Communication method, first device, second device, communication system, storage medium, and program product

Abstract

The present disclosure relates to a communication method, a first device, a second device, a communication system, a storage medium, and a program product. The communication method comprises: a first device sends first information used for requesting computing power, the first information comprising a computing power range and / or a computation amount of the computing power. The present disclosure achieves the sharing of computing power and improves the communication efficiency.

Description

Communication methods, first devices, second devices, communication systems, storage media, and software products Technical Field

[0001] This disclosure relates to the field of communication technology, and in particular to communication methods, first devices, second devices, communication systems, storage media, and program products. Background Technology

[0002] In recent years, artificial intelligence (AI) technology has developed rapidly, and various AI-based methods and services have permeated all aspects of life, including entertainment, communication, healthcare, transportation, and factory production.

[0003] Summary of the Invention

[0004] Future AI technologies include computing power services, and how to share computing power is a problem that is being studied.

[0005] This disclosure provides embodiments of a communication method, a first device, a second device, a communication system, a storage medium, and a program product.

[0006] According to a first aspect of the present disclosure, a communication method is proposed, the method comprising: a first device sending first information for requesting computing power, the first information including the computing power range and / or computing power quantity of the computing power.

[0007] According to a second aspect of the present disclosure, a communication method is provided, the method comprising: a second device receiving first information for requesting computing power, the first information including the computing power range and / or computational quantity of the computing power.

[0008] According to a third aspect of the present disclosure, a communication method is proposed, the method comprising: a first device sending first information for requesting computing power, the first information including the computing power range and / or computational load of the computing power; and a second device receiving the first information.

[0009] According to a fourth aspect of the present disclosure, a first device is provided, comprising: a transceiver module for transmitting first information for requesting computing power, the first information including the computing power range and / or computational quantity of the computing power.

[0010] According to a fifth aspect of the present disclosure, a second device is provided, comprising: a transceiver module for receiving first information for requesting computing power, the first information including the computing power range and / or computational quantity of the computing power.

[0011] According to a sixth aspect of the present disclosure, a first device is provided, comprising: one or more processors; wherein the processors are configured to perform the first aspect and any one of the communication methods in the first aspect.

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

[0013] According to an eighth 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 first aspect and any one of the communication method of the first aspect, and the second device is configured to implement the second aspect and any one of the communication method of the second aspect.

[0014] According to a ninth aspect of the embodiments of the present disclosure, a storage medium is provided, which stores instructions, when the instructions are executed on a communication device, the communication device executes the communication method of the first aspect and any one of the first aspect or the second aspect and any one of the second aspect.

[0015] The present disclosure sends first information to request computing power, and the computing power range and / or computing amount of the computing power are included in the first information, so as to facilitate the second device to determine whether to accept the request of the first device, or to determine how to provide the computing power, so as to realize the sharing of the computing power, and improve the communication efficiency. BRIEF DESCRIPTION OF DRAWINGS

[0016] 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.

[0017] FIG. 1a is a schematic diagram of a communication system architecture according to an embodiment of the present disclosure.

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

[0019] FIG. 1c is a schematic diagram of a communication system architecture according to an embodiment of the present disclosure.

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

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

[0022] FIG. 2c is a schematic diagram of a communication method interaction according to an embodiment of the present disclosure.

[0023] FIG. 2d is a schematic diagram of a communication method interaction according to an embodiment of the present disclosure.

[0024] FIG. 3a is a flowchart of a communication method according to an embodiment of the present disclosure.

[0025] FIG. 3b is a flow chart of a communication method, according to an embodiment of the present disclosure.

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

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

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

[0029] FIG. 6a is a structural diagram of a terminal, according to an embodiment of the present disclosure.

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

[0031] FIG. 7a is a structural diagram of a communication device, according to an example embodiment.

[0032] FIG. 7b is a chip structural diagram, according to an example embodiment. DETAILED DESCRIPTION

[0033] Embodiments of the present disclosure provide a communication method, a first device, a second device, a communication system, a storage medium and a program product.

[0034] In a first aspect, embodiments of the present disclosure provide a communication method, the method comprising: a first device sending first information for requesting a computing power, the first information comprising a computing power range and / or a computing amount of the computing power.

[0035] In the above embodiments, the first information is sent to request the computing power, and the computing power range and / or the computing amount of the computing power are included in the first information, so that the second device can determine whether to accept the request of the first device or determine how to provide the computing power, thereby realizing sharing of the computing power and improving communication efficiency.

[0036] In some embodiments in combination with the first aspect, in some embodiments, the first information further comprises a type of the computing power.

[0037] In the above embodiments, the type of the computing power can be included in the first information, so that the second device can determine whether to provide the computing power or how to provide the computing power according to the type of the computing power.

[0038] In some embodiments in combination with the first aspect, in some embodiments, different types of the computing power correspond to different time domain characteristics.

[0039] In the above embodiments, the computing power can be classified according to the time domain characteristics, i.e., different time domain characteristics correspond to different types of the computing power, so that the second device can determine whether to provide the computing power or how to provide the computing power according to the different time domain characteristics of the computing power.

[0040] In some embodiments of the first aspect, in some embodiments, the type includes at least one of: a periodic type; a semi-persistent type; an aperiodic type.

[0041] In the above embodiments, the computing power is classified according to the time domain characteristics, for example, can be divided into periodic, semi-persistent, aperiodic, so that the second device can determine whether to provide computing power or how to provide computing power according to the different time domain characteristics of the computing power.

[0042] In some embodiments of the first aspect, in some embodiments, the type includes a periodic type, and the first information further includes a periodic value.

[0043] In the above embodiments, if the requested computing power is of a periodic type, the first device can further indicate a periodic value, so that the second device can determine whether to accept the request of the first device or how to provide computing power.

[0044] In some embodiments of the first aspect, in some embodiments, the type includes a semi-persistent type, and the first information further includes a number of times of using the computing power requested by the first device and / or a time interval between each two times of using the computing power.

[0045] In the above embodiments, if the requested computing power is of a semi-persistent type, the first device can further indicate the number of times of using the computing power and / or the time interval between each two times of using the computing power.

[0046] In some embodiments of the first aspect, in some embodiments, the type includes a semi-persistent type, and the method further includes: the first device sending second information, the second information being used to request to activate the computing power of the semi-persistent type; or, the first device receiving third information, the third information being used to activate the computing power of the semi-persistent type.

[0047] In the above embodiments, if the requested computing power is of a semi-persistent type, the first device can further request to activate the computing power of the semi-persistent type, or the second device can actively activate the computing power of the semi-persistent type, so as to periodically use the computing power of the second device before deactivating the computing power.

[0048] In some embodiments of the first aspect, in some embodiments, different types of the computing power correspond to different quality of services (QoS).

[0049] In the above embodiments, the computing power can be classified according to the quality of service, so that the second device can determine whether to provide computing power or how to provide computing power according to the different quality of service of the computing power.

[0050] In some embodiments of the first aspect, in some embodiments, the QoS comprises at least one of: a service type; a service priority; a packet delay budget; a packet error rate; an average window; a maximum data burst amount; an allocation and retention priority; a packet data unit (PDU) set comprehensive processing information; a reflective QoS attribute; a guaranteed traffic bit rate; a maximum traffic bit rate; a maximum packet loss rate; a latency requirement.

[0051] In the above embodiments, the quality of service can comprise at least one of the above parameters, and the type of the computing power depends on at least one of the above parameters, so that the second device can determine whether to provide the computing power or how to provide the computing power according to the different quality of service of the computing power.

[0052] In some embodiments of the first aspect, in some embodiments, the different types of the computing power comprise at least one of: a central processing unit (CPU) type; a data processing unit (DPU) type; a field programmable gate array (FPGA) type; a graphics processing unit (GPU) type; a neural processing unit (NPU) type; a tensor processing unit (TPU) type.

[0053] In some embodiments of the first aspect, in some embodiments, the method further comprises: receiving, by the first device, fourth information; the fourth information is used to instruct the first device to send an AI model; or the fourth information comprises response information of the first information.

[0054] In the above embodiments, if the second device does not deploy the AI model required by the first device, the first device can be instructed to send the AI model, and the second device can provide the computing power for the first device based on the AI model. Or the response information can be included to inform the first device whether the second device has accepted its request, etc.

[0055] In some embodiments of the first aspect, in some embodiments, the fourth information is used to instruct the first device to send the AI model, and the method further comprises: sending, by the first device, the AI model.

[0056] In the above embodiments, the first device can send the AI model to the second device after receiving the fourth information, so that the second device can provide the computing power for the first device based on the AI model.

[0057] In some embodiments of the first aspect, in some embodiments, the fourth information comprises response information of the first information, and the method further comprises: determining, by the first device based on the fourth information, that the second device has reserved periodic computing power; or determining, by the first device based on the fourth information, that the second device has reserved one or more times of computing power within a preset time; or determining, by the first device based on the fourth information, that the second device has reserved one time of computing power within a preset time.

[0058] In the above embodiment, the fourth information can include response information, and the first device can determine, based on the response information, that the second device has reserved periodic computing power, or has reserved one or more times of computing power within a preset time, or has reserved one time of computing power within a preset time, that is, the first device can be informed of the specific situation of providing computing power through the fourth information.

[0059] In combination with some embodiments of the first aspect, in some embodiments, the method further includes: the first device sending or receiving fifth information, the fifth information including allocation information of first resources, the first resources being used for transmitting data corresponding to the computing power.

[0060] In the above embodiment, the first device can send or receive the fifth information, and the fifth information is used for transmitting data corresponding to the computing power, so as to accurately transmit the data corresponding to the computing power at a suitable time domain position.

[0061] In combination with some embodiments of the first aspect, in some embodiments, the fourth information includes the fifth information.

[0062] In the above embodiment, the fifth information can be included in the fourth information, that is, the transmission resource can be sent or received at the same time as the first information is responded to, so as to save the consumption of signaling.

[0063] In combination with some embodiments of the first aspect, in some embodiments, at least one of the second information, the third information, the fourth information and the fifth information includes a first identifier and / or a second identifier; the second information is sent by the first device and is used for requesting to activate the semi-persistent type of computing power; the third information is received by the first device and is used for activating the semi-persistent type of computing power; the fourth information is received by the first device and is used for indicating that the first device sends an AI model, or the fourth information is received by the first device and includes response information of the first information; the fifth information is received by the first device and includes allocation information of first resources, the first resources being used for transmitting data corresponding to the computing power; the first identifier is used for identifying an AI model, and the second identifier is used for identifying a computing power request corresponding to the first information.

[0064] In the above embodiment, the first device can also send or receive the first identifier and / or the second identifier through at least one of the above-mentioned second information, the third information, the fourth information and the fifth information. For example, if the first device sends the first identifier and / or the second identifier, the first device can identify the current request in the second device, and / or can inform the second device of the current request. If the first device receives the first identifier and / or the second identifier, the first device can determine the specific situation of the computing power provided by the second device. For example, which request the computing power corresponds to, or which AI model the computing power corresponds to.

[0065] In some embodiments of the first aspect, in some embodiments, the fifth information is carried by at least one of: radio resource control information (RRC); a medium access control control element (MAC CE); control information.

[0066] In the above embodiments, the transmission resource can be configured through different signaling, improving communication efficiency.

[0067] In some embodiments of the first aspect, in some embodiments, the allocation information of the first resource includes at least one of: a time domain resource; a frequency domain resource; an offset value of the time domain resource relative to a reference system frame number; a period value of the time domain resource; a hybrid automatic repeat request (HARQ) process number; a modulation and coding scheme; a power control value; an antenna port; demodulation reference signal (DMRS) information; transmission configuration indication (TCI) state.

[0068] In the above embodiments, the allocation information of the first resource can include at least one of the above, to flexibly configure the transmission resource.

[0069] In some embodiments of the first aspect, in some embodiments, the allocation information of the first resource includes a first part of parameters and a second part of parameters, the first part of parameters is carried by the RRC, and the second part of parameters is carried by the MAC CE or the control information.

[0070] In the above embodiments, part of the transmission resource can be configured by the RRC, and part of the transmission resource can be activated or indicated by the MAC CE or the control information, thereby improving flexibility.

[0071] In some embodiments of the first aspect, in some embodiments, the type of the computing power is a periodic type or a semi-persistent type.

[0072] In the above embodiments, the transmission resource can be configured in the above manner, which can be applicable to the case where the type of the computing power is a periodic type or a semi-persistent type, to improve communication efficiency.

[0073] In some embodiments of the first aspect, in some embodiments, the first resource includes at least one of the following resources: a periodic physical uplink control channel (PUCCH); a configured grant physical uplink shared channel (CG PUSCH); a semi-persistent PUSCH; a physical downlink control channel (PDCCH); a physical downlink shared channel (PDSCH); a physical sidelink shared channel (PSSCH); a physical sidelink control channel (PSCCH).

[0074] In the above embodiments, the first resource can include at least one of the above, to flexibly configure the transmission resource.

[0075] In some embodiments of the first aspect, in some embodiments, the first information is carried by at least one of: a MAC CE; uplink control information; downlink control information; sidelink control information; a physical random access channel (PRACH); a PUCCH; a PUSCH; a PDCCH; a PDSCH; a PSCCH; a PSSCH.

[0076] In the above embodiments, the first information can be carried by at least one of the above information, so as to flexibly cope with different situations and provide communication efficiency.

[0077] In a second aspect, a communication method is provided. The method comprises: receiving, by a second device, first information for requesting a computing power, the first information comprising a computing power range and / or a computing amount of the computing power.

[0078] In some embodiments of the second aspect, in some embodiments, the first information further comprises a type of the computing power.

[0079] In some embodiments of the second aspect, in some embodiments, different types of the computing power correspond to different time domain characteristics.

[0080] In some embodiments of the second aspect, in some embodiments, the type comprises at least one of: a periodic type; a semi-persistent type; an aperiodic type.

[0081] In some embodiments of the second aspect, in some embodiments, the type comprises a periodic type, and the first information further comprises a periodic value.

[0082] In some embodiments of the second aspect, in some embodiments, the type comprises a semi-persistent type, and the first information further comprises a number of times of using the computing power and / or a time interval between each two times of using the computing power.

[0083] In some embodiments of the second aspect, in some embodiments, the type comprises a semi-persistent type, and the method further comprises: receiving, by the second device, second information for requesting to activate the computing power of the semi-persistent type; or, transmitting, by the second device, third information for activating the computing power of the semi-persistent type.

[0084] In some embodiments of the second aspect, in some embodiments, different types of the computing power correspond to different quality of services (QoS).

[0085] In some embodiments of the second aspect, in some embodiments, the QoS comprises at least one of: a service type; a service priority; a packet delay budget; a packet error rate; an average window; a maximum data burst amount; an allocation and retention priority; a packet data unit (PDU) set comprehensive processing information; a reflective QoS attribute; a guaranteed traffic bit rate; a maximum traffic bit rate; a maximum packet loss rate; a latency requirement.

[0086] In some embodiments of the second aspect, in some embodiments, the different types of computing power comprise at least one of: a central processing unit (CPU) type; a data processing unit (DPU) type; a field programmable gate array (FPGA) type; a graphics processing unit (GPU) type; a neural processing unit (NPU) type; a tensor processing unit (TPU) type.

[0087] In some embodiments of the second aspect, in some embodiments, the method further comprises: the second device sending fourth information; the fourth information being used to instruct the first device to send an AI model; or, the fourth information comprising response information of the first information.

[0088] In some embodiments of the second aspect, in some embodiments, the fourth information is used to instruct the first device to send the AI model, and the method further comprises: the second device receiving the AI model.

[0089] In some embodiments of the second aspect, in some embodiments, the method further comprises: the second device receiving or sending fifth information, the fifth information comprising allocation information of a first resource, the first resource being used to transmit data corresponding to the computing power.

[0090] In some embodiments of the second aspect, in some embodiments, the fourth information comprises the fifth information.

[0091] In some embodiments of the second aspect, in some embodiments, at least one of the second information, the third information, the fourth information, and the fifth information comprises a first identifier and / or a second identifier; wherein the second information is received by the second device and is used to request to activate the semi-persistent type of computing power; the third information is sent by the second device and is used to activate the semi-persistent type of computing power; the fourth information is sent by the second device and is used to instruct the first device to send an AI model, or the fourth information is sent by the second device and comprises response information of the first information; the fifth information is sent by the second device and comprises allocation information of a first resource, the first resource being used to transmit data corresponding to the computing power; the first identifier is used to identify an AI model, and the second identifier is used to identify a computing power request corresponding to the first information.

[0092] In some embodiments of the second aspect, in some embodiments, the fifth information is carried by at least one of: radio resource control information (RRC); a medium access control control element (MAC CE); control information.

[0093] In some embodiments of the second aspect, in some embodiments, the allocation information of the first resource comprises at least one of: a time domain resource; a frequency domain resource; an offset value of the time domain resource relative to a reference system frame number; a periodicity value of the time domain resource; a hybrid automatic repeat request (HARQ) process number; a modulation and coding scheme; a power control value; an antenna port; demodulation reference signal (DMRS) information.

[0094] In some embodiments of the second aspect, in some embodiments, the allocation information of the first resource comprises a first part of parameters and a second part of parameters, the first part of parameters is carried by RRC, and the second part of parameters is carried by a MAC CE or control information.

[0095] In some embodiments of the second aspect, in some embodiments, the type of the computing power is a periodic type or a semi-persistent type.

[0096] In some embodiments of the second aspect, in some embodiments, the first resource comprises at least one of: a periodic physical uplink control channel (PUCCH); a configured grant physical uplink shared channel (CG PUSCH); a semi-persistent PUSCH; a physical downlink control channel (PDCCH); a physical downlink shared channel (PDSCH); a physical sidelink shared channel (PSSCH); a physical sidelink control channel (PSCCH).

[0097] In some embodiments of the second aspect, in some embodiments, the first information is carried by at least one of: a MAC CE; uplink control information; downlink control information; sidelink control information; a physical random access channel (PRACH); a PUCCH; a PUSCH; a PDCCH; a PDSCH; a PSCCH; a PSSCH.

[0098] In a third aspect, a communication method is provided, the method comprising: a first device sending first information for requesting computing power, the first information comprising a computing power range and / or a computing amount of the computing power; and a second device receiving the first information.

[0099] In a fourth aspect, a first device is provided, comprising: a transceiver configured to send first information for requesting computing power, the first information comprising a computing power range and / or a computing amount of the computing power.

[0100] In some embodiments of the fourth aspect, in some embodiments, the first information further comprises a type of the computing power.

[0101] In some embodiments combined with the fourth aspect, in some embodiments, the different types of the computing power correspond to different time domain characteristics.

[0102] In some embodiments combined with the fourth aspect, in some embodiments, the type includes at least one of the following: a periodic type; a semi-persistent type; an aperiodic type.

[0103] In some embodiments combined with the fourth aspect, in some embodiments, the type includes the periodic type, and the first information further includes a periodic value.

[0104] In some embodiments combined with the fourth aspect, in some embodiments, the type includes the semi-persistent type, and the first information further includes a number of times of the computing power requested by the first device and / or a time interval between each two times of using the computing power.

[0105] In some embodiments combined with the fourth aspect, in some embodiments, the type includes the semi-persistent type, and the transceiver is further configured to: the first device sends second information, the second information being used to request to activate the semi-persistent type of the computing power; or, the first device receives third information, the third information being used to activate the semi-persistent type of the computing power.

[0106] In some embodiments combined with the fourth aspect, in some embodiments, the different types of the computing power correspond to different quality of service (QoS).

[0107] In some embodiments combined with the fourth aspect, in some embodiments, the QoS includes at least one of the following parameters: a service type; a service priority; a packet delay budget; a packet error rate; an average window; a maximum data burst quantity; an allocation and retention priority; a packet data unit (PDU) set comprehensive processing information; a reflective QoS attribute; a guaranteed traffic bit rate; a maximum traffic bit rate; a maximum packet loss rate; a latency requirement.

[0108] In some embodiments combined with the fourth aspect, in some embodiments, the different types of the computing power include at least one of the following: a central processing unit (CPU) type; a data processing unit (DPU) type; a field programmable gate array (FPGA) type; a graphics processing unit (GPU) type; a neural processing unit (NPU) type; a tensor processing unit (TPU) type.

[0109] In some embodiments combined with the fourth aspect, in some embodiments, the transceiver is further configured to: the first device receives fourth information; the fourth information is used to indicate that the first device sends an AI model; or, the fourth information includes response information of the first information.

[0110] In some embodiments combined with the fourth aspect, in some embodiments, the fourth information is used to instruct the first device to send the AI model, and the method further includes: the first device sending the AI model.

[0111] In some embodiments combined with the fourth aspect, in some embodiments, the fourth information includes response information of the first information, and the method further includes: the first device determining, based on the fourth information, that the second device has reserved periodic computing power; or, the first device determining, based on the fourth information, that the second device has reserved one or more times of computing power within a preset time; or, the first device determining, based on the fourth information, that the second device has reserved one time of computing power within a preset time.

[0112] In some embodiments combined with the fourth aspect, in some embodiments, the transceiving module is further configured to: the first device sending or receiving fifth information, the fifth information including allocation information of a first resource, the first resource being used to transmit data corresponding to the computing power.

[0113] In some embodiments combined with the fourth aspect, in some embodiments, the fourth information includes the fifth information.

[0114] In some embodiments combined with the fourth aspect, in some embodiments, at least one of the second information, the third information, the fourth information, and the fifth information includes a first identifier and / or a second identifier; the second information is sent by the first device and is used to request to activate the semi-persistent type of computing power; the third information is received by the first device and is used to activate the semi-persistent type of computing power; the fourth information is received by the first device and is used to instruct the first device to send an AI model, or the fourth information is received by the first device and includes response information of the first information; the fifth information is received by the first device and includes allocation information of a first resource, the first resource being used to transmit data corresponding to the computing power; the first identifier is used to identify an AI model, and the second identifier is used to identify a computing power request corresponding to the first information.

[0115] In some embodiments combined with the fourth aspect, in some embodiments, the fifth information is carried by at least one of the following: radio resource control information (RRC); a medium access control control element (MAC CE); and control information.

[0116] In some embodiments, the allocation information of the first resource includes at least one of the following: a time domain resource; a frequency domain resource; an offset value of the time domain resource relative to a reference system frame number; a period value of the time domain resource; a hybrid automatic repeat request (HARQ) process number; a modulation and coding scheme; a power control value; an antenna port; demodulation reference signal (DMRS) information; and transmission configuration indication (TCI) state.

[0117] In some embodiments, the allocation information of the first resource comprises a first part of parameters and a second part of parameters, the first part of parameters is carried by the RRC, and the second part of parameters is carried by the MAC CE or the control information.

[0118] In some embodiments, the type of the computing resource is a periodic type or a semi-persistent type.

[0119] In some embodiments, the first resource comprises at least one of the following resources: a periodic physical uplink control channel (PUCCH), a configured grant physical uplink shared channel (CG-PUSCH), a semi-persistent PUSCH, a physical downlink control channel (PDCCH), a physical downlink shared channel (PDSCH), a physical sidelink shared channel (PSSCH), and a physical sidelink control channel (PSCCH).

[0120] In some embodiments, the first information is carried by at least one of the following: a MAC CE, uplink control information, downlink control information, sidelink control information, a physical random access channel (PRACH), a PUCCH, a PUSCH, a PDCCH, a PDSCH, a PSCCH, and a PSSCH.

[0121] In a fifth aspect, a second device is provided, comprising: a transceiver configured to receive first information for requesting a computing resource, the first information comprising a computing resource range and / or a computing amount of the computing resource.

[0122] In some embodiments in combination with the fifth aspect, the first information further comprises a type of the computing resource.

[0123] In some embodiments in combination with the fifth aspect, different types of the computing resource correspond to different time domain characteristics.

[0124] In some embodiments in combination with the fifth aspect, the type comprises at least one of the following: a periodic type, a semi-persistent type, and an aperiodic type.

[0125] In some embodiments in combination with the fifth aspect, the type comprises a periodic type, and the first information further comprises a periodic value.

[0126] In some embodiments in combination with the fifth aspect, the type comprises a semi-persistent type, and the first information further comprises a number of times of using the computing resource and / or a time interval between each two times of using the computing resource.

[0127] In some embodiments of the fifth aspect, in some embodiments, the type includes a semi-persistent type, and the transceiving module is further configured to: receive, by the second device, second information, the second information being used to request to activate the computing power of the semi-persistent type; or, send, by the second device, third information, the third information being used to activate the computing power of the semi-persistent type.

[0128] In some embodiments of the fifth aspect, in some embodiments, the different types of the computing power correspond to different quality of service (QoS).

[0129] In some embodiments of the fifth aspect, in some embodiments, the QoS includes at least one of the following parameters: a service type; a service priority; a packet delay budget; a packet error rate; an average window; a maximum data burst quantity; an allocation and retention priority; a packet data unit (PDU) set comprehensive processing information; a reflective QoS attribute; a guaranteed traffic bit rate; a maximum traffic bit rate; a maximum packet loss rate; and a latency requirement.

[0130] In some embodiments of the fifth aspect, in some embodiments, the different types of the computing power include at least one of the following: a central processing unit (CPU) type; a data processing unit (DPU) type; a field programmable gate array (FPGA) type; a graphics processing unit (GPU) type; a neural processing unit (NPU) type; and a tensor processing unit (TPU) type.

[0131] In some embodiments of the fifth aspect, in some embodiments, the transceiving module is further configured to: send, by the second device, fourth information; the fourth information being used to instruct the first device to send an AI model; or, the fourth information including response information of the first information.

[0132] In some embodiments of the fifth aspect, in some embodiments, the fourth information is used to instruct the first device to send the AI model, and the method further includes: receiving, by the second device, the AI model.

[0133] In some embodiments of the fifth aspect, in some embodiments, the transceiving module is further configured to: receive or send, by the second device, fifth information, the fifth information including allocation information of a first resource, the first resource being used to transmit data corresponding to the computing power.

[0134] In some embodiments of the fifth aspect, in some embodiments, the fourth information includes the fifth information.

[0135] In some embodiments of the fifth aspect, in some embodiments, at least one of the second information, the third information, the fourth information, and the fifth information comprises the first identifier and / or the second identifier; wherein the second information is received by the second device and is used to request to activate the semi-persistent type of computing power; the third information is sent by the second device and is used to activate the semi-persistent type of computing power; the fourth information is sent by the second device and is used to indicate that the first device sends an AI model, or the fourth information is sent by the second device and comprises response information of the first information; the fifth information is sent by the second device and comprises allocation information of a first resource, the first resource being used to transmit data corresponding to the computing power; the first identifier is used to identify an AI model, and the second identifier is used to identify a computing power request corresponding to the first information.

[0136] In some embodiments of the fifth aspect, in some embodiments, the fifth information is carried by at least one of the following: radio resource control information (RRC); a medium access control control element (MAC CE); control information.

[0137] In some embodiments of the fifth aspect, in some embodiments, the allocation information of the first resource comprises at least one of the following: a time domain resource; a frequency domain resource; an offset value of the time domain resource relative to a reference system frame number; a period value of the time domain resource; a hybrid automatic repeat request (HARQ) process number; a modulation and coding scheme; a power control value; an antenna port; demodulation reference signal (DMRS) information.

[0138] In some embodiments of the fifth aspect, in some embodiments, the allocation information of the first resource comprises a first part of parameters and a second part of parameters, the first part of parameters being carried by RRC, and the second part of parameters being carried by a MAC CE or control information.

[0139] In some embodiments of the fifth aspect, in some embodiments, the type of the computing power is a periodic type or a semi-persistent type.

[0140] In some embodiments of the fifth aspect, in some embodiments, the first resource comprises at least one of the following resources: a periodic physical uplink control channel (PUCCH); a configured grant physical uplink shared channel (CG PUSCH); a semi-persistent PUSCH; a physical downlink control channel (PDCCH); a physical downlink shared channel (PDSCH); a physical sidelink shared channel (PSSCH); a physical sidelink control channel (PSCCH).

[0141] In some embodiments combining with the fifth aspect, in some embodiments, the first information is carried by at least one of the following: a MAC CE; uplink control information; downlink control information; sidelink control information; a physical random access channel (PRACH); a PUCCH; a PUSCH; a PDCCH; a PDSCH; a PSCCH; and a PSSCH.

[0142] In a sixth aspect, a first device is provided, comprising: one or more processors; wherein the processor is configured to perform the first aspect and any one of the communication methods in the first aspect.

[0143] In a seventh aspect, a second device is provided, comprising: one or more processors; wherein the processor is configured to perform the second aspect and any one of the communication methods in the second aspect.

[0144] In an eighth aspect, a communication system is provided, comprising the first device and the second device, wherein the first device is configured to implement the first aspect and any one of the communication methods in the first aspect, and the second device is configured to implement the second aspect and any one of the communication methods in the second aspect.

[0145] In a ninth aspect, a storage medium is provided, which stores instructions, when the instructions are executed on a communication device, causing the communication device to perform the communication method in the first aspect and any one of the optional implementation manners of the first aspect, or the communication method in the second aspect and any one of the optional implementation manners of the second aspect.

[0146] In a tenth aspect, a program product is provided, when the program product is executed by a communication device, causing the communication device to perform the method described in the first aspect or the optional implementation manners of the second aspect.

[0147] In an eleventh aspect, a computer program is provided, when it is executed on a computer, causing the computer to perform the method described in the first aspect or the optional implementation manners of the second aspect.

[0148] In a twelfth aspect, a chip or chip system is provided. The chip or chip system comprises processing circuitry configured to perform the method described in the first aspect or the optional implementation manners of the second aspect.

[0149] It can be understood that the terminal, the access network device, the first network element, the second network element, the core network device, the communication system, the storage medium, the program product, the computer program, the chip or the chip system are all used to perform the method proposed in the embodiments of the present disclosure. Therefore, the beneficial effects that can be achieved are referred to the beneficial effects in the corresponding method, which will not be described here.

[0150] The embodiments of the present disclosure provide a communication method, a first device, a second device, a communication system, a storage medium and a program product. In some embodiments, the communication method, the information processing method, and the like can be replaced with each other, the first device, the second device, and the like can be replaced with each other, and the information processing system and the communication system can be replaced with each other.

[0151] The embodiments of the present disclosure are not exhaustive, but are only schematic of 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, some or all steps of different embodiments can be combined arbitrarily, an embodiment can be combined with optional implementation manners of other embodiments.

[0152] In the embodiments of the present disclosure, the terms and / or descriptions between the embodiments are consistent and can be referred to each other if there is no special description and logical conflict, and the technical features in different embodiments can be combined to form new embodiments according to their inherent logical relationship.

[0153] The terms used in the embodiments of the present disclosure are only for the purpose of describing specific embodiments, and not as a limitation on the present disclosure.

[0154] 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" in English, the noun after the article can be understood as singular expression, or as plural expression.

[0155] In the embodiments of the present disclosure, "a plurality of" means two or more.

[0156] 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.

[0157] In some embodiments, the description of "at least one of A, B", "A and / or B", "in a case A, in another case B", "in response to a case A, in response to a case B", and the like, can include the following technical solutions according to the case: in some embodiments, A (A is executed regardless of B); in some embodiments, B (B is executed regardless of A); in some embodiments, A and B are selectively executed (A and B are selected from A and B); in some embodiments, A and B (A and B are executed). When there are more branches such as A, B, C, and the like, the above is similar.

[0158] In some embodiments, the description of "A or B" and the like can include the following technical solutions according to the case: in some embodiments, A (A is executed regardless of B); in some embodiments, B (B is executed regardless of A); in some embodiments, A and B are selectively executed (A and B are selected from A and B). When there are more branches such as A, B, C, and the like, the above is similar.

[0159] The prefix words "first", "second", and the like in the embodiments of the present disclosure are only used to distinguish different description objects, and do not constitute a limitation on the position, order, priority, quantity, or content of the description objects. The description of the description objects should refer to the description in the context of the claims or embodiments, and should not constitute an additional limitation because of the use of the prefix words. For example, the description object is "field", and the ordinal words before "field" 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 thereby are in the same message or not, nor limit the order of "first field" and "second field". For another example, the description object is "level", and the ordinal words before "level" in "first level" and "second level" do not limit the priority between "levels". For another example, the quantity of the description object is not limited by the ordinal words, and can be one or more. For example, "first device", wherein the quantity of "device" can be one or more. In addition, the objects modified by different prefix words can be the same or different, for example, the description object is "device", and "first device" and "second device" can be the same device or different devices, and the types thereof can be the same or different; for another example, the description object is "information", and "first information" and "second information" can be the same information or different information, and the content thereof can be the same or different.

[0160] In some embodiments, "including A", "containing A", "for indicating A", "carrying A" can be interpreted as directly carrying A, or indirectly indicating A.

[0161] In some embodiments, the terms "time / frequency", "time / frequency domain", and the like refer to the time domain and / or the frequency domain.

[0162] In some embodiments, the terms “in response to,” “in response to determining,” “in the event that,” “when,” “if,” “upon,” and the like can be replaced with each other.

[0163] In some embodiments, the terms “greater than,” “greater than or equal to,” “not less than,” “more than,” “more than or equal to,” “not less than,” “higher than,” “higher than or equal to,” “not lower than,” “above,” and the like can be replaced with each other, and the terms “less than,” “less than or equal to,” “not greater than,” “less than,” “less than or equal to,” “not more than,” “lower than,” “lower than or equal to,” “not higher than,” “below,” and the like can be replaced with each other.

[0164] 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 described 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.

[0165] 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.

[0166] 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.

[0167] 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.

[0168] 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.

[0169] 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.

[0170] In some embodiments, the data, information, etc. can be obtained in compliance with the laws and regulations of the country where the location is located.

[0171] In some embodiments, the data, information, etc. can be obtained after obtaining the consent of the user.

[0172] 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 element, any row, or any column combination can also be implemented as an independent embodiment.

[0173] FIG. 1a is a schematic diagram of an architecture of a communication system according to an embodiment of the present disclosure.

[0174] As shown in FIG. 1a, the communication system 100 includes a first device 101 and a second device 102.

[0175] In some embodiments, the first device 101 may, for example, be a device requesting computing power, and the second device 102 may, for example, be a device requested to provide computing power. For example, the first device can be a terminal, and the second device can be a network device, i.e., the terminal can request the network device to provide computing power. For another example, the first device can be a network device, and the second device can be a terminal, i.e., the network device can request the terminal to provide computing power. For another example, the first device and the second device can both be terminals, i.e., the terminal can request the terminal to provide computing power. For example, a low-capability terminal requests computing power from a normal terminal. Or, a terminal without an AI model deployed requests computing power from a terminal with an AI model deployed, but not limited to this.

[0176] The computing power requested in the embodiments can be understood as requesting to share computing power, or requesting to provide computing power. For example, the first device requests the second device to provide computing power, which means that the first device requests the second device to share its computing power with the first device, or the first device requests the second device to provide computing power to the first device. For example, the first device requests the second device to process data required to be processed by the first device based on an AI model, and the present disclosure does not enumerate all examples, but is not limited to the enumerated cases.

[0177] In some embodiments, computing power can refer to the ability of a node with computing power in a network to achieve a specific result output through processing of data. For example, it can include but is not limited to computing, reading and writing (memory or storage) capabilities. Computing power can be distributed on various forms of devices such as network edge, cloud data center, networked terminal, forwarding node, etc., but not limited to this.

[0178] FIG. 1b is a schematic diagram of an architecture of a communication system according to an embodiment of the present disclosure.

[0179] The embodiments of the present disclosure exemplarily show a communication system 200, as shown in FIG. 1b, which includes a terminal 201 and a network device 202.

[0180] FIG. 1c is a schematic diagram of an architecture of a communication system according to an embodiment of the present disclosure.

[0181] An embodiment of the present disclosure exemplarily shows a communication system 300, as shown in FIG. 1c, which includes a terminal 301 and a terminal 302.

[0182] In some embodiments, the terminal 201 (or the terminal 301, or the terminal 302) includes at least one of a mobile phone, a wearable device, an Internet of Things device, a communication-capable automobile, a smart automobile, a tablet computer (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.

[0183] In some embodiments, the network device 202 can include at least one of an access network device and a core network device.

[0184] 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.

[0185] 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.

[0186] 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.

[0187] 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).

[0188] 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.

[0189] 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.

[0190] 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), 6th generation mobile communication system (6G), 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 thereon, and the like. In addition, a plurality of systems can be combined (for example, combination of LTE or LTE-A and 5G, and the like).

[0191] FIG. 2a is an interaction diagram of a communication method according to an embodiment of the present disclosure. As shown in FIG. 2a, the embodiment of the present disclosure relates to a communication method for a communication system 100, the above-mentioned method comprising:

[0192] In step S2101, the first device 101 sends first information to the second device 102.

[0193] In some embodiments, the second device 102 receives the first information sent by the first device 101. For example, the first device 101 can be a terminal, and the second device 102 can be a network device. That is, the terminal can send the first information to the network device. For another example, the first device 101 can be a network device, and the second device 102 can be a terminal. That is, the network device can send the first information to the terminal. For another example, the first device 101 and the second device 102 can both be terminals, that is, the terminal can send the first information to the terminal. For example, a low-capability terminal sends the first information to a normal terminal. For another example, a terminal without deploying an AI model sends the first information to a terminal deploying an AI model. However, the above examples are only exemplary, and the present disclosure is not limited thereto.

[0194] In some embodiments, the names of information and the like 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”, “code point”, “bit”, “data”, “program”, “chip”, and the like can be replaced with each other.

[0195] 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, acquiring from protocols, acquiring from higher layers, obtaining by self-processing, autonomously implementing, and the like.

[0196] In some embodiments, the terms of “send”, “transmit”, “report”, “issue”, “transmit”, “bidirectional transmission”, “send and / or receive” can be replaced with each other.

[0197] In some embodiments, the first information is used to request computing capability. For example, different computing capabilities can correspond to different computing tasks.

[0198] In some embodiments, the computing power can refer to the ability of a node with computing power in the network to achieve a specific result output through processing of data. For example, it can include but is not limited to computing, read-write (memory or storage) capability. The computing power can be distributed on various forms of devices such as network edge, cloud data center, networked terminal, forwarding node, etc., but is not limited thereto.

[0199] In some embodiments, the first information can include a computing power range and / or a computing amount of the computing power.

[0200] In some embodiments, the disclosure takes the computing power range as an example, which can be represented in at least one of the following ways: based on a use corresponding to the computing power in a plurality of preconfigured uses, and a computing power range in a plurality of computing power ranges corresponding to the use; or, based on a computing power range in a plurality of preconfigured computing power ranges; or, based on model information of an AI model.

[0201] In some embodiments, the terms "preconfigured", "certain", "preseted", "preset", "set", "indicated", "certain", "arbitrary", "first" and the like can be replaced with 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, configuring, or indicating, or A as a certain A, an arbitrary A, or a first A, but is not limited thereto.

[0202] Optionally, the computing power range can be represented based on a use corresponding to the computing power requested by the first device in a plurality of preconfigured uses, and a computing power range in a plurality of computing power ranges corresponding to the use. For example, the use of the requested computing power can be indicated first. The use can include model training, model derivation, data processing, image processing, etc., but is not limited thereto. Different uses correspond to different computing power ranges and different quantization gradients. Different uses can also correspond to different computing power types, such as GPU type for some uses, DPU type for some uses, TPU type for some uses, etc., which are not listed one by one.

[0203] Exemplarily, for model training, the quantized gradient can be 100M, and the computing power range can include 0-100M, 100M-200M, 200M-300M, and greater than 300M. The first device can first indicate that the use of the computing power corresponds to model training, and then use a first number of bits to represent the computing power range in the plurality of computing power ranges. For example, the first number can be 2, the bits corresponding to 0-100M can be 00, when 00 is indicated, it means that the computing power range is 0-100M, and the first device requests computing power of 0-100M. Correspondingly, the bits corresponding to 100M-200M can be 01, the bits corresponding to 200M-300M can be 10, and the bits corresponding to greater than 300M can be 11. It can be understood that the values in the embodiment are exemplary and are not limited thereto.

[0204] Exemplarily, for model derivation, the quantized gradient can be 10M, and the computing power range can include 0-10M, 100M-20M, 20M-30M, and greater than 30M. For example, the first number can be 2, the bits corresponding to 0-10M can be 00, when 00 is indicated, it means that the computing power range is 0-10M, and the first device requests computing power of 0-10M. Correspondingly, the bits corresponding to 10M-20M can be 01, the bits corresponding to 20M-30M can be 10, and the bits corresponding to greater than 30M can be 11. It can be understood that the values in the embodiment are exemplary and are not limited thereto.

[0205] Of course, the present disclosure is only exemplified by model training and model derivation, and is not limited thereto.

[0206] Optionally, the computing power range can be represented based on a plurality of preconfigured computing power ranges. For example, the use of the computing power can not be indicated, and the computing power range can be directly indicated. For example, the computing power range can be represented using a second number of bits. The second number is greater than or equal to the first number. It can be understood that when the use is not distinguished, in order to represent the same range size of computing power, more bits are needed, or the quantized gradient is larger.

[0207] Optionally, the computing power range can be represented based on model information of the AI model. For example, different models need different sizes of computing power when used. The computing power range can be predicted according to the model information of the AI model.

[0208] It can be understood that the computing power range in the above embodiment can also be a calculation amount, or can be a computing power value, etc.

[0209] In some embodiments, the model information of the AI model comprises at least one of: a structure of the AI model; a number of layers of the AI model; a number of hidden nodes of each layer of the AI model; a number of parameters of each layer of the AI model; a form of input data of the AI model; a form of output data of the AI model; a size of the AI model; a data volume corresponding to training of the AI model; a data volume corresponding to inference of the AI model; a data volume corresponding to output of the AI model.

[0210] Optionally, the model information can comprise a structure of the AI model. For example, the structure of the AI model comprises a structure of linear regression, a structure of recurrent neural network, a structure of convolutional neural network, etc., but is not limited thereto. Different structures correspond to different ranges of computing power and / or different amounts of computation. For example, for the structure of linear regression, there is no hidden layer between the input layer and the output layer, the structure is relatively simple, and the computing power required for using the linear regression model is also small. For example, for the structure of recurrent neural network, there is a recurrent layer, the structure is relatively complex, and the computing power required for using the recurrent neural network model is also relatively large. However, it can be understood that the structure of the model is only one of the characteristics representing the range of computing power and / or the amount of computation, and the computing power is not only determined by the model structure. Therefore, the size relationship in the above examples is only relative and is not limited.

[0211] Optionally, the model information can comprise a number of layers of the AI model. The layers of the AI model can comprise an input layer, an output layer, a hidden layer, a convolutional layer, a recurrent layer, a fully connected layer, etc. The number of layers of the AI model represents the number of layers of the AI model. For example, the more the number of layers of the AI model, the greater the range of computing power and / or the amount of computation represented.

[0212] Optionally, the model information can comprise a number of hidden nodes of each layer of the AI model. For example, the more the number of hidden nodes of each layer of the AI model, the greater the range of computing power and / or the amount of computation represented.

[0213] Optionally, the model information can comprise a form of input / output data of the AI model. For example, the more complex the form of input / output data, the greater the range of computing power and / or the amount of computation represented.

[0214] Optionally, the model information can comprise a data volume of input / output of the AI model. For example, the greater the data volume of input / output, the greater the range of computing power and / or the amount of computation represented.

[0215] Optionally, the model information can comprise a size of the AI model. The size of the AI model can refer to a number of parameters of the AI model, a storage space occupied by the AI model, etc. For example, the larger the AI model, the greater the range of computing power and / or the amount of computation represented.

[0216] Optionally, the model information can include a data volume of AI model training. For example, the larger the data volume of AI model training, the larger the represented computing power range and / or the larger the computation amount.

[0217] In some embodiments, the first information further includes a type of computing power.

[0218] Optionally, different types of computing power correspond to different time domain characteristics. That is, the computing power can be classified according to time domain characteristics. The first device can report the type corresponding to the required computing power. The computing power classified according to time domain characteristics can include at least one of the following: a periodic type; a semi-persistent type; a non-periodic type. The periodic type can represent a type of computing power provided periodically according to a periodic value. The semi-persistent type can represent a type of computing power provided after activation and before deactivation. Alternatively, the semi-persistent type can also represent a type of computing power provided according to a configured number of times and a time interval between each two times. The non-periodic type can represent a type of computing power provided once.

[0219] Optionally, different types of computing power correspond to different quality of service (QoS). That is, the computing power can be classified according to the quality of service. The quality of service can include at least one of the following parameters: a service type; a priority level; a packet delay budget; a packet error rate; an averaging window; a maximum data burst volume; an allocation and retention priority; packet data unit (PDU) set comprehensive processing information; reflective QoS attribute; guaranteed flow bit rate (GFBR); maximum flow bit rate (MFBR); maximum packet loss rate; latency requirement.

[0220] Optionally, different types of computing power are used for different time domain characteristic services, such as periodic services requiring periodic computing power; semi-persistent services requiring semi-persistent computing power; and non-periodic services requiring non-periodic computing power.

[0221] Optionally, different types of computing power can correspond to different units. The computing power can include at least one of the following processing units: a central processing unit (CPU), a data processing unit (DPU), a field-programmable gate array (FPGA), a graphics processing unit (GPU), a neural-network processing unit (NPU), and a tensor processing unit (TPU). The types of computing power classified according to the processing units include at least one of the following: a CPU type, a DPU type, an FPGA type, a GPU type, an NPU type, and a TPU type. For example, different types of computing power can be used to process different computing tasks, and the corresponding computing power information can also be different. For example, the computing power of the GPU type can be used to process images, and the present disclosure does not list all examples.

[0222] In some embodiments, when the computing power is classified according to the time domain characteristics, and the type of computing power included in the first information is a periodic type, the first information further includes a periodic value, so that the second device can determine whether to accept the request of the first device, or can periodically provide the computing power according to the periodic value.

[0223] In some embodiments, when the computing power is classified according to the time domain characteristics, and the type of computing power included in the first information is a semi-persistent type, the first information can further include the number of times of the computing power and / or the time interval between each two uses of the computing power. So that the second device can determine whether to accept the request of the first device, or can provide the computing power according to the number of times of the computing power and the time interval between each two uses.

[0224] In some embodiments, when the computing power is classified according to the time domain characteristics, and the type of computing power included in the first information is a semi-persistent type, the first device can further send second information to request to activate the semi-persistent type of computing power. It can be understood that in this case, the first device actively activates the semi-persistent type of computing power. The first device can also receive third information for activating the semi-persistent type of computing power. It can be understood that in this case, the second device actively activates the semi-persistent type of computing power.

[0225] In some embodiments, when the computing power is classified according to the quality of service, the parameter of the quality of service includes a service type. The service type can also be referred to as a resource type. For example, the service type can include a Non-Guaranteed Bit Rate (Non-GBR) type. The Non-GBR type can refer to a network service type without a specific minimum transmission rate guarantee, which can be suitable for applications with less stringent requirements or can tolerate fluctuations in transmission rate. For another example, the service type can include a Guaranteed Bit Rate (GBR) type. The GBR type can refer to a network service type with a specific minimum transmission rate guarantee, which can be suitable for applications with higher requirements for network stability and transmission rate.

[0226] In some embodiments, when the service type is the GBR type, the parameter of the quality of service can include an average window and / or a maximum data burst volume.

[0227] In some embodiments, when the computing power is classified according to the quality of service, the parameter of the quality of service includes a packet delay budget. The packet delay budget can include a core network packet delay budget. For example, the packet delay budget can be a packet delay budget set by a PDU.

[0228] In some embodiments, when the computing power is classified according to the quality of service, the parameter of the quality of service includes a packet error rate. The packet error rate can include an error rate set by a PDU.

[0229] In some embodiments, when the computing power is classified according to the quality of service, the parameter of the quality of service includes a GFBR. The GFBR can include an uplink GFBR and / or a downlink GFBR.

[0230] In some embodiments, when the computing power is classified according to the quality of service, the parameter of the quality of service includes a MFBR. The MFBR can include an uplink MFBR and / or a downlink MFBR.

[0231] In some embodiments, when the computing power is classified according to the quality of service, the parameter of the quality of service includes a maximum packet loss rate. The maximum packet loss rate can include an uplink maximum packet loss rate and / or a downlink maximum packet loss rate.

[0232] In some embodiments, the parameter of the quality of service can further include notification control.

[0233] In some embodiments, the parameter of the quality of service can further include latency requirement.

[0234] The first information is carried by at least one of the following: Radio Resource Control (RRC) information, the RRC including at least one of a DL RRC, an UL RRC, and an SL RRC; a Medium Access Control Control Element (MAC CE), the MAC CE including at least one of a Downlink (DL) MAC CE, an uplink (UL) MAC CE, and a Sidelink (SL) MAC CE; Uplink Control Information (UCI); Downlink control information (DCI); Sidelink control information; a Physical Random Access Channel (PRACH); a Physical Uplink Control Channel (PUCCH); a Physical Uplink Shared Channel (PUSCH); a Physical Downlink Control Channel (PDCCH); a Physical Downlink Shared Channel (PDSCH); a Physical Sidelink Control Channel (PSCCH); and a Physical Sidelink Shared Channel (PSSCH).

[0235] Optionally, when the first device is a terminal and the second device is a network device, the first information can be carried by at least one of the RRC, the MAC CE, the UCI, the PRACH, the PUCCH, the PUSCH, and the like. The RRC is a Uu interface RRC. The Uu is a name of an interface. The Uu interface can refer to a wireless interface between the terminal and the network device. The MAC CE can be an uplink MAC CE.

[0236] Optionally, when the first device is a network device and the second device is a terminal, the first information can be carried by at least one of the RRC, the MAC CE, the DCI, the PDCCH, the PDSCH, and the like. The RRC is a Uu interface RRC. The Uu is a name of an interface. The Uu interface can refer to a wireless interface between the terminal and the network device. The MAC CE can be a downlink MAC CE.

[0237] Optionally, when the first device and the second device are both terminals, the first information can be carried by at least one of sidelink control information, PSCCH, PSSCH, etc. Wherein, the RRC is the RRC of the sidelink. Wherein, the MAC CE can be the MAC CE of the sidelink.

[0238] In some embodiments, the terms “downlink control information (DCI)”, “downlink (DL) assignment”, “DL DCI”, “uplink (UL) grant”, “UL DCI”, etc. can be replaced with each other.

[0239] In some embodiments, the terms “physical downlink shared channel (PDSCH)”, “DL data”, etc. can be replaced with each other, and the terms “physical uplink shared channel (PUSCH)”, “UL data”, etc. can be replaced with each other.

[0240] In some embodiments, the terms “radio”, “wireless”, “radio access network (RAN)”, “access network (AN)”, “RAN-based”, etc. can be replaced with each other.

[0241] In some embodiments, the first information name is not limited, which can be, for example, “computing power state information”, “request information”, etc., but is not limited thereto. Wherein, the computing power state information can be information representing the computing power state of the terminal, for example, when the computing task to be processed by the terminal exceeds the computing power currently possessed by the terminal, the computing power of the terminal is negative, which is a computing power state of the terminal.

[0242] Step S2102, the first device 101 sends the second information to the second device 102, or the second device 102 sends the third information to the first device 101.

[0243] In some embodiments, the second device 102 receives the second information sent by the first device 101, or the first device 101 receives the third information sent by the second device 102.

[0244] In some embodiments, the second information is used to request to activate the computing power of the semi-persistent type.

[0245] In some embodiments, the third information is used to activate the computing power of the semi-persistent type.

[0246] In some embodiments, the first identifier and / or the second identifier can be included in the second information. The first identifier is used to identify the AI model, and the second identifier is used to identify the computing power request corresponding to the first information. The first device sends the first identifier to the second device to indicate the required AI model. If the second device is deployed with the corresponding AI model, the second device can provide computing power for the first device. Alternatively, the second device is deployed with the corresponding AI model, and the remaining computing power is sufficient to support the training, or inference, etc. of the AI model, and the second device can provide computing power for the first device. If the second device is not deployed with the corresponding AI model, the first device can send the AI model to the second device, or request the AI model from other devices. The first device sends the second identifier to the second device to associate the identifier with the relevant information (e.g., the computing power range and / or the computing amount of the computing power, the type of the computing power, the first identifier, etc., but not limited to) in the current request of the first device. If the second device does not accept the request of the first device, the first device can continue to request computing power with the second identifier in the future. After receiving the second identifier, the second device can determine the relevant information of the computing power requested by the first device based on the second identifier.

[0247] In some embodiments, the first identifier and / or the second identifier can be included in the third information. For example, the second device can send the first identifier of the started AI model to the first device through the third information. For example, when the first device requests computing power of multiple AI models, and the second device can provide computing power of all the AI models requested by the first device, or can only provide computing power of part of the AI models, the second device can inform the first device of the first identifier of the started AI model. The second identifier can be included in the third information. For example, the first device can request computing power from multiple devices including the second device, or the first device can send multiple requests to the second device, and the second device can include the identifier of the request in the second information to identify which request is responded to.

[0248] It can be understood that step S2102 is optional. When the type of the computing power requested by the first device is the semi-persistent type, the first device can send the second information to request activation of the computing power of the semi-persistent type. Alternatively, the first device can receive the third information to actively activate the computing power of the semi-persistent type by the second device. If the type of the computing power is not the semi-persistent type, step S2102 can be omitted. Alternatively, if the type of the computing power is the semi-persistent type, but the second device provides multiple times of computing power according to the number of times and the time interval between each two times, step S2102 can also be omitted.

[0249] In some embodiments, the name of the second information is not limited, which can be, for example, “request information”. The name of the third information is not limited, which can be, for example, “activation information” or “indication information”, etc.

[0250] In step S2103, the second device 102 sends fourth information to the first device 101.

[0251] In some embodiments, the first device 101 receives the fourth information sent by the second device 102.

[0252] In some embodiments, the fourth information is used to indicate that the first device sends the AI model. For example, if there is no corresponding AI model deployed in the second device, the second device can send the second information to the first device to indicate the first device to send the AI model to the second device.

[0253] It can be understood that the second device can also send the fourth information to other devices, that is, the second device can request other devices to send the AI model.

[0254] In some embodiments, the first identifier and / or the second identifier in the above embodiments can also be included in the fourth information.

[0255] In some embodiments, the name of the fourth information is not limited, which can be, for example, “indication information”.

[0256] In step S2104, the first device 101 sends the AI model to the second device 102.

[0257] In some embodiments, the second device 102 receives the AI model sent by the first device 101. The second device can share computing power with the first device based on the received AI model. For example, the first device can be model-inferred based on the AI model, but is not limited thereto, and the present disclosure will not be exemplified one by one.

[0258] In step S2105, the first device 101 sends fifth information to the second device 102, or the second device 102 sends the fifth information to the first device 101.

[0259] In some embodiments, the second device 102 receives the fifth information sent by the first device 101. Or, the first device 101 receives the fifth information sent by the second device 102. For example, the first device is a terminal, and the second device is a network device. In this case, the first device receives the fifth information sent by the second device. For another example, the first device is a network device, and the second device is a terminal. In this case, the second device receives the fifth information sent by the first device. That is, no matter whether the device sending the first information is a terminal or a network device, the network device sends the fifth information to the terminal. However, it should be understood that this example is only illustrative, and is not limited thereto. For another example, the first device and the second device are both terminals. In this case, the first device can receive the fifth information sent by the second device, or the second device can receive the fifth information sent by the first device.

[0260] In some embodiments, the fifth information includes allocation information of the first resource, where the first resource is used to transmit data of a computing task corresponding to the computing power. For example, the data of the computing task corresponding to the computing power can include an image corresponding to image processing, data corresponding to data processing, speech corresponding to online translation, data for AI model training, data for AI model derivation, and the like. However, the present disclosure is not limited thereto. In addition, the data of the computing task corresponding to the computing power can also be referred to as data corresponding to the computing power. It should be understood that in the embodiments of the present disclosure, the data of the computing task corresponding to the computing power and the data corresponding to the computing power have the same meaning, and can be used interchangeably.

[0261] In some embodiments, when the first device is a terminal, and the second device is a network device. Or, the first device is a network device, and the second device is a terminal. The fifth information can be an uplink transmission resource. When the first device and the second device are both terminals, the fifth information can be a sidelink transmission resource.

[0262] In some embodiments, the fifth information is carried by at least one of the following: a radio resource control (RRC) information, the RRC information including at least one of a DL RRC and a SL RRC; a medium access control control element (MAC CE), the MAC CE including at least one of a downlink (DL) MAC CE and a sidelink (SL) MAC CE; a control information, the control information including at least one of a downlink control information (DCI) and a sidelink control information. For example, if the first device is a terminal and the second device is a network device, the first device receives the fifth information sent by the second device, and the fifth information can be sent by at least one of the DL RRC, the DL MAC CE and the DCI. For another example, if the first device is a network device and the second device is a terminal, the first device can send the fifth information to the second device, and the fifth information can be sent by at least one of the DL RRC, the DL MAC CE and the DCI. For another example, if the first device and the second device are both terminals, the first device sends the fifth information to the second device, or the second device sends the fifth information to the first device, and the fifth information can be sent by at least one of the SL RRC, the SL MAC CE and the sidelink control information.

[0263] In some embodiments, the allocation information of the first resource includes at least one of the following: a time domain resource; a frequency domain resource; an offset value of the time domain resource relative to a reference system frame number; a period value of the time domain resource; a process number of a hybrid automatic repeat request (HARQ); a modulation and coding scheme; a power control value; an antenna port; demodulation reference signal (DMRS) information; and transmission configuration indicator (TCI) state. For example, when the fifth information is configured by the RRC, the at least one of the above can be included, but is not limited thereto.

[0264] In some embodiments, a first part of parameters in the allocation information of the first resource is carried by the RRC, and a second part of parameters is carried by the MAC CE or the control information. For example, the first part of parameters can be configured by the RRC, and the second part of parameters can be activated by the MAC CE for transmitting data of a computing task corresponding to the computing power. For another example, the first part of parameters can be configured by the RRC, and the second part of parameters can be indicated by the control information for transmitting data of a computing task corresponding to the computing power.

[0265] In some embodiments, the first part of parameters comprises at least one of: a periodicity value of time domain resource; a process number of hybrid automatic repeat request (HARQ); a power control value; demodulation reference signal (DMRS) information.

[0266] In some embodiments, the second part of parameters comprises at least one of: time domain resource; frequency domain resource; modulation and coding scheme; antenna port; transmission configuration indication (TCI) state.

[0267] In some embodiments, the first resource can comprise at least one of: periodic physical uplink control channel (PUCCH); configured grant physical uplink shared channel (CG PUSCH); semi-persistent PUSCH; physical downlink control channel (PDCCH); physical downlink shared channel (PDSCH); physical side-link control channel (PSCCH); physical sidelink shared channel (PSSCH). For example, when the fifth information is scheduled by control information, the above-mentioned at least one can be included, but is not limited thereto.

[0268] The two dashed lines in step S2105 in FIG. 2a indicate that both are optional, i.e., the first device 101 can send the fifth information to the second device 102. The second device 102 can also send the fifth information to the first device 101.

[0269] The communication method related to the embodiments of the present disclosure can comprise at least one of steps S2101-S2105. For example, step S2101 can be implemented as an independent embodiment, steps S2101-S2104 can be implemented as an independent embodiment, and steps S2101, S2102 and S2105 can be implemented as separate embodiments, but are not limited thereto.

[0270] In some embodiments, steps S2102-S2105 are optional, and one or more of these steps can be omitted or replaced in different embodiments.

[0271] In some embodiments, other optional implementations can be described before or after the corresponding description of FIG. 2a.

[0272] The present disclosure takes the first device as a terminal and the second device as a network device as an example, and provides the following embodiments.

[0273] FIG. 2b is an interaction diagram of a communication method according to an embodiment of the present disclosure. As shown in FIG. 2b, the embodiment of the present disclosure relates to a communication method for a communication system 200, and the above method comprises the following steps.

[0274] In step S2201, the terminal 201 sends first information to the network device 202.

[0275] The step S2201 can refer to the optional implementation of the step S2101, and the present disclosure will not be repeated here.

[0276] In step S2202, the terminal 201 sends second information to the network device 202, or the network device 202 sends third information to the terminal 201.

[0277] The step S2202 can refer to the optional implementation of the step S2102, and the present disclosure will not be repeated here.

[0278] In step S2203, the network device 202 sends fourth information to the terminal 201.

[0279] The step S2203 can refer to the optional implementation of the step S2103, and the present disclosure will not be repeated here.

[0280] In step S2204, the terminal 201 sends an AI model to the network device 202.

[0281] The step S2204 can refer to the optional implementation of the step S2104, and the present disclosure will not be repeated here.

[0282] In step S2205, the terminal 201 sends fifth information to the network device 202, or the network device 202 sends fifth information to the terminal 201.

[0283] The step S2205 can refer to the optional implementation of the step S2105, and the present disclosure will not be repeated here.

[0284] The communication method related to the embodiment of the present disclosure can include at least one of the steps S2201-S2205. For example, the step S2201 can be implemented as an independent embodiment, the steps S2201-S2204 can be implemented as an independent embodiment, and the steps S2201, S2202 and S2205 can be implemented as separate embodiments, but not limited thereto.

[0285] In some embodiments, the steps S2202-S2205 are optional, and one or more of these steps can be omitted or replaced in different embodiments.

[0286] In some embodiments, other optional implementations described before or after the corresponding description of FIG. 2b can be referred to.

[0287] The present disclosure takes the first device as a network device and the second device as a terminal as an example, and provides the following embodiments.

[0288] FIG. 2c is an interaction diagram of a communication method according to an embodiment of the present disclosure. As shown in FIG. 2c, the embodiment of the present disclosure relates to a communication method for a communication system 200, and the above method comprises the following steps.

[0289] In step S2301, the network device 202 sends first information to the terminal 201.

[0290] Step S2301 can refer to the optional implementation of step S2101, and the present disclosure will not be repeated here.

[0291] In step S2302, the network device 202 sends second information to the terminal 201, or the terminal 201 sends third information to the network device 202.

[0292] Step S2302 can refer to the optional implementation of step S2102, and the present disclosure will not be repeated here.

[0293] In step S2303, the terminal 201 sends fourth information to the network device 202.

[0294] Step S2303 can refer to the optional implementation of step S2103, and the present disclosure will not be repeated here.

[0295] In step S2304, the network device 202 sends an AI model to the terminal 201.

[0296] Step S2304 can refer to the optional implementation of step S2104, and the present disclosure will not be repeated here.

[0297] In step S2305, the network device 202 sends fifth information to the terminal 201, or the terminal 201 sends fifth information to the network device 202.

[0298] Step S2305 can refer to the optional implementation of step S2105, and the present disclosure will not be repeated here.

[0299] The communication method related to the embodiment of the present disclosure can include at least one of steps S2301-S2305. For example, step S2301 can be implemented as an independent embodiment, steps S2301-S2304 can be implemented as an independent embodiment, and steps S2301, S2302 and S2305 can be implemented as separate embodiments, but not limited thereto.

[0300] In some embodiments, steps S2302-S2305 are optional, and one or more of these steps may be omitted or substituted in different embodiments.

[0301] In some embodiments, other optional implementations may be described before or after the specification corresponding to FIG2c.

[0302] This disclosure takes the example where both the first device and the second device are terminals, and provides the following embodiments.

[0303] Figure 2d is an interactive schematic diagram of a communication method according to an embodiment of the present disclosure. As shown in Figure 2d, the present disclosure relates to a communication method for a communication system 300, the method comprising:

[0304] In step S2401, terminal 301 sends the first information to terminal 302.

[0305] Step S2401 can be implemented with reference to the optional implementation of step S2101, which will not be elaborated here.

[0306] In step S2402, terminal 301 sends second information to terminal 302, or terminal 302 sends third information to terminal 301.

[0307] Step S2402 can be implemented with reference to the optional implementation of step S2102, which will not be elaborated here.

[0308] In step S2403, terminal 302 sends the fourth information to terminal 301.

[0309] Step S2403 can be implemented with reference to the optional implementation of step S2103, which will not be elaborated here.

[0310] In step S2404, terminal 301 sends the AI ​​model to terminal 302.

[0311] Step S2404 can be implemented with reference to the optional implementation of step S2104, which will not be elaborated here.

[0312] In step S2405, terminal 301 sends the fifth information to terminal 302, or terminal 302 sends the fifth information to terminal 301.

[0313] The communication method involved in the embodiments of this disclosure may include at least one of steps S2401 to S2405. For example, step S2401 may be implemented as a standalone embodiment, steps S2401-S2404 may be implemented as standalone embodiments, and steps S2401, S2402 and S2405 may be implemented as separate embodiments, but are not limited thereto.

[0314] In some embodiments, steps S2402-S2405 are optional, and one or more of these steps can be omitted or replaced in different embodiments.

[0315] In some embodiments, other optional implementations can be found in the description before or after the description of Figure 2d.

[0316] Figure 3a is a flow diagram of a communication method according to an embodiment of the present disclosure. As shown in Figure 3a, the embodiment of the present disclosure relates to a communication method, which is performed by a first device 101 (or a terminal 201, or a network device 202, or a terminal 301), and the above method comprises:

[0317] Step S3101: transmitting first information.

[0318] Optional implementations of step S3101 can be found in the optional implementations of step S2101 of Figure 2a and other associated parts in the embodiments related to Figure 2a, which will not be repeated here.

[0319] In some embodiments, the first device 101 transmits the first information to the second device 102, but is not limited thereto, and can also transmit the first information to other subjects.

[0320] In some embodiments, the terminal 201 transmits the first information to the network device 202, but is not limited thereto, and can also transmit the first information to other subjects.

[0321] In some embodiments, the network device 202 transmits the first information to the terminal 201, but is not limited thereto, and can also transmit the first information to other subjects.

[0322] In some embodiments, the terminal 301 transmits the first information to the terminal 302, but is not limited thereto, and can also transmit the first information to other subjects.

[0323] Step S3102: transmitting second information, or obtaining third information.

[0324] Optional implementations of step S3102 can be found in the optional implementations of step S2102 of Figure 2a and other associated parts in the embodiments related to Figure 2a, which will not be repeated here.

[0325] In some embodiments, the first device 101 transmits the second information to the second device 102, but is not limited thereto, and can also transmit the second information to other subjects.

[0326] In some embodiments, the terminal 201 transmits the second information to the network device 202, but is not limited thereto, and can also transmit the second information to other subjects.

[0327] In some embodiments, the network device 202 sends the second information to the terminal 201, but is not limited thereto, and can also send the second information to other subjects.

[0328] In some embodiments, the terminal 301 sends the second information to the terminal 302, but is not limited thereto, and can also send the second information to other subjects.

[0329] In some embodiments, the first device 101 receives the third information sent by the second device 102, but is not limited thereto, and can also receive the third information sent by other subjects.

[0330] In some embodiments, the terminal 201 receives the third information sent by the network device 202, but is not limited thereto, and can also receive the third information sent by other subjects.

[0331] In some embodiments, the network device 202 receives the third information sent by the terminal 201, but is not limited thereto, and can also receive the third information sent by other subjects.

[0332] In some embodiments, the terminal 301 receives the third information sent by the terminal 302, but is not limited thereto, and can also receive the third information sent by other subjects.

[0333] In some embodiments, the first device 101 (or the terminal 201, or the network device 202, or the terminal 301) acquires the third information as specified by a protocol.

[0334] In some embodiments, the first device 101 (or the terminal 201, or the network device 202, or the terminal 301) acquires the third information from an upper layer.

[0335] In some embodiments, the first device 101 (or the terminal 201, or the network device 202, or the terminal 301) processes to obtain the third information.

[0336] In some embodiments, the step S3102 is omitted, and the first device 101 (or the terminal 201, or the network device 202, or the terminal 301, or the terminal 302) autonomously implements the function indicated by the first information, or the above function is default or default.

[0337] In step S3103, the fourth information is acquired.

[0338] The optional implementation of step S3103 can refer to the optional implementation of step S2103 in FIG. 2a and other associated parts in the embodiments involved in FIG. 2a, which will not be repeated here.

[0339] In some embodiments, the first device 101 receives the fourth information sent by the second device 102, but is not limited thereto, and can also receive the fourth information sent by other subjects.

[0340] In some embodiments, the terminal 201 receives the fourth information sent by the network device 202, but is not limited thereto, and can also receive the fourth information sent by other subjects.

[0341] In some embodiments, the network device 202 receives the fourth information sent by the terminal 201, but is not limited thereto, and can also receive the fourth information sent by other subjects.

[0342] In some embodiments, the terminal 301 receives the fourth information sent by the terminal 302, but is not limited thereto, and can also receive the fourth information sent by other subjects.

[0343] In some embodiments, the first device 101 (or the terminal 201, or the network device 202, or the terminal 301) obtains the fourth information as specified by a protocol.

[0344] In some embodiments, the first device 101 (or the terminal 201, or the network device 202, or the terminal 301) obtains the fourth information from an upper layer.

[0345] In some embodiments, the first device 101 (or the terminal 201, or the network device 202, or the terminal 301) processes to obtain the fourth information.

[0346] In some embodiments, step S3103 is omitted, and the first device 101 (or the terminal 201, or the network device 202, or the terminal 301, or the terminal 302) autonomously implements the function indicated by the first information, or the above function is default or default.

[0347] Step S3104, sending the AI model.

[0348] The optional implementation of step S3104 can refer to the optional implementation of step S2104 in FIG. 2a and other associated parts in the embodiments involved in FIG. 2a, which will not be repeated here.

[0349] The optional implementation of step S3103 can refer to the optional implementation of step S2103 in FIG. 2a and other associated parts in the embodiments involved in FIG. 2a, which will not be repeated here.

[0350] In some embodiments, the first device 101 sends the AI model to the second device 102, but is not limited thereto, and can also send the AI model to other subjects.

[0351] In some embodiments, the terminal 201 sends the AI model to the network device 202, but is not limited thereto, and can also send the AI model to other subjects.

[0352] In some embodiments, the network device 202 sends the AI model to the terminal 201, but is not limited thereto, and can also send the AI model to other subjects.

[0353] In some embodiments, the terminal 301 sends the AI model to the terminal 302, but is not limited thereto, and can also send the AI model to other subjects.

[0354] Step S3105: sending the fifth information, or obtaining the fifth information.

[0355] The optional implementation of step S3105 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.

[0356] The communication method involved in the embodiments of the present disclosure can include at least one of steps S3101-S3105. For example, step S3101 can be implemented as an independent embodiment, steps S3101-S3103 can be implemented as an independent embodiment, and steps S3101, S3102 and S3104 can be implemented as separate embodiments, but are not limited thereto.

[0357] In some embodiments, steps S3102-S3105 are optional, and one or more of these steps can be omitted or replaced in different embodiments.

[0358] In some embodiments, other optional implementations can be described before or after the description of FIG. 3a.

[0359] FIG. 3b is a flow chart of a communication method according to an embodiment of the present disclosure. As shown in FIG. 3b, the embodiment of the present disclosure relates to a communication method, which is performed by a first device 101 (or a terminal 201, or a network device 202, or a terminal 301), and the above method includes:

[0360] Step S3201: sending first information.

[0361] The optional implementation of step S3201 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.

[0362] In some embodiments, the first device 101 sends the first information to the second device 102, but is not limited thereto, and can also send the first information to other subjects.

[0363] In some embodiments, the terminal 201 sends the first information to the network device 202, but is not limited thereto, and can also send the first information to other subjects.

[0364] In some embodiments, the network device 202 sends the first information to the terminal 201, but is not limited thereto, and can also send the first information to other subjects.

[0365] In some embodiments, the terminal 301 sends the first information to the terminal 302, but is not limited thereto, and can also send the first information to other subjects.

[0366] FIG. 4a is a flowchart of a communication method according to an embodiment of the present disclosure. As shown in FIG. 4a, the embodiment of the present disclosure relates to a communication method, which is performed by the second device 102 (or the network device 202, or the terminal 201, or the terminal 302), and the above method comprises the following steps:

[0367] In step S4101, the first information is acquired.

[0368] 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 described here.

[0369] In some embodiments, the second device 102 receives the first information sent by the first device 101, but is not limited thereto, and can also receive the first information sent by other subjects.

[0370] In some embodiments, the network device 202 receives the first information sent by the terminal 201, but is not limited thereto, and can also receive the first information sent by other subjects.

[0371] In some embodiments, the terminal 201 receives the first information sent by the network device 202, but is not limited thereto, and can also receive the first information sent by other subjects.

[0372] In some embodiments, the terminal 302 receives the first information sent by the terminal 301, but is not limited thereto, and can also receive the first information sent by other subjects.

[0373] In some embodiments, the second device 102 (or the network device 202, or the terminal 201, or the terminal 302) acquires the first information specified by a protocol.

[0374] In some embodiments, the second device 102 (or the network device 202, or the terminal 201, or the terminal 302) acquires the first information from an upper layer.

[0375] In some embodiments, the second device 102 (or the network device 202, or the terminal 201, or the terminal 302) processes to obtain the first information.

[0376] In some embodiments, the step S4101 is omitted, and the second device 102 (or the network device 202, or the terminal 201, or the terminal 302) autonomously implements the function indicated by the first information, or the function is default or default.

[0377] In step S4102, the second information is obtained, or the third information is sent.

[0378] The optional implementation of step S4102 can refer to the optional implementation of step S2102 in FIG. 2a, and other associated parts in the embodiments involved in FIG. 2a, which will not be repeated here.

[0379] In some embodiments, the second device 102 receives the second information sent by the first device 101, but is not limited thereto, and can also receive the second information sent by other subjects.

[0380] In some embodiments, the network device 202 receives the second information sent by the terminal 201, but is not limited thereto, and can also receive the second information sent by other subjects.

[0381] In some embodiments, the terminal 201 receives the second information sent by the network device 202, but is not limited thereto, and can also receive the second information sent by other subjects.

[0382] In some embodiments, the terminal 302 receives the second information sent by the terminal 301, but is not limited thereto, and can also receive the second information sent by other subjects.

[0383] In some embodiments, the second device 102 (or the network device 202, or the terminal 201, or the terminal 301) obtains the second information specified by a protocol.

[0384] In some embodiments, the second device 102 (or the network device 202, or the terminal 201, or the terminal 301) obtains the second information from an upper layer.

[0385] In some embodiments, the second device 102 (or the network device 202, or the terminal 201, or the terminal 301) processes to obtain the second information.

[0386] In some embodiments, the step S3102 is omitted, and the second device 102 (or the network device 202, or the terminal 201, or the terminal 301, or the terminal 302) autonomously implements the function indicated by the first information, or the function is default or default.

[0387] In some embodiments, the second device 102 sends the third information to the first device 101, but is not limited thereto, and can send the third information to other subjects.

[0388] In some embodiments, the network device 202 sends the third information to the terminal 201, but is not limited thereto, and can send the third information to other subjects.

[0389] In some embodiments, the network device 202 sends the third information to the terminal 201, but is not limited thereto, and can send the third information to other subjects.

[0390] In some embodiments, the terminal 302 sends the third information to the terminal 301, but is not limited thereto, and can send the third information to other subjects.

[0391] Step S4103: sending fourth information.

[0392] The optional implementation of step S4103 can refer to the optional implementation of step S2103 in FIG. 2a and other associated parts in the embodiments involved in FIG. 2a, which will not be repeated here.

[0393] In some embodiments, the second device 102 sends the fourth information to the first device 101, but is not limited thereto, and can send the fourth information to other subjects.

[0394] In some embodiments, the network device 202 sends the fourth information to the terminal 201, but is not limited thereto, and can send the fourth information to other subjects.

[0395] In some embodiments, the network device 202 sends the fourth information to the terminal 201, but is not limited thereto, and can send the fourth information to other subjects.

[0396] In some embodiments, the terminal 302 sends the fourth information to the terminal 301, but is not limited thereto, and can send the fourth information to other subjects.

[0397] Step S4104: obtaining an AI model.

[0398] The optional implementation of step S4104 can refer to the optional implementation of step S2104 in FIG. 2a and other associated parts in the embodiments involved in FIG. 2a, which will not be repeated here.

[0399] In some embodiments, the second device 102 receives the AI model sent by the first device 101, but is not limited thereto, and can receive the AI model sent by other subjects.

[0400] In some embodiments, the network device 202 receives the AI model sent by the terminal 201, but is not limited thereto, and can also receive the AI model sent by other subjects.

[0401] In some embodiments, the terminal 201 receives the AI model sent by the network device 202, but is not limited thereto, and can also receive the AI model sent by other subjects.

[0402] In some embodiments, the terminal 302 receives the AI model sent by the terminal 301, but is not limited thereto, and can also receive the AI model sent by other subjects.

[0403] In some embodiments, the second device 102 (or the network device 202, or the terminal 201, or the terminal 302) acquires the AI model specified by the protocol.

[0404] In some embodiments, the second device 102 (or the network device 202, or the terminal 201, or the terminal 302) acquires the AI model from the upper layer(s).

[0405] In some embodiments, the second device 102 (or the network device 202, or the terminal 201, or the terminal 302) processes to obtain the AI model.

[0406] In some embodiments, the step S4104 is omitted, and the second device 102 (or the network device 202, or the terminal 201, or the terminal 302) autonomously implements the function indicated by the AI model, or the above function is default or default.

[0407] Step S4105, acquiring or sending the fifth information.

[0408] The optional implementation of step S4105 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.

[0409] The communication method involved in the embodiments of the present disclosure can include at least one of steps S4101-S4105. For example, step S4101 can be implemented as an independent embodiment, steps S4101-S4104 can be implemented as an independent embodiment, and steps S4101, S4102 and S4105 can be implemented as separate embodiments, but are not limited thereto.

[0410] In some embodiments, steps S4102-S4105 are optional, and one or more of these steps can be omitted or replaced in different embodiments.

[0411] In some embodiments, reference can be made to the description of Figure 4a and the other optional implementations described before or after the description of Figure 4a.

[0412] Figure 4b is a flow chart of a communication method according to an embodiment of the present disclosure. As shown in Figure 4b, the embodiment of the present disclosure relates to a communication method, which is performed by the second device 102 (or the network device 202, or the terminal 201, or the terminal 302), and the above method comprises the following steps:

[0413] In step S4201, first information is acquired.

[0414] Optional implementations of step S4201 can be found in the optional implementations of step S2101 of Figure 2a and other related parts of the embodiments related to Figure 2a, which will not be described here.

[0415] In some embodiments, the second device 102 receives the first information sent by the first device 101, but is not limited thereto, and can also receive the first information sent by other subjects.

[0416] In some embodiments, the network device 202 receives the first information sent by the terminal 201, but is not limited thereto, and can also receive the first information sent by other subjects.

[0417] In some embodiments, the terminal 201 receives the first information sent by the network device 202, but is not limited thereto, and can also receive the first information sent by other subjects.

[0418] In some embodiments, the terminal 302 receives the first information sent by the terminal 301, but is not limited thereto, and can also receive the first information sent by other subjects.

[0419] In some embodiments, the second device 102 (or the network device 202, or the terminal 201, or the terminal 302) acquires the first information specified by a protocol.

[0420] In some embodiments, the second device 102 (or the network device 202, or the terminal 201, or the terminal 302) acquires the first information from an upper layer.

[0421] In some embodiments, the second device 102 (or the network device 202, or the terminal 201, or the terminal 302) processes to obtain the first information.

[0422] In some embodiments, step S4201 is omitted, and the second device 102 (or the network device 202, or the terminal 201, or the terminal 302) autonomously implements the function indicated by the first information, or the above function is default or default.

[0423] FIG. 5 is a schematic diagram of a communication method according to an embodiment of the present disclosure. As shown in FIG. 5, the embodiment of the present disclosure relates to a communication method, and the method comprises:

[0424] In step S5101, the first device 101 sends first information to the second device 102.

[0425] The optional implementation of step S5101 can refer to the optional implementation of step S2101 in FIG. 2a, step S3101 in FIG. 3a, step S4101 in FIG. 4a, and other associated parts in the embodiments related to FIG. 2a, FIG. 3a, and FIG. 4a, which are not described here.

[0426] In some embodiments, the above method can include the method of the embodiments of the above communication system side, first device (or terminal, or network device) side, second device (or network device, or terminal) side, etc., which are not described here.

[0427] The present disclosure provides a communication method, which is as follows:

[0428] In some embodiments, the terminal sends the first information, which includes the required calculation amount and / or the range of computing power.

[0429] In some embodiments, the first information further includes a request ID, a model ID, or a functionality ID.

[0430] In some embodiments, the terminal further sends second information, which informs the network device of the type to which the next calculation amount / computing power request of the terminal belongs.

[0431] In some embodiments, the type includes at least one type, such as a first type, a second type, and a third type.

[0432] In some embodiments, different types correspond to different computing power time domain characteristics: the first type corresponds to periodic computing power requests; the second type corresponds to semi-persistent computing power requests; and the third type corresponds to aperiodic computing power requests.

[0433] In some embodiments, the periodic computing power request: the terminal needs the computing power periodically from the start of sending the request to the cancellation of the computing power request.

[0434] In some embodiments, if it is periodic, the period value also needs to be indicated.

[0435] In some embodiments, semi-persistent computing power request: that is, the terminal needs to send a computing power activation request after sending the request, and periodically needs the computing power before the computing power is deactivated.

[0436] In some embodiments, if it is semi-persistent, the number of times, the period value / time interval between two times also need to be indicated

[0437] In some embodiments, aperiodic computing power request: that is, the terminal only needs the computing power before the computing power demand ends.

[0438] In some embodiments, one case is that the service is aperiodic, and another case is that the terminal's own computing power can sometimes also handle it. Or different types correspond to different QoS values(value), and different QoS values are one-to-one mapped with at least one of the following:

[0439] QoS flow ID

[0440] The QoS identifier corresponds to at least one of the following:

[0441] Resource type (non-GBR: guaranteed bit rate, GBR, delay critical GBR);

[0442] Priority;

[0443] Packet delay budget (including core network packet delay budget);

[0444] Data packet error rate;

[0445] Average window (only applicable to GBR and delay critical GBR resource types);

[0446] Maximum data burst size (only applicable to delay critical GBR resource type).

[0447] Allocation and retention priority (ARP).

[0448] The PDU sets QoS parameters corresponding to at least one of the following:

[0449] PDU sets delay budget (PSDB).

[0450] PDU sets error rate (PSER).

[0451] PDU set integrated processing information (PSIHI).

[0452] Reflective QoS attribute (RQA).

[0453] Guaranteed traffic bit rate (GFBR), including UL and DL; and

[0454] Maximum flow bit rate (MFBR), including UL and DL; and

[0455] Notification control;

[0456] Maximum packet loss rate, including UL and DL.

[0457] Three, based on one or two, the second step: the network side device gives a response,

[0458] In some embodiments, the meaning of response includes at least one of the following:

[0459] The response can indicate that the base station has reserved computing power. Of course, reserving computing power also means that the network side can activate the model.

[0460] In some embodiments, the meaning of reserving computing power includes the following:

[0461] For periodic, periodic computing power resources have been reserved.

[0462] For semi-persistent, one or more times within T have been reserved.

[0463] For aperiodic, a single time within T has been reserved.

[0464] The response can be that the network side device can activate the model.

[0465] In some embodiments, it can include model ID or request ID or functionality ID.

[0466] In some embodiments, the response can also indicate that the network side device needs the terminal to provide the model, that is, instruct the terminal to send the model to the network side device.

[0467] In some embodiments, the third step: the network side device configures the transmission resource of the data that needs to be processed corresponding to the computing power request. The configuration method includes at least one of the following (such as having reserved computing power):

[0468] In some embodiments, the resource configuration signaling includes at least one of RRC, MAC CE and DCI.

[0469] In some embodiments, the resource of configured grant is configured.

[0470] In some embodiments, such as RRC configuration of resource, time and frequency resource location, port, MCS and all information, similar to CG type1PUSCH; The specific RRC configuration is as follows:

[0471] Period;

[0472] time domain resource offset value relative to Reference SFN;

[0473] time domain resource allocation;

[0474] HARQ process number;

[0475] frequency domain resource location;

[0476] MCS;

[0477] power control related value;

[0478] antenna port;

[0479] DMRS related information.

[0480] In some embodiments, part of the RRC configured resource information is activated by MAC CE or triggered by DCI, and another part of the information is indicated. Similar to CG type 2 PUSCH. Specifically, the MAC CE or DCI indicates at least one of the following:

[0481] time domain resource allocation;

[0482] frequency domain resource allocation;

[0483] MCS;

[0484] antenna port;

[0485] TCI state.

[0486] In some embodiments, the above configuration method is applicable to the first type of computing power request and the second type of computing power request.

[0487] In some embodiments, the DCI schedules the resource, similar to dynamic scheduled PUSCH.

[0488] In some embodiments, the above configuration method is applicable to any type of computing power request

[0489] In some embodiments, the resource configuration signaling can be included in the same signaling or different signaling as the network side device response, and if in different signaling, the resource configuration signaling can contain the model ID or request ID.

[0490] In some embodiments, the terminal is instructed that the resource is used for the transmission of data corresponding to the model ID or request ID.

[0491] In some embodiments, the base station configures a first uplink resource for dynamically requesting computing power (such as unreserved computing power).

[0492] In some embodiments, the first uplink resource can be a periodic PUCCH or CG PUSCH or semi-persistent PUSCH for dynamic transmission of the computing power request, and at this time the computing power request only needs to upload an ID, based on which the base station can know the corresponding model and the required computing power value.

[0493] In some embodiments, after receiving the request, the base station sends DCI to schedule the PUSCH resource for uploading the computing power related data

[0494] In some embodiments, the DCI can include the model ID or request ID.

[0495] In some embodiments, the base station configures the first uplink resource and the second uplink resource.

[0496] In some embodiments, the first uplink resource can be a periodic PUCCH or CG PUSCH or semi-persistent PUSCH; the second uplink resource can be a periodic CG PUSCH or semi-persistent PUSCH. When the terminal needs to request computing power, it sends a computing power request on the first uplink resource, which is also only one ID, based on which the base station can know the corresponding model and the required computing power value. Next, the terminal sends the computing power related data on the second uplink resource. Compared with method one, this is to reduce the latency of the second uplink resource allocation.

[0497] In some embodiments, the required computing amount and / or computing power range can be indicated in different ways.

[0498] In some embodiments, the computing amount / computing power range indication method includes at least one of the following:

[0499] 1) The type of use of the requested computing amount / computing power can be indicated first: for data processing, model training or model inference; then the range of computing amount / computing power for the corresponding use is indicated, such as the quantization gradient and range of computing amount / computing power for each use are different.

[0500] For example, model training:

[0501] Bit 00 corresponds to 0-100M;

[0502] Bit 01 corresponds to 100M-200M;

[0503] Bit 10 corresponds to 200M-300M;

[0504] Bit 11 corresponds to 300M-∞. Where ∞ represents positive infinity. 300M-∞ represents a computing power range greater than or equal to 300M.

[0505] For example, model derivation:

[0506] Bit 00 corresponds to 0~10M;

[0507] Bit 01 corresponds to 10M~20M;

[0508] Bit 10 corresponds to 20M~30M;

[0509] Bit 11 corresponds to 30M to ∞. 30M to ∞ represents a computing power range greater than or equal to 30M.

[0510] 2) Directly indicating the range of computational load / power eliminates the need to differentiate between different uses. Therefore, compared to prioritizing usage, either more bits are required, or a larger quantization gradient is needed.

[0511] In some embodiments, the first information may be sent based on RRC, MAC CE, or UCI.

[0512] In some embodiments, the first information can also be called computing power status information, that is, computing power request is also a computing power status, for example, when computing power is requested, the computing power of the terminal is negative.

[0513] This disclosure also provides an apparatus for implementing any of the above methods. For example, an apparatus is provided that includes units or modules for implementing the steps performed by the terminal in any of the above methods. Alternatively, another apparatus is provided that includes units or modules for implementing the steps performed by a network device (e.g., an access network device, a core network functional node, a core network device, etc.) in any of the above methods.

[0514] 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, the processor is connected with a memory, the memory stores instructions, and the processor calls the instructions stored in the memory to realize the functions of any one of the above methods or the units or modules of the above apparatus, wherein the processor is a general processor such as a central processing unit (CPU) or a microprocessor, and the memory is a memory in 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 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 units or modules are realized by the design of logical relationship of elements in the circuit; for another 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 units or modules. All units or modules of the above apparatus can be all implemented in the form of processor calling software, or all implemented in the form of hardware circuit, or part implemented in the form of processor calling software and the remaining part implemented in the form of hardware circuit.

[0515] 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 reconfigurable. 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.

[0516] 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 at least one of a transceiver module 6101 and a processing module 6102. The transceiver module 6101 is configured to send first information for requesting computing power, wherein the first information includes a computing power range and / or a computing amount of the computing power.

[0517] In some embodiments, the first information further includes a type of the computing power.

[0518] In some embodiments, different types of the computing power correspond to different time domain characteristics.

[0519] In some embodiments, the type includes at least one of the following: a periodic type; a semi-persistent type; and a non-periodic type.

[0520] In some embodiments, the type includes a periodic type, and the first information further includes a periodic value.

[0521] In some embodiments, the type includes a semi-persistent type, and the first information further includes a number of times of the computing resource requested by the first device and / or a time interval between each two times of the computing resource.

[0522] In some embodiments, the type includes a semi-persistent type, and the transceiver 6101 is further configured to: send, by the first device, second information, the second information being used to request to activate the computing resource of the semi-persistent type; or, receive, by the first device, third information, the third information being used to activate the computing resource of the semi-persistent type.

[0523] In some embodiments, different types of the computing resource correspond to different quality of service (QoS).

[0524] In some embodiments, the QoS includes at least one of the following parameters: a service type; a service priority; a packet delay budget; a packet error rate; an average window; a maximum data burst quantity; an allocation and retention priority; a packet data unit (PDU) set comprehensive processing information; a reflective QoS attribute; a guaranteed traffic bit rate; a maximum traffic bit rate; a maximum packet loss rate; and a latency requirement.

[0525] In some embodiments, different types of the computing resource include at least one of the following: a central processing unit (CPU) type; a data processing unit (DPU) type; a field programmable gate array (FPGA) type; a graphics processing unit (GPU) type; a neural processing unit (NPU) type; and a tensor processing unit (TPU) type.

[0526] In some embodiments, the transceiver 6101 is further configured to: receive, by the first device, fourth information; and the fourth information is used to indicate that the first device sends an AI model; or, the fourth information includes response information of the first information.

[0527] In some embodiments, the fourth information is used to indicate that the first device sends the AI model, and the method further includes: sending, by the first device, the AI model.

[0528] In some embodiments, the fourth information includes response information of the first information, and the method further includes: determining, by the first device based on the fourth information, that a second device has reserved a periodic computing resource; or, determining, by the first device based on the fourth information, that a second device has reserved one or more computing resources within a preset time; or, determining, by the first device based on the fourth information, that a second device has reserved one computing resource within a preset time.

[0529] In some embodiments, the transceiver 6101 is further configured to: send or receive, by the first device, fifth information, the fifth information including allocation information of a first resource, and the first resource being used to transmit data corresponding to the computing resource.

[0530] In some embodiments, the fourth information includes the fifth information.

[0531] In some embodiments, at least one of the second information, the third information, the fourth information and the fifth information includes the first identifier and / or the second identifier; the second information is transmitted by the first device and is used to request to activate the semi-persistent type of computing power; the third information is received by the first device and is used to activate the semi-persistent type of computing power; the fourth information is received by the first device and is used to indicate that the first device transmits an AI model, or the fourth information is received by the first device and includes response information of the first information; the fifth information is received by the first device and includes allocation information of a first resource, the first resource being used to transmit data corresponding to the computing power; the first identifier is used to identify an AI model, and the second identifier is used to identify a computing power request corresponding to the first information.

[0532] In some embodiments, the fifth information is carried by at least one of the following: radio resource control information (RRC); a medium access control control element (MAC CE); and control information.

[0533] In some embodiments, the allocation information of the first resource includes at least one of the following: a time domain resource; a frequency domain resource; an offset value of the time domain resource relative to a reference system frame number; a period value of the time domain resource; a hybrid automatic repeat request (HARQ) process number; a modulation and coding scheme; a power control value; an antenna port; demodulation reference signal (DMRS) information; and transmission configuration indication (TCI) state.

[0534] In some embodiments, the allocation information of the first resource includes first part parameters and second part parameters, the first part parameters are carried by the RRC, and the second part parameters are carried by the MAC CE or the control information.

[0535] In some embodiments, the type of the computing power is a periodic type or a semi-persistent type.

[0536] In some embodiments, the first resource includes at least one of the following resources: a periodic physical uplink control channel (PUCCH); a configured grant physical uplink shared channel (CG PUSCH); a semi-persistent PUSCH; a physical downlink control channel (PDCCH); a physical downlink shared channel (PDSCH); a physical sidelink shared channel (PSSCH); and a physical sidelink control channel (PSCCH).

[0537] In some embodiments, the first information is carried by at least one of the following: a MAC CE; uplink control information; downlink control information; sidelink control information; a physical random access channel (PRACH); a PUCCH; a PUSCH; a PDCCH; a PDSCH; a PSCCH; and a PSSCH.

[0538] 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 at least one of a transceiver module 6201 and a processing module 6202. The transceiver module 6201 is configured to receive first information for requesting a computing power, the first information including a computing power range and / or a computing amount of the computing power.

[0539] In some embodiments, the first information further includes a type of the computing power.

[0540] In some embodiments, different types of the computing power correspond to different time domain characteristics.

[0541] In some embodiments, the type includes at least one of the following: a periodic type; a semi-persistent type; and an aperiodic type.

[0542] In some embodiments, the type includes a periodic type, and the first information further includes a periodic value.

[0543] In some embodiments, the type includes a semi-persistent type, and the first information further includes a number of times of using the computing power and / or a time interval between two times of using the computing power.

[0544] In some embodiments, the type includes a semi-persistent type, and the transceiver module 6201 is further configured to: receive, by the second device, second information for requesting to activate the semi-persistent type of the computing power; or transmit, by the second device, third information for activating the semi-persistent type of the computing power.

[0545] In some embodiments, different types of the computing power correspond to different quality of services (QoSs).

[0546] In some embodiments, the QoS includes at least one of the following parameters: a service type; a service priority; a packet delay budget; a packet error rate; an average window; a maximum data burst volume; an allocation and retention priority; a packet data unit (PDU) set comprehensive processing information; a reflective QoS attribute; a guaranteed flow bit rate; a maximum flow bit rate; a maximum packet loss rate; and a latency requirement.

[0547] In some embodiments, the different types of computing power include at least one of the following: a central processing unit (CPU) type; a data processing unit (DPU) type; a field programmable gate array (FPGA) type; a graphics processing unit (GPU) type; a neural processing unit (NPU) type; and a tensor processing unit (TPU) type.

[0548] In some embodiments, the transceiver 6201 is further configured to: receive, by the second device, fourth information; and / or the fourth information is used to instruct the first device to send an AI model; and / or the fourth information includes response information of the first information.

[0549] In some embodiments, the fourth information is used to instruct the first device to send the AI model, and the method further includes: receiving, by the second device, the AI model.

[0550] In some embodiments, the transceiver 6201 is further configured to: receive or send, by the second device, fifth information, and the fifth information includes allocation information of a first resource, and the first resource is used to transmit data corresponding to the computing power.

[0551] In some embodiments, the fifth information is included in the fourth information.

[0552] In some embodiments, at least one of the second information, the third information, the fourth information, and the fifth information includes a first identifier and / or a second identifier; wherein the second information is received by the second device and is used to request to activate the semi-persistent type of computing power; the third information is sent by the second device and is used to activate the semi-persistent type of computing power; the fourth information is sent by the second device and is used to instruct the first device to send an AI model, or the fourth information is sent by the second device and includes response information of the first information; the fifth information is sent by the second device and is used to include allocation information of a first resource, and the first resource is used to transmit data corresponding to the computing power; the first identifier is used to identify an AI model, and the second identifier is used to identify a computing power request corresponding to the first information.

[0553] In some embodiments, the fifth information is carried by at least one of the following: radio resource control (RRC) information; a medium access control (MAC) control element (CE); and control information.

[0554] In some embodiments, the allocation information of the first resource includes at least one of the following: a time domain resource; a frequency domain resource; an offset value of the time domain resource relative to a reference system frame number; a period value of the time domain resource; a hybrid automatic repeat request (HARQ) process number; a modulation and coding scheme; a power control value; an antenna port; and demodulation reference signal (DMRS) information.

[0555] In some embodiments, the allocation information of the first resource comprises a first part of parameters and a second part of parameters, the first part of parameters is carried by RRC, and the second part of parameters is carried by a MAC CE or control information.

[0556] In some embodiments, the type of the computing power is a periodic type or a semi-persistent type.

[0557] In some embodiments, the first resource comprises at least one of the following resources: a periodic physical uplink control channel (PUCCH), a configured grant physical uplink shared channel (CG PUSCH), a semi-persistent PUSCH, a physical downlink control channel (PDCCH), a physical downlink shared channel (PDSCH), a physical sidelink shared channel (PSSCH), and a physical sidelink control channel (PSCCH).

[0558] In some embodiments, the first information is carried by at least one of the following: a MAC CE, uplink control information, downlink control information, sidelink control information, a physical random access channel (PRACH), a PUCCH, a PUSCH, a PDCCH, a PDSCH, a PSCCH, and a PSSCH.

[0559] FIG. 7a is a structural schematic diagram of a communication device 7100 according to an embodiment of the present disclosure. The communication device 7100 can be a network device, a terminal, a chip, a chip system, a processor, or the like supporting the network device to implement any of the above methods, or a chip, a chip system, a processor, or the like supporting the terminal to implement any of the above methods. Optionally, the network device can be an access network device, a core network device, or the like. Optionally, the terminal can be a user equipment, or the like. 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.

[0560] As shown in FIG. 7a, the communication device 7100 comprises one or more processors 7101. The processor 7101 can be a general-purpose processor or a special-purpose processor, for example, a baseband processor or a central processing unit. The baseband processor can be used to process communication protocols and communication data, and the central processing unit can be used to control the communication device, execute programs, and process data of the programs. The communication device 7100 is used to execute any of the above methods. Optionally, the communication device can be a base station, a baseband chip, a terminal device, a terminal device chip, a DU, a CU, or the like.

[0561] In some embodiments, the communication device 7100 further comprises one or more memories 7102 for storing instructions. Optionally, all or part of the memory 7102 can also be outside the communication device 7100.

[0562] In some embodiments, the communication device 7100 further includes one or more transceivers 7103. When the communication device 7100 includes one or more transceivers 7103, the transceiver 7103 performs the communication steps S2101 of transmitting and / or receiving in the above-described methods, and the processor 7101 performs other steps.

[0563] In some embodiments, the transceiver can include a receiver and / or a transmitter, which can be separate or integrated together. Optionally, the terms of transceiver, transceiving unit, transceiver, transceiving circuit, etc. can be replaced by each other, the terms of transmitter, transmitting unit, transmitter, transmitting circuit, etc. can be replaced by each other, and the terms of receiver, receiving unit, receiver, receiving circuit, etc. can be replaced by each other.

[0564] In some embodiments, the communication device 7100 can include one or more interface circuits 7104. Optionally, the interface circuit 7104 is connected with the memory 7102, and the interface circuit 7104 can be used to receive signals from the memory 7102 or other devices, and can be used to send signals to the memory 7102 or other devices. For example, the interface circuit 7104 can read the instructions stored in the memory 7102 and send the instructions to the processor 7101.

[0565] 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 Figure 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, etc.; (6) other devices, etc.

[0566] Figure 7b is a structural schematic 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 schematic diagram of the chip 7200 shown in Figure 7b can be referred to, but is not limited thereto.

[0567] The chip 7200 includes one or more processors 7201, and the chip 7200 is configured to execute any of the above methods.

[0568] In some embodiments, the chip 7200 further includes one or more interface circuits 7202. Optionally, the interface circuits 7202 are connected with the memory 7203, and the interface circuits 7202 can be configured to receive signals from the memory 7203 or other devices, and the interface circuits 7202 can be configured to send signals to the memory 7203 or other devices. For example, the interface circuits 7202 can read instructions stored in the memory 7203 and send the instructions to the processor 7201.

[0569] In some embodiments, the interface circuits 7202 perform the communication steps S2101 of sending and / or receiving in the above-described methods, and the processor 7201 performs other steps.

[0570] In some embodiments, the terms interface circuit, interface, transceiver pin, transceiver, etc. can be replaced with each other.

[0571] In some embodiments, the chip 7200 further includes one or more memories 7203 for storing instructions. Optionally, all or part of the memories 7203 can be outside the chip 7200.

[0572] The present disclosure further proposes a storage medium having instructions stored thereon, which, when executed on the communication device 7100, cause the communication device 7100 to perform any of the above methods. Optionally, the storage medium is an electronic storage medium. Optionally, 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. Optionally, 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.

[0573] The present disclosure further proposes a program product, which, when executed by the communication device 7100, causes the communication device 7100 to perform any of the above methods. Optionally, the program product is a computer program product.

[0574] The present disclosure further proposes 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 sends first information for requesting computing power, wherein the first information comprises a computing power range and / or a computing amount of the computing power.

2. The method of claim 1, wherein, The type of the computing power is further included in the first information.

3. The method of claim 2, wherein, Different types of the computing power correspond to different time domain characteristics.

4. The method of claim 3, wherein, The type comprises at least one of the following: Periodic type; Semi-persistent type; Aperiodic type.

5. The method of claim 4, wherein, The type comprises a periodic type, and the first information further comprises a periodic value; and / or, the type comprises a semi-persistent type, and the first information further comprises a number of times of the computing power requested by the first device and / or a time interval between each two times of using the computing power.

6. The method of claim 4, wherein, The type comprises a semi-persistent type, and the method further comprises: The first device sends second information for requesting to activate the semi-persistent type of computing power; or, The first device receives third information for activating the semi-persistent type of computing power.

7. The method of claim 2, wherein, Different types of the computing power correspond to different quality of service (QoS); The QoS comprises at least one of the following parameters: Service type; Service priority; Packet delay budget; Data packet error rate; Average window; Maximum data burst volume; Allocation and retention priority; Packet data unit (PDU) set comprehensive processing information; Reflective QoS attribute; Guaranteed traffic bit rate; Maximum traffic bit rate; Maximum packet loss rate; Latency requirement.

8. The method of claim 2, wherein, The type comprises at least one of the following: Central processing unit (CPU) type; Data processing unit (DPU) type; Field programmable gate array (FPGA) type; Graphics processing unit (GPU) type; Neural processing unit (NPU) type; Tensor processing unit (TPU) type.

9. The method of claim 1, wherein, The method further comprises: The first device receives fourth information; The fourth information is used to instruct the first device to send an AI model; or, the fourth information comprises response information of the first information.

10. The method of claim 9, wherein, The fourth information is used to instruct the first device to send the AI model, and the method further comprises: The first device sends the AI model.

11. The method of claim 9, wherein, The fourth information comprises response information of the first information, and the method further comprises: The first device determines, based on the fourth information, that a second device has reserved periodic computing power; or, The first device determines, based on the fourth information, that a second device has reserved one or more times of computing power within a preset time; or, The first device determines, based on the fourth information, that a second device has reserved one time of computing power within a preset time.

12. The method of claim 9, wherein, The method further comprises: The first device sends or receives fifth information, wherein the fifth information comprises allocation information of a first resource, and the first resource is used for Transmitting data corresponding to the computing power.

13. The method of claim 12, wherein, The fourth information comprises the fifth information.

14. The method of claim 1, wherein, At least one of the second information, the third information, the fourth information, and the fifth information comprises a first identifier and / or a second identifier; The second information is transmitted by the first device and is used to request to activate the computing power of the semi-persistent type; the third information is received by the first device and is used to activate the computing power of the semi-persistent type; the fourth information is received by the first device and is used to indicate that the first device transmits an AI model, or the fourth information is received by the first device and includes response information of the first information; and the fifth information is received by the first device and includes allocation information of a first resource, the first resource being used to transmit data corresponding to the computing power. The first identifier is used to identify an AI model, and the second identifier is used to identify the computing power request corresponding to the first information.

15. The method of claim 12, wherein, The fifth information is carried by at least one of the following: Radio resource control information (RRC); a medium access control control element (MAC CE); control information.

16. The method of claim 15, wherein, The allocation information of the first resource includes at least one of the following: a time domain resource; a frequency domain resource; an offset value of the time domain resource relative to a reference system frame number; a period value of the time domain resource; a hybrid automatic repeat request (HARQ) process number; a modulation and coding scheme; a power control value; an antenna port; demodulation reference signal (DMRS) information; transmission configuration indication (TCI) state.

17. The method of claim 16, wherein, The allocation information of the first resource includes first part parameters and second part parameters, the first part parameters are carried by the RRC, and the second part parameters are carried by the MAC CE or the control information.

18. The method of any of claims 16-17, wherein, The type of the computing power is a periodic type or a semi-persistent type.

19. The method of claim 12, wherein, The first resource includes at least one of the following resources: a periodic physical uplink control channel (PUCCH); a configured grant physical uplink shared channel (CG PUSCH); a semi-persistent PUSCH; a physical downlink control channel (PDCCH); a physical downlink shared channel (PDSCH); a physical sidelink shared channel (PSSCH); a physical sidelink control channel (PSCCH).

20. The method of any of claims 1-19, wherein, The first information is carried by at least one of the following: a MAC CE; uplink control information; downlink control information; Sidelink control information; a physical random access channel (PRACH); a PUCCH; a PUSCH; a PDCCH; a PDSCH; a PSCCH; a PSSCH.

21. A method of communication, comprising: The method includes: The second device receives first information used to request computing power, the first information including a computing power range and / or a calculation amount of the computing power.

22. The method of claim 21, wherein, The type of the computing power is further included in the first information.

23. The method of claim 22, wherein, Different types of the computing power correspond to different time domain characteristics.

24. The method of claim 23, wherein, The type includes at least one of the following: a periodic type; a semi-persistent type; an aperiodic type.

25. The method of claim 24, wherein, When the type includes a periodic type, a period value is further included in the first information; and / or when the type includes a semi-persistent type, a number of times of using the computing power and / or a time interval between every two times of using the computing power are further included in the first information.

26. The method of claim 24, wherein, When the type includes a semi-persistent type, the method further includes: The second device receives second information used to request to activate the computing power of the semi-persistent type; or, The second device sends third information, and the third information is used to activate the computing power of the semi-persistent type.

27. The method of claim 22, wherein, Different types of the computing power correspond to different quality of service (QoS), and the QoS includes at least one of the following parameters: service type; service priority; packet delay budget; data packet error rate; average window; maximum data burst volume; allocation and retention priority; packet data unit (PDU) set comprehensive processing information; reflective QoS attribute; guaranteed traffic bit rate; maximum traffic bit rate; maximum packet loss rate; latency requirement.

28. The method of claim 22, wherein, The different types of the computing power include at least one of the following: central processing unit (CPU) type; data processing unit (DPU) type; field programmable gate array (FPGA) type; graphics processing unit (GPU) type; neural processing unit (NPU) type; tensor processing unit (TPU) type.

29. The method of claim 21, wherein, The method further includes: The second device sends fourth information; The fourth information is used to instruct the first device to send an AI model, or the fourth information includes response information of the first information.

30. The method of claim 29, wherein, The fourth information is used to instruct the first device to send the AI model, and the method further includes: The second device receives the AI model.

31. The method of claim 29, wherein, The method further includes: The second device receives or sends fifth information, and the fifth information includes allocation information of a first resource, and the first resource is used to transmit data corresponding to the computing power.

32. The method of claim 31, wherein, The fourth information includes the fifth information.

33. The method of claim 21, wherein, At least one of the second information, the third information, the fourth information, and the fifth information includes a first identifier and / or a second identifier; The second information is received by the second device and is used to request to activate the computing power of the semi-persistent type; the third information is sent by the second device and is used to activate the computing power of the semi-persistent type; the fourth information is sent by the second device and is used to instruct the first device to send an AI model, or the fourth information is sent by the second device and includes response information of the first information; and the fifth information is sent by the second device and includes allocation information of a first resource, and the first resource is used to transmit data corresponding to the computing power; The first identifier is used to identify an AI model, and the second identifier is used to identify computing power requested by the first information. The fifth information is carried by at least one of the following:

34. The method of claim 31, wherein, radio resource control (RRC) information; medium access control (MAC) control element (CE); control information. The allocation information of the first resource includes at least one of the following:

35. The method of claim 34, wherein, time domain resource; frequency domain resource; offset value of the time domain resource relative to a reference system frame number; period value of the time domain resource; hybrid automatic repeat request (HARQ) process number; modulation and coding scheme; power control value; antenna port; demodulation reference signal (DMRS) information. The allocation information of the first resource includes first part parameters and second part parameters, the first part parameters are carried by RRC, and the second part parameters are carried by MAC CE or control information.

36. The method of claim 34, wherein, The type of the computing power is a periodic type or a semi-persistent type.

37. The method of any of claims 35-36, wherein, The first resource includes at least one of the following resources:

38. The method of claim 31, wherein, periodic physical uplink control channel (PUCCH); ​ configured grant physical uplink shared channel, CG-PUSCH semi-persistent PUSCH physical downlink control channel, PDCCH physical downlink shared channel, PDSCH physical sidelink shared channel, PSSCH physical sidelink control channel, PSCCH.

39. The method of any of claims 21-38, wherein, The first information is carried by at least one of: a MAC CE uplink control information downlink control information sidelink control information a physical random access channel, PRACH a PUCCH a PUSCH a PDCCH a PDSCH a PSCCH a PSSCH.

40. A method of communication, comprising: The method comprises: a first device sending first information for requesting a computing power, the first information comprising a computing power range and / or a computing amount of the computing power; a second device receiving the first information.

41. A first device, comprising: comprise: a transceiver module configured to send first information for requesting a computing power, the first information comprising a computing power range and / or a computing amount of the computing power.

42. A second device, comprising: comprise: a transceiver module configured to receive first information for requesting a computing power, the first information comprising a computing power range and / or a computing amount of the computing power.

43. A first device, comprising: comprise: one or more processors wherein the processor is configured to perform the communication method of any one of claims 1-20.

44. A second device, comprising: comprise: one or more processors wherein the processor is configured to perform the communication method of any one of claims 21-39.

45. A communication system, characterized by comprise: a first device and a second device, wherein the first device is configured to implement the communication method of any one of claims 1-20, and the second device is configured to implement the communication method of any one of claims 21-39.

46. A storage medium, characterized by comprise: the storage medium stores instructions that, when executed on a communication device, cause the communication device to perform the communication method of any one of claims 1-20 or 21-39.

47. A program product, characterized by comprise: a computer program that, when executed on a communication device, causes the communication device to perform the communication method of any one of claims 1-20 or 21-39.

Images