate to the UE to release part of the computing power resources. The gNB will send a second message to the UE indicating the request for computing power release. After receiving the second information, the UE sends a third information to the gNB, and the third information includes computing power resource ID 1 and computing power resource ID 2. After receiving the third information, the gNB releases the computing power resources with lower priority first according to the priority determined by the computing power resource ID, that is, the resources corresponding to computing power resource ID 2 are released first. If the released resources still cannot meet the demand of the gNB, the gNB can further release the computing power resources corresponding to computing power resource ID 1. After completing the release of the computing power resources, the gNB sends a response message to the UE, such as a response message indicating that the gNB has released the resources corresponding to computing power resource ID 2. The gNB can still provide the UE with computing power services of computing power resource ID 1. Optionally, the UE also sends a confirmation message to the gNB confirming that the gNB has released the resources corresponding to computing power resource ID 2.

[0459] In some embodiments, the terminal side provides computing power services.

[0460] The gNB may need many UEs to provide training data set for model training, considering the privacy of data set, part of data set is not suitable to send to the network. In order to solve this problem, the training of the model is divided into distributed federated learning, that is, each UE participates in the training process of the model, which requires the UE to provide computing power service for the network.

[0461] Assuming that the gNB has informed the UE to provide computing power service through signaling broadcast, the UE providing computing power service will allocate a certain computing power resource. Different computing power requests can be associated with different computing power resource IDs. Assuming that the computing power ID is contained in the broadcast message sent by the gNB to the UE.

[0462] In some embodiments, the gNB requests computing power release.

[0463] If the model training has been completed, the UE no longer needs to provide computing power service. At this time, the gNB can inform each UE to release the computing power resource by sending a broadcast message. The broadcast message contains the relevant computing power resource ID. The UE releases the computing power resource ID according to the received broadcast message, and sends a response message to the gNB that the computing power resource release has been completed. Optionally, the gNB also sends a confirmation message to the UE that the computing power resource release has been received.

[0464] In some embodiments, the UE indicates computing power release.

[0465] For the computing power resource allocated by the UE, it may cause the UE to send an indication message to the gNB to release the computing power due to various events such as the end of service time, insufficient computing power of the UE itself, etc. Different events can define different event IDs, which are used by the gNB to confirm the cause of the computing power release.

[0466] For example, the following events and corresponding event IDs are defined.

[0467] Event ID1: the computing power service time has ended;

[0468] Event ID2: the computing power fee has been used up;

[0469] Event ID3: the computing power resource of the UE is insufficient;

[0470] Event ID4: others.

[0471] If the event ID2 occurs, the UE sends second information to the gNB, the second information contains the computing resource ID and the event ID2. The gNB determines whether to continue to charge the UE according to the received second information, and if necessary, the gNB provides the computing resource service cost for the UE and sends a response message to the UE to continue to provide the computing resource service. The UE determines whether to continue to provide the computing resource service for the gNB according to the received response message, and if the UE continues to provide the computing resource service for the gNB, the UE sends indication information to the gNB to indicate that the UE continues to provide the computing resource service for the gNB.

[0472] The embodiments of the present disclosure propose a method and a working signaling flow for how to release the allocated computing resource, so as to realize flexible computing resource release between the providers of providing and receiving the computing resource service.

[0473] In the embodiments of the present disclosure, part or all of the steps, and optional implementation manners thereof, can be combined with part or all of the steps in other embodiments, or can be combined with optional implementation manners of other embodiments.

[0474] The embodiments of the present disclosure also propose an apparatus for implementing any of the above methods, for example, an apparatus including units or modules for implementing each step performed by the terminal in any of the above methods. For another example, another apparatus is proposed, including units or modules for implementing each step performed by the network device (such as an access network device, a core network function node, a core network device, etc.) in any of the above methods.

[0475] It should be understood that the division of each unit or module in the above apparatus is only a logical function division, and all or part of them can be integrated into a physical entity or physically separated in actual implementation. In addition, the units or modules in the apparatus can be implemented in the form of processor calling software: for example, the apparatus includes a processor connected with a memory, the memory stores instructions, and the processor calls the instructions stored in the memory to implement any of the above methods or realize the functions of each unit or module of the above apparatus, wherein the processor is, for example, a general processor such as a central processing unit (CPU) or a microprocessor, and the memory is a memory within the apparatus or a memory outside the apparatus. Alternatively, the units or modules in the apparatus can be implemented in the form of hardware circuit, and the functions of part or all of the units or modules can be realized by the design of the hardware circuit. The above hardware circuit can be understood as one or more processors; for example, in one implementation, the above hardware circuit is an application-specific integrated circuit (ASIC), and the functions of part or all of the above units or modules are realized by the design of the logical relationship of the elements in the circuit; for example, in another implementation, the above hardware circuit is a programmable logic device (PLD), and a field programmable gate array (FPGA) is taken as an example, which can include a large number of logic gate circuits, and the connection relationship between the logic gate circuits is configured by a configuration file, so as to realize the functions of part or all of the above units or modules. All units or modules of the above apparatus can be implemented in the form of processor calling software, or all units or modules can be implemented in the form of hardware circuit, or part of the units or modules are implemented in the form of processor calling software, and the remaining part is implemented in the form of hardware circuit.

[0476] In the embodiments of the present disclosure, the processor is a circuit with signal processing capability. In one implementation, the processor can be a circuit with instruction reading and running capability, such as a central processing unit (CPU), a microprocessor, a graphics processing unit (GPU) (which can be understood as a microprocessor), a digital signal processor (DSP), or the like. In another implementation, the processor can implement certain functions through a logical relationship of a hardware circuit, and the logical relationship of the hardware circuit is fixed or can be reconfigured. For example, the processor is a hardware circuit implemented by an application-specific integrated circuit (ASIC) or a programmable logic device (PLD), such as an FPGA. In the reconfigurable hardware circuit, the processor loads a configuration document to implement the configuration of the hardware circuit. It can be understood that the processor loads instructions to implement the functions of the above part or all units or modules. In addition, it can also be a hardware circuit designed for artificial intelligence, which can be understood as an ASIC, such as a neural network processing unit (NPU), a tensor processing unit (TPU), a deep learning processing unit (DPU), and the like.

[0477] FIG. 6A is a structural schematic diagram of a first device according to an embodiment of the present disclosure. As shown in FIG. 6A, the first device 6100 can include a processing module 6101.

[0478] In some embodiments, the processing module 6101 releases a first computing resource, and the first computing resource is a computing resource allocated by the first device to a second device.

[0479] In some embodiments, the first device further includes a transceiver module, configured to receive first information sent by the second device, and the first information is used to request to release the first computing resource.

[0480] In some embodiments, the first information includes a first computing resource identifier, and the first computing resource identifier is associated with the first computing resource.

[0481] In some embodiments, the transceiver module is configured to send second information to the second device, and the second information is used to indicate to release a computing resource.

[0482] In some embodiments, the second information is sent based on an event trigger, the second information comprising a second computing resource identifier and / or an event identifier, the second computing resource identifier being used to identify the computing resource indicated to be released by the first device.

[0483] In some embodiments, the event comprises at least one of: an end of a computing service time; a shortage of computing resources; an exhaustion of computing fees; a switching of a computing service.

[0484] In some embodiments, the second information is further used to indicate a third device providing computing resources.

[0485] In some embodiments, the transceiver is configured to receive third information sent by the second device, the third information comprising a third computing resource identifier, the third computing resource identifier comprising one or more computing resource identifiers, each computing resource identifier corresponding to a priority of a computing resource, the third computing resource identifier being used to identify the computing resource determined by the second device to be released based on the second information.

[0486] In some embodiments, the first computing resource is released according to the priority corresponding to each computing resource identifier, the first computing resource being all or part of the computing resources allocated by the first device to the second device.

[0487] In some embodiments, the transceiver is configured to receive fourth information sent by the second device, the fourth information being used to request a third device to provide computing resources for the second device.

[0488] In some embodiments, the third information is used to indicate at least one of: whether the second device renews the fees; whether the second device continues to provide computing resources through the first device.

[0489] In some embodiments, the transceiver is configured to send fifth information to the second device, the fifth information being used to indicate that the first computing resource has been released by the first device.

[0490] In some embodiments, the fifth information comprises a first computing resource identifier and / or an event identifier, the first computing resource identifier being associated with the first computing resource, the first computing resource being a computing resource shared between the first device and the second device; the fifth information being used by the second device to determine whether to release a second computing resource, the second computing resource being a computing resource shared between the first device and the second device, the second computing resource being associated with the first computing resource identifier.

[0491] In some embodiments, the transceiver module is configured to receive sixth information sent by the second device, the sixth information being used to indicate that the second device has confirmed that the first device has released the first computing resource.

[0492] FIG. 6B is a structural schematic diagram of a second device according to an embodiment of the present disclosure. As shown in FIG. 6B, the second device 6200 can include a processing module 6201.

[0493] In some embodiments, the processing module 6201 is configured to determine, by the second device, a first computing resource, the first computing resource being a computing resource allocated to the second device by the first device.

[0494] In some embodiments, the second device can further include a transceiver module configured to send first information to the first device, the first information being used to request to release the first computing resource.

[0495] In some embodiments, the first information includes a first computing resource identifier, the first computing resource identifier being associated with the first computing resource.

[0496] In some embodiments, the transceiver module is configured to receive second information sent by the first device, the second information being used to indicate to release a computing resource.

[0497] In some embodiments, the second information is sent based on an event, the second information including a second computing resource identifier and / or an event identifier, the second computing resource identifier being used to identify the computing resource indicated to be released by the first device.

[0498] In some embodiments, the event includes at least one of: an end of a computing service time; a shortage of computing resources; an exhaustion of computing fees; and a switching of a computing service.

[0499] In some embodiments, the second information is further used to indicate a third device providing the computing resource.

[0500] In some embodiments, the transceiver module is configured to send third information to the first device, the third information including a third computing resource identifier, the third computing resource identifier including one or more computing resource identifiers, each computing resource identifier corresponding to a priority of a computing resource, the third computing resource identifier being used to identify the computing resource determined by the second device to be released based on the second information.

[0501] In some embodiments, the first computing resource is released according to the priority corresponding to each computing resource identifier, the first computing resource being all or part of the computing resource allocated to the second device by the first device.

[0502] In some embodiments, the transceiving module is configured to receive fourth information from the first device, the fourth information being used to request the third device to provide computing resource for the second device.

[0503] In some embodiments, the third information is used to indicate at least one of the following: whether the second device renews the computing resource; whether the second device continues to provide the computing resource through the first device.

[0504] In some embodiments, the transceiving module is configured to receive fifth information from the first device, the fifth information being used to indicate that the first device has released the first computing resource.

[0505] In some embodiments, the fifth information comprises a first computing resource identifier and / or an event identifier, the first computing resource identifier being associated with the first computing resource, the first computing resource being a computing resource shared between the first device and the second device; and the fifth information is used by the second device to determine whether to release a second computing resource, the second computing resource being a computing resource shared between the first device and the second device, the second computing resource being associated with the first computing resource identifier.

[0506] In some embodiments, the transceiving module is configured to send sixth information to the first device, the sixth information being used to indicate that the second device has confirmed that the first device has released the first computing resource.

[0507] In some embodiments, the processing module can be one module, or can comprise a plurality of sub-modules. Optionally, the plurality of sub-modules respectively perform all or part of the steps required to be performed by the processing module. Optionally, the processing module can be mutually replaced with the processor.

[0508] FIG. 7A is a structural schematic diagram of a communication device 7100 according to the embodiments of the present disclosure. The communication device 7100 can be a network device (for example, an access network device, a core network device, etc.), a terminal (for example, a user equipment, etc.), a chip, a chip system, or a processor supporting the network device to implement any of the above methods, or a chip, a chip system, or a processor supporting the terminal to implement any of the above methods. The communication device 7100 can be used to implement the methods described in the above method embodiments, and details can be referred to the descriptions in the above method embodiments.

[0509] As shown in FIG. 7A, the communication device 7100 includes one or more processors 7101. The processor 7101 can be a general processor or a special-purpose processor, etc., such as a baseband processor or a central processing unit. The baseband processor can be configured to process communication protocols and communication data, and the central processing unit can be configured to control a communication apparatus (e.g., a base station, a baseband chip, a terminal device, a terminal device chip, a DU or a CU, etc.), execute programs, and process data of the programs. Optionally, the communication device 7100 is configured to perform any of the above methods. Optionally, the one or more processors 7101 are configured to invoke instructions to cause the communication device 7100 to perform any of the above methods.

[0510] In some embodiments, the communication device 7100 further includes one or more transceivers 7102. When the communication device 7100 includes one or more transceivers 7102, the transceiver 7102 performs at least one of the communication steps (e.g., step S2101, but not limited to) in the above methods, and the processor 7101 performs at least one of the other steps (e.g., step S2103, but not limited to). In optional embodiments, the transceiver can include a receiver and / or a transmitter, which can be separate or integrated together. Optionally, the terms transceiver, transceiving unit, transceiver, transceiving circuit, interface circuit, interface, etc. can be replaced by each other, and the terms transmitter, transmitting unit, transmitter, transmitting circuit, etc. can be replaced by each other, and the terms receiver, receiving unit, receiver, receiving circuit, etc. can be replaced by each other.

[0511] In some embodiments, the communication device 7100 further includes one or more memories 7103 for storing data. Optionally, all or part of the memory 7103 can also be outside the communication device 7100. In optional embodiments, the communication device 7100 can include one or more interface circuits 7104. Optionally, the interface circuit 7104 is connected to the memory 7103, and the interface circuit 7104 can be configured to receive data from the memory 7103 or other devices, and can be configured to send data to the memory 7103 or other devices. For example, the interface circuit 7104 can read data stored in the memory 7103 and send the data to the processor 7101.

[0512] The communication device 7100 described in the above embodiments can be a network device or a terminal, but the scope of the communication device 7100 described in the present disclosure is not limited thereto, and the structure of the communication device 7100 can not be limited by FIG. 7A. The communication device can be a standalone device or can be part of a larger device. For example, the communication device can be: 1) a standalone integrated circuit (IC), or a chip, or a chip system or subsystem; (2) a set of one or more ICs, which can optionally also include storage components for storing data, programs; (3) an ASIC, such as a modem; (4) a module that can be embedded in other devices; (5) a receiver, a terminal device, a smart terminal device, a cellular phone, a wireless device, a handset, a mobile unit, a vehicle-mounted device, a network device, a cloud device, an artificial intelligence device, and the like; (6) other devices, and the like.

[0513] FIG. 7B is a structural diagram of a chip 7200 according to an embodiment of the present disclosure. For the case where the communication device 7100 is a chip or a chip system, the structural diagram of the chip 7200 shown in FIG. 7B can be referred to, but is not limited thereto.

[0514] The chip 7200 includes one or more processors 7201. The chip 7200 is configured to perform any of the above methods.

[0515] In some embodiments, the chip 7200 further includes one or more interface circuits 7202. Optionally, the terms interface circuit, interface, transceiver pin, and the like can be replaced with each other. In some embodiments, the chip 7200 further includes one or more memories 7203 for storing data. Optionally, all or part of the memory 7203 can be outside the chip 7200. Optionally, the interface circuit 7202 is connected to the memory 7203, and the interface circuit 7202 can be configured to receive data from the memory 7203 or other devices, and the interface circuit 7202 can be configured to send data to the memory 7203 or other devices. For example, the interface circuit 7202 can read data stored in the memory 7203 and send the data to the processor 7201.

[0516] In some embodiments, the interface circuit 7202 performs at least one of the communication steps (for example, step S2101, but not limited thereto) of transmitting and / or receiving in the above methods. The interface circuit 7202 performing the communication steps such as transmitting and / or receiving in the above methods means that the interface circuit 7202 performs data interaction between the processor 7201, the chip 7200, the memory 7203, or a transceiver device. In some embodiments, the processor 7201 performs at least one of the other steps (for example, step S2103, but not limited thereto).

[0517] The modules and / or devices described in various embodiments of the virtual device, the physical device, the chip, etc. can be combined or separated according to circumstances. Alternatively, part or all of the steps can also be performed by a plurality of modules and / or devices in cooperation, which is not limited here.

[0518] The disclosure further provides a storage medium having stored instructions which, when executed on the communication device 7100, cause the communication device 7100 to perform any of the above methods. Alternatively, the storage medium is an electronic storage medium. Alternatively, the storage medium is a computer readable storage medium, but is not limited to this, and it can also be a storage medium readable by other devices. Alternatively, the storage medium can be a non-transitory storage medium, but is not limited to this, and it can also be a transitory storage medium.

[0519] The disclosure further provides a program product which, when executed by the communication device 7100, causes the communication device 7100 to perform any of the above methods. Alternatively, the program product is a computer program product.

[0520] The disclosure further provides a computer program which, when executed on a computer, causes the computer to perform any of the above methods.

Claims

1. A communication method characterized by comprising: The method comprises: The first device releases the first computing resource, the first computing resource being a computing resource allocated by the first device to the second device.

2. The method of claim 1, wherein, The method further comprises: The first device receives first information sent by the second device, the first information being used to request release of the first computing resource.

3. The method of claim 2, wherein, The first information comprises a first computing resource identifier associated with the first computing resource.

4. The method of claim 1, wherein, The method further comprises: The first device sends second information to the second device, the second information being used to indicate release of a computing resource.

5. The method of claim 4, wherein, The second information is sent based on an event, and the second information comprises a second computing resource identifier and / or an event identifier, the second computing resource identifier being used to identify the computing resource indicated by the first device to release.

6. The method of claim 5, wherein, The event comprises at least one of: The computing service time has ended; The computing resource is insufficient; The computing fee is used up; The computing service is switched.

7. The method according to claim 5 or 6, characterized in that, The second information is also used to indicate a third device providing a computing resource.

8. The method of claim 4, wherein, The method further comprises: The first device receives third information sent by the second device, the third information comprising a third computing resource identifier, the third computing resource identifier comprising one or more computing resource identifiers, each computing resource identifier corresponding to a priority of a computing resource, and the third computing resource identifier being used to identify the computing resource determined by the second device to release based on the second information.

9. The method of claim 8, wherein, The method further comprises: The first device releases the first computing resource based on the third information.

10. The method according to claim 8 or 9, characterized in that, The first computing resource is released according to the priority corresponding to each computing resource identifier, and the first computing resource is all or part of the computing resource allocated by the first device to the second device.

11. The method according to any one of claims 4 to 10, characterized in that, The method further comprises: The first device receives fourth information sent by the second device, the fourth information being used to request a third device to provide a computing resource for the second device.

12. The method according to any one of claims 8 to 10, characterized in that, The third information is used to indicate at least one of: Whether the second device renews the fee; Whether the second device continues to provide a computing resource through the first device.

13. The method of claim 1, wherein, The method further comprises: The first device sends fifth information to the second device, the fifth information being used to indicate that the first device has released the first computing resource.

14. The method of claim 13, wherein, The fifth information comprises a first computing resource identifier associated with the first computing resource, and the first computing resource is a computing resource shared between the first device and the second device; The fifth information is used by the second device to determine whether to release a second computing resource, the second computing resource being a computing resource shared between the first device and the second device, and the second computing resource being associated with the first computing resource identifier.

15. The method of claim 1 or 13, wherein, The method further comprises: The first device receives sixth information sent by the second device, the sixth information being used to indicate that the second device confirms that the first device has released the first computing resource.

16. A method of communication, comprising: The method comprises: The second device determines a first computing resource, the first computing resource being a computing resource allocated by a first device to the second device.

17. The method of claim 16, wherein, The method further includes: The second device sends first information to the first device, and the first information is used to request to release the first computing resource.

18. The method of claim 17, wherein, The first information includes a first computing resource identifier, and the first computing resource identifier is associated with the first computing resource.

19. The method of claim 16, wherein, The method further includes: The second device receives second information sent by the first device, and the second information is used to indicate to release the computing resource.

20. The method of claim 19, wherein, The second information is sent based on an event, and the second information includes a second computing resource identifier and / or an event identifier, and the second computing resource identifier is used to identify the computing resource indicated to be released by the first device.

21. The method of claim 20, wherein, The event includes at least one of: The computing service time has ended; The computing resource is insufficient; The computing fee is used up; The computing service is switched.

22. The method of claim 20 or 21, wherein, The second information is also used to indicate a third device providing the computing resource.

23. The method of claim 19, wherein, The method further includes: The second device sends third information to the first device, and the third information includes a third computing resource identifier, and the third computing resource identifier includes one or more computing resource identifiers, and each computing resource identifier corresponds to a priority of a computing resource, and the third computing resource identifier is used to identify the computing resource determined by the second device to be released based on the second information.

24. The method of claim 23, wherein, The first computing resource is released according to the priority corresponding to each computing resource identifier, and the first computing resource is all or part of the computing resource allocated to the second device by the first device.

25. The method of claim 23 or 24, wherein, The method further includes: The second device sends fourth information to the first device, and the fourth information is used to request the third device to provide the computing resource for the second device.

26. The method of claim 23 or 24, wherein, The third information is used to indicate at least one of: Whether the second device renews the fee; Whether the second device continues to provide the computing resource through the first device.

27. The method of claim 16, wherein, The second device determines the first computing resource, including: The second device receives fifth information sent by the first device, and the fifth information is used to indicate that the first device has released the first computing resource.

28. The method of claim 27, wherein, The fifth information includes a first computing resource identifier and / or an event identifier, the first computing resource identifier is associated with the first computing resource, and the first computing resource is a computing resource shared between the first device and the second device; The fifth information is used for the second device to determine whether to release a second computing resource, the second computing resource is a computing resource shared between the first device and the second device, and the second computing resource is associated with the first computing resource identifier.

29. The method of claim 16 or 28, wherein, The method further includes: The second device sends sixth information to the first device, and the sixth information is used to indicate that the second device has confirmed that the first device has released the first computing resource.

30. A first device, comprising: Including: A processing module is configured to release a first computing resource, and the first computing resource is a computing resource allocated to a second device by a first device.

31. A second device, comprising: Including: A processing module is configured to determine, by a second device, a first computing resource, and the first computing resource is a computing resource allocated to the second device by a first device.

32. A communications device, characterized by Including: One or more processors; The processor is configured to perform the method of any one of claims 1 to 15.

33. A communications device, characterized by Comprising: one or more processors; The processor is configured to perform the method of any one of claims 16 to 29.

34. A communication system, characterized by Comprising a first device and a second device, wherein the first device is configured to implement the method of any one of claims 1 to 15 and the second device is configured to implement the method of any one of claims 16 to 29.

35. A storage medium, the storage medium storing instructions, wherein, The instructions, when executed on the communication device, cause the communication device to perform the method of any one of claims 1 to 15 or the method of any one of claims 16 to 29.

36. A program product, characterized by Comprising: a computer program which, when executed by a communication device, causes the communication device to perform the method of any one of claims 1 to 15 or the method of any one of claims 16 to 29.

Images