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

Abstract

The present disclosure relates to a communication method, a device, a communication system, a storage medium, and a program product. The communication method comprises: a first device sending first information used for requesting computing power, the first information comprising model information of an artificial intelligence (AI) model. The present disclosure can improve efficiency.

Description

Communication method, device, communication system, storage medium and program product TECHNICAL FIELD

[0001] The present disclosure relates to the technical field of communication, and particularly relates to a communication method, device, communication system, storage medium and program product. BACKGROUND

[0002] In recent years, artificial intelligence (AI) technology has developed rapidly, and various methods or services based on AI have penetrated into various fields of life, including entertainment, communication, medical treatment, transportation, factory production, etc.

[0003] SUMMARY

[0004] Future AI technology includes computing power services, and how to share computing power is a problem being studied.

[0005] Embodiments of the present disclosure provide a communication method, device, communication system, storage medium and program product.

[0006] According to a first aspect of embodiments of the present disclosure, a communication method is provided, and the method comprises: a first device sending first information for requesting computing power, wherein the first information comprises model information of an artificial intelligence (AI) model.

[0007] According to a second aspect of embodiments of the present disclosure, a communication method is provided, and the method comprises: a second device receiving first information for requesting computing power, wherein the first information comprises model information of an artificial intelligence (AI) model.

[0008] According to a third aspect of embodiments of the present disclosure, a communication method is provided, and the method comprises: a first device sending first information for requesting computing power to a second device, wherein the first information comprises model information of an artificial intelligence (AI) model; and the second device receiving the first information.

[0009] According to a fourth aspect of embodiments of the present disclosure, a first device is provided, comprising: a transceiver module configured to send first information for requesting computing power, wherein the first information comprises model information of an artificial intelligence (AI) model.

[0010] According to a fifth aspect of embodiments of the present disclosure, a second device is provided, comprising: a transceiver module configured to receive first information for requesting computing power, wherein the first information comprises model information of an artificial intelligence (AI) model.

[0011] According to a sixth aspect of embodiments of the present disclosure, a first device is provided, comprising: one or more processors; and wherein the processor is configured to execute the communication method of the first aspect and any one of 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 improves efficiency by sending first information to request computing power, and the model information is included in the first information, so as to facilitate the second device to determine whether to accept the request of the first device. 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 flowchart of a communication method according to an embodiment of the present disclosure.

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

[0027] FIG. 4b is a flowchart 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 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, which includes: a first device sending first information for requesting computing power, wherein the first information includes model information of an artificial intelligence (AI) model.

[0035] In the above embodiments, the first information is sent to request computing power, and the model information is included in the first information, so that the second device can determine whether to accept the request of the first device, thereby improving efficiency.

[0036] In some embodiments in combination with the first aspect, in some embodiments, the model information of the AI model includes at least one of the following: a first identifier for identifying the request of the first device; a second identifier for identifying a logical channel or a logical channel group; a third identifier for identifying the AI model; 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 output data of the AI model; a form of input data of the AI model; a size of the AI model; and a data volume corresponding to the AI model.

[0037] In the above embodiments, the model information can include at least one of the above, so that the second device can accurately determine whether to provide computing power or how to provide computing power.

[0038] In some embodiments in combination with the first aspect, in some embodiments, the third identifier includes a model identifier of the AI model and / or a function identifier of an AI function corresponding to the AI model.

[0039] In some embodiments of the first aspect, in some embodiments, the third identifier comprises at least one of: a third identifier specific to the first device, different AI models deployed by the same first device having different third identifiers; a third identifier specific to a cell, different AI models deployed by at least one first device of the same cell having different third identifiers; a third identifier specific to an operator, different AI models deployed by at least one first device of the same operator having different third identifiers; a third identifier specific to the world, any two AI models having different third identifiers.

[0040] In the above embodiments, the third identifier can be at least one of the above, to flexibly cope with different situations and improve efficiency.

[0041] In some embodiments of the first aspect, in some embodiments, the first information further comprises a range of computing power required by the first device and / or a calculation amount.

[0042] In the above embodiments, the first information can further comprise a range of computing power required by the first device and / or a calculation amount, to more intuitively determine whether to provide computing power.

[0043] In some embodiments of the first aspect, in some embodiments, the method further comprises: receiving, by the first device, second information, the second information being used to instruct the first device to send the AI model; and sending, by the first device, the AI model.

[0044] In the above embodiments, if the second device does not deploy a corresponding AI model, the first device can be instructed to send the AI model, to achieve shared computing power.

[0045] In some embodiments of the first aspect, in some embodiments, the method further comprises: receiving, by the first device, third information, the third information comprising response information to the first information.

[0046] In the above embodiments, the first device can receive response information to the first information, to determine whether the second device accepts the request of the first device, to facilitate the first device to prepare for the next operation and improve efficiency.

[0047] In some embodiments of the first aspect, in some embodiments, the third information further comprises at least one of: a first identifier, the first identifier being used to identify the request of the first device; a second identifier, the second identifier being used to identify a logical channel or a logical channel group; and a third identifier, the third identifier being used to identify an AI model.

[0048] In the above embodiments, the third information can include the above identifier, so as to inform the first device of specific conditions of the computing power provided by the second device. For example, which request corresponds to the computing power provided, or which AI model corresponds to the computing power provided, or which logical channel or logical channel group corresponds to the service for which the computing power is provided.

[0049] In combination with some embodiments of the first aspect, in some embodiments, the method further includes: the first device sending or receiving fourth information, the fourth information being used for configuring a first resource, the first resource being used for transmitting data of the computing task corresponding to the computing power.

[0050] In the above embodiments, the first device can send or receive resource allocation information used for transmitting data, so that the data can be transmitted based on the resource allocation information.

[0051] In combination with some embodiments of the first aspect, in some embodiments, the computing power range and / or the computing amount are indicated in the following manners: indicating the use of the computing power required by the first device, and a first number of bits of the computing power range and / or the computing amount; or, indicating a second number of bits of the computing power range and / or the computing amount; the first number is less than or equal to the second number.

[0052] In the above embodiments, the computing power range and / or the computing amount are indicated in the above manners, so as to flexibly cope with different situations and provide communication efficiency.

[0053] In combination with some embodiments of the first aspect, in some embodiments, the first information is carried by at least one of the following: radio resource control information; a medium access control control element; uplink control information; downlink control information; 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.

[0054] 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.

[0055] The second aspect provides a communication method, which includes: a second device receiving first information used for requesting computing power, the first information including model information of an artificial intelligence AI model.

[0056] In some embodiments of the second aspect, in some embodiments, the model information of the AI model comprises at least one of: a first identifier for identifying the request; a second identifier for identifying a logical channel or a logical channel group; a third identifier for identifying an AI model; 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 output data of the AI model; a form of input data of the AI model; a size of the AI model; a data volume corresponding to the AI model.

[0057] In some embodiments of the second aspect, in some embodiments, the third identifier comprises a model identifier of the AI model and / or a function identifier of an AI function corresponding to the AI model.

[0058] In some embodiments of the second aspect, in some embodiments, the third identifier comprises at least one of: a third identifier specific to a first device, different AI models deployed by the same first device having different third identifiers; a third identifier specific to a cell, different AI models deployed by at least one first device in the same cell having different third identifiers; a third identifier specific to an operator, different AI models deployed by at least one first device of the same operator having different third identifiers; a third identifier specific to the world, any two AI models having different third identifiers.

[0059] In some embodiments of the second aspect, in some embodiments, the first information further comprises a range of computing power and / or a computing amount required by the first device.

[0060] In some embodiments of the second aspect, in some embodiments, the method further comprises: the second device sending second information, the second information being used to indicate sending the AI model; and the second device receiving the AI model.

[0061] In some embodiments of the second aspect, in some embodiments, the method further comprises: the second device sending third information, the third information comprising response information to the first information.

[0062] In some embodiments of the second aspect, in some embodiments, the third information further comprises at least one of: a first identifier for identifying the request of the first device; a second identifier for identifying a logical channel or a logical channel group; and a third identifier for identifying an AI model.

[0063] In some embodiments of the second aspect, in some embodiments, the method further includes: receiving or transmitting, by the second device, fourth information, the fourth information being used for configuring a first resource, the first resource being used for transmitting data of the computing task corresponding to the computing power.

[0064] In some embodiments of the second aspect, in some embodiments, the computing power range and / or the computing amount is indicated in the following manner: indicating a use of the computing power required by the first device, and a first number of bits of the computing power range and / or the computing amount; or, directly indicating a second number of bits of the computing power range and / or the computing amount; the first number is less than or equal to the second number.

[0065] In some embodiments of the second aspect, in some embodiments, the first information is carried by at least one of the following: radio resource control information; media access control control element; uplink control information; physical random access channel (PRACH); physical uplink control channel (PUCCH); physical uplink shared channel (PUSCH).

[0066] In a third aspect, a communication method is provided, the method including: transmitting, by a first device, first information for requesting computing power to a second device, the first information including model information of an artificial intelligence (AI) model; and receiving, by the second device, the first information.

[0067] In a fourth aspect, a first device is provided, including: a transceiver configured to transmit first information for requesting computing power, the first information including model information of an artificial intelligence (AI) model.

[0068] In some embodiments of the fourth aspect, in some embodiments, the model information of the AI model includes at least one of the following: a first identifier used to identify the request of the first device; a second identifier used to identify a logical channel or a logical channel group; a third identifier used to identify the AI model; 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 output data of the AI model; a form of input data of the AI model; a size of the AI model; and a data volume corresponding to the AI model.

[0069] In some embodiments of the fourth aspect, in some embodiments, the third identifier includes a model identifier of the AI model and / or a function identifier of an AI function corresponding to the AI model.

[0070] In some embodiments of the fourth aspect, in some embodiments, the third identifier comprises at least one of: a third identifier specific to the first device, different AI models deployed by the same first device having different third identifiers; a third identifier specific to a cell, different AI models deployed by at least one first device of the same cell having different third identifiers; a third identifier specific to an operator, different AI models deployed by at least one first device of the same operator having different third identifiers; a third identifier specific to the world, any two AI models having different third identifiers.

[0071] In some embodiments of the fourth aspect, in some embodiments, the first information further comprises a range of computing power and / or a quantity of computation required by the first device.

[0072] In some embodiments of the fourth aspect, in some embodiments, the transceiver is further configured to: receive second information, the second information being used to instruct the first device to send the AI model; and send, by the first device, the AI model.

[0073] In some embodiments of the fourth aspect, in some embodiments, the transceiver is further configured to: receive third information, the third information comprising response information to the first information.

[0074] In some embodiments of the fourth aspect, in some embodiments, the third information further comprises at least one of: a first identifier used to identify a request of the first device; a second identifier used to identify a logical channel or a logical channel group; and a third identifier used to identify an AI model.

[0075] In some embodiments of the fourth aspect, in some embodiments, the transceiver is further configured to send or receive, by the first device, fourth information, the fourth information being used to configure a first resource, the first resource being used to transmit data of a computing task corresponding to the computing power.

[0076] In some embodiments of the fourth aspect, in some embodiments, the range of computing power and / or the quantity of computation is indicated in the following manner: indicating a use of the computing power required by the first device, and a range of computing power and / or a quantity of computation of a first number of bits; or, indicating a range of computing power and / or a quantity of computation of a second number of bits, the first number being less than or equal to the second number.

[0077] In some embodiments of the fourth aspect, in some embodiments, the first information is carried by at least one of: radio resource control information; a medium access control control element; uplink control information; downlink control information; 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).

[0078] In a fifth aspect, a second device is provided, comprising: a transceiver configured to receive first information for requesting a computing power, wherein the first information comprises model information of an artificial intelligence (AI) model.

[0079] In some embodiments of the fifth aspect, in some embodiments, the model information of the AI model comprises at least one of: a first identifier for identifying the request; a second identifier for identifying a logical channel or a logical channel group; a third identifier for identifying the AI model; 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 output data of the AI model; a form of input data of the AI model; a size of the AI model; and a data volume corresponding to the AI model.

[0080] In some embodiments of the fifth aspect, in some embodiments, the third identifier comprises a model identifier of the AI model and / or a function identifier of an AI function corresponding to the AI model.

[0081] In some embodiments of the fifth aspect, in some embodiments, the third identifier comprises at least one of: a third identifier specific to a first device, wherein different AI models deployed by the same first device have different third identifiers; a third identifier specific to a cell, wherein different AI models deployed by at least one first device in the same cell have different third identifiers; a third identifier specific to an operator, wherein different AI models deployed by at least one first device of the same operator have different third identifiers; and a third identifier specific to the world, wherein any two AI models have different third identifiers.

[0082] In some embodiments of the fifth aspect, in some embodiments, the first information further comprises a range of computing power and / or a computation amount required by the first device.

[0083] In some embodiments combined with the fifth aspect, in some embodiments, the transceiver is further configured to: transmit second information, the second information being used to indicate that the AI model is transmitted; and the second device receives the AI model.

[0084] In some embodiments combined with the fifth aspect, in some embodiments, the transceiver is further configured to: transmit third information, the third information including response information to the first information.

[0085] In some embodiments combined with the fifth aspect, in some embodiments, the third information further includes at least one of: a first identifier, the first identifier being used to identify a request of the first device; a second identifier, the second identifier being used to identify a logical channel or a logical channel group; a third identifier, the third identifier being used to identify an AI model.

[0086] In some embodiments combined with the fifth aspect, in some embodiments, the transceiver is further configured to: receive or transmit fourth information, the fourth information being used to configure a first resource, the first resource being used to transmit data of a computing task corresponding to the computing power.

[0087] In some embodiments combined with the fifth aspect, in some embodiments, the computing power range and / or the computing amount is indicated in the following manner: indicating a use of the computing power required by the first device, and a first number of bits of the computing power range and / or the computing amount; or, directly indicating a second number of bits of the computing power range and / or the computing amount; the first number is less than or equal to the second number.

[0088] In some embodiments combined with the fifth aspect, in some embodiments, the first information is carried by at least one of: radio resource control information; a medium access control control element; uplink control information; a physical random access channel (PRACH); a physical uplink control channel (PUCCH); and a physical uplink shared channel (PUSCH).

[0089] In a sixth aspect, a first device is provided, including: one or more processors; wherein the processor is configured to execute the first aspect and any one of the communication methods in the first aspect.

[0090] In a seventh aspect, a second device is provided, including: one or more processors; wherein the processor is configured to execute the second aspect and any one of the communication methods in the second aspect.

[0091] In an eighth aspect, a communication system is provided, including a first device and a 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.

[0092] In a ninth aspect, a storage medium is provided, which stores instructions that, when executed on a communication device, cause the communication device to perform the communication method according to the first aspect and any one of the optional implementation manners of the first aspect or the second aspect and any one of the optional implementation manners of the second aspect.

[0093] In a tenth aspect, a program product is provided, which, when executed on a communication device, causes the communication device to perform the method described in the first aspect or the optional implementation manners of the second aspect.

[0094] In an eleventh aspect, a computer program is provided, which, when executed on a computer, causes the computer to perform the method described in the first aspect or the optional implementation manners of the second aspect.

[0095] In a twelfth aspect, a chip or chip system is provided, which includes processing circuitry configured to perform the method described in the first aspect or the optional implementation manners of the second aspect.

[0096] 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.

[0097] The embodiments of the present disclosure propose a communication method, a device, a communication system, a storage medium and a program product. In some embodiments, the communication method and the information processing method, and the terms such as communication method can be replaced with each other, the first device and the second device, and the terms such as communication apparatus and information processing apparatus can be replaced with each other, and the terms such as information processing system and communication system can be replaced with each other.

[0098] The embodiments of the present disclosure are not exhaustive, but only illustrate some embodiments, and are not specific limitations on the protection scope of the present disclosure. In the case of no contradiction, each step in an embodiment can be implemented as an independent embodiment, and the steps can be combined arbitrarily, for example, the scheme after removing some steps in an embodiment can also be implemented as an independent embodiment, and the order of the steps in an embodiment can be exchanged arbitrarily, in addition, the optional implementation manners in an embodiment can be combined arbitrarily; in addition, the embodiments can be combined arbitrarily, for example, the steps of different embodiments or part of the steps of different embodiments can be combined arbitrarily, an embodiment can be combined with the optional implementation manners of other embodiments.

[0099] In each of the disclosed embodiments, unless otherwise specified or in case of logical conflict, the terminology and / or descriptions of the embodiments are consistent and can be referenced by each other. Technical features in different embodiments can be combined to form new embodiments based on their inherent logical relationships.

[0100] The terminology used in the embodiments of this disclosure is for the purpose of describing particular embodiments only and is not intended to limit the scope of this disclosure.

[0101] In this embodiment of the disclosure, unless otherwise stated, elements expressed in the singular form, such as "a," "an," "the," "the," "the," "the," "the," "the," "this," etc., can mean "one and only one," or "one or more," "at least one," etc. For example, when using articles such as "a," "an," "the," etc. in translation, the noun following the article can be understood as either a singular expression or a plural expression.

[0102] In the embodiments of this disclosure, "multiple" refers to two or more.

[0103] In some embodiments, the terms “at least one of”, “one or more”, “a plurality of”, “multiple”, etc., may be used interchangeably.

[0104] In some embodiments, the notation "at least one of A and B", "A and / or B", "A in one case, B in another", "in response to one case A, in response to another case B", etc., may include the following technical solutions depending on the situation: in some embodiments, A (execute A regardless of B); in some embodiments, B (execute B regardless of A); in some embodiments, execution is selected from A and B (A and B are selectively executed); in some embodiments, A and B (both A and B are executed). The same applies when there are more branches such as A, B, C, etc.

[0105] In some embodiments, the notation "A or B" may include the following technical solutions, depending on the situation: in some embodiments, A (execution of A regardless of B); in some embodiments, B (execution of B regardless of A); in some embodiments, execution is selected from A and B (A and B are selectively executed). The same applies when there are more branches such as A, B, C, etc.

[0106] The prefix words "first", "second", etc. in the embodiments of the present disclosure are merely used to distinguish different description objects, and do not constitute limitation on the position, sequence, 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 redundant limitation because of the use of the prefix words. For example, the description objects are "fields", and the ordinal words before "fields" in "first field" and "second field" do not limit the position or sequence between "fields". "First" and "second" do not limit whether the "fields" modified thereby are in the same message, nor do they limit the sequence of "first field" and "second field". For another example, the description objects are "levels", and the ordinal words before "levels" in "first level" and "second level" do not limit the priority between "levels". For another example, the quantity of the description objects is not limited by the ordinal words, and can be one or more. For example, "first device", wherein the quantity of "devices" can be one or more. In addition, the objects modified by different prefix words can be the same or different. For example, the description objects are "devices", and "first device" and "second device" can be the same device or different devices, and their types can be the same or different. For another example, the description objects are "information", and "first information" and "second information" can be the same information or different information, and their contents can be the same or different.

[0107] In some embodiments, "including A", "containing A", "for indicating A", "carrying A" can be interpreted as directly carrying A, or indirectly indicating A.

[0108] In some embodiments, the terms "time / frequency", "time / frequency domain" and the like refer to the time domain and / or the frequency domain.

[0109] In some embodiments, the terms "in response to", "in response to determining", "in the case of", "when", "when", "if", "if" and the like can be replaced with each other.

[0110] 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.

[0111] In some embodiments, an apparatus or 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.

[0112] In some embodiments, a "network" can be interpreted as an apparatus (for example, an access network device, a core network device, and the like) included in the network.

[0113] 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 replaced with each other.

[0114] 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.

[0115] 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.

[0116] 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.

[0117] 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.

[0118] In some embodiments, the data, information, etc. can be obtained after obtaining the consent of the user.

[0119] In addition, each element, each row, or each column in the table of the embodiments of the present disclosure can be implemented as an independent embodiment, and any combination of any element, any row, or any column can also be implemented as an independent embodiment.

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

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

[0122] 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 thereto.

[0123] 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.

[0124] In some embodiments, computing power can refer to the ability of a node with computing capability 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) capability. 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 thereto.

[0125] FIG. 1b is a schematic diagram of an architecture of a communication system according to an embodiment of the present disclosure.

[0126] 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.

[0127] FIG. 1c is a schematic diagram of an architecture of a communication system according to an embodiment of the present disclosure.

[0128] 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.

[0129] 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.

[0130] In some embodiments, the network device 202 can include at least one of an access network device and a core network device.

[0131] 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.

[0132] 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.

[0133] 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.

[0134] 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).

[0135] 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.

[0136] 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 real 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.

[0137] 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).

[0138] FIG. 2a is an interaction diagram of a communication method according to an embodiment of the present disclosure. As shown in FIG. 2a, the present embodiment relates to a communication method for the communication system 100, the above-mentioned method comprising:

[0139] In step S2101, the first device 101 sends first information to the second device 102.

[0140] 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.

[0141] 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”, “codepoint”, “bit”, “data”, “program”, “chip”, and the like can be replaced with each other.

[0142] 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.

[0143] In some embodiments, the terms of “send”, “transmit”, “report”, “issue”, “transmit”, “bidirectional transmission”, “send and / or receive” can be replaced with each other.

[0144] In some embodiments, the first information is used to request computing capability. Different computing capabilities can correspond to different computing tasks.

[0145] In some embodiments, the computing power can refer to the ability of a node with computing capability 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.

[0146] In some embodiments, the computing power can include at least one of the following: 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); a tensor processing unit (TPU).

[0147] In some embodiments, the processing units of the computing power are different, which can also represent that the types of the computing power are different. That is, each type of computing power can correspond to a processing unit. Illustratively, the types of the computing power can include at least one of the following: CPU type; DPU type; FPGA type; GPU type; NPU type; 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 enumerate one by one.

[0148] In some embodiments, the types of the computing power can also be classified according to the time domain characteristics. For example, the computing power classified according to the time domain characteristics includes at least one of the following types: periodic type; semi-persistent type; aperiodic type.

[0149] In some embodiments, the type of the computing resource can also be classified according to a Quality of Service (QoS) classification. 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; a Packet Data Unit (PDU) Set Aggregate Handling Information; a Reflective QoS Attribute; a Guaranteed Flow Bit Rate (GFBR); a Maximum Flow Bit Rate (MFBR); a Maximum Packet Loss Rate; a latency requirement.

[0150] In some embodiments, 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 that do not have strict requirements on transmission rate or can tolerate fluctuations. 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 that have high requirements on network stability and transmission rate.

[0151] In some embodiments, 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.

[0152] In some embodiments, when the service type is the GBR type, the parameters of the Quality of Service can include the Averaging window and / or the Maximum Data Burst Volume.

[0153] In some embodiments, the Packet Error Rate can include an error rate set by a PDU.

[0154] In some embodiments, the GFBR can include an uplink GFBR and / or a downlink GFBR.

[0155] In some embodiments, the MFBR can comprise an uplink MFBR and / or a downlink MFBR.

[0156] In some embodiments, the maximum packet loss rate can comprise an uplink maximum packet loss rate and / or a downlink maximum packet loss rate.

[0157] In some embodiments, the parameter of the quality of service can further comprise a notification control.

[0158] In some embodiments, the model information of the AI model can be comprised in the first information. For example, the model information can be used by the second device to determine whether the corresponding AI model is deployed. For another example, different models require different sizes of computing power when used, and the second device can predict the size of the computing power required by the first device, or the range of the computing power, or the amount of calculation according to the model information of the AI model.

[0159] In some embodiments, the model information of the AI model comprises at least one of the following: a first identifier, the first identifier being used to identify the request of the first device; a second identifier, the second identifier being used to identify a logical channel or a logical channel group; a third identifier, the third identifier being used to identify the AI model; 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 output data of the AI model; a form of input data of the AI model; a size of the AI model; and a data volume corresponding to the AI model.

[0160] In some embodiments, the data volume corresponding to the AI model comprises at least one of a data volume corresponding to training of the AI model, an input data volume corresponding to derivation of the AI model, and an output data volume corresponding to derivation of the AI model.

[0161] Optionally, the model information can comprise a first identifier, the first identifier being used to identify the request of the first device. The first identifier can also be referred to as a request identifier, which is not limited in the present disclosure. The first device sends the first identifier in the first information, and if the second device does not accept the request of the first device, the first device can dynamically request computing power in the future and only needs to carry the first identifier. The second device receives the first identifier, and can determine other information about the request of the first device, such as other model information, etc.

[0162] Optionally, the model information can comprise a second identifier, the second identifier being used to identify a logical channel or a logical channel group. The logical channel or the logical channel group has a mapping relationship with a service of the terminal. Alternatively, the logical channel or the logical channel group has a mapping relationship with a quality of service. Based on the logical channel or the logical channel group, the second device can determine the service corresponding to the computing power requested by the first device based on the logical channel or the logical channel group, or the corresponding quality of service, or the computing power itself is defined as a service, and the logical channel or the logical channel group is used to distinguish the computing power service from other services. Thus, the second device can determine whether to provide the computing power for the first device or how to provide the computing power.

[0163] Optionally, the model information can comprise a third identifier, the third identifier being used to identify an AI model. The third identifier can be a model identifier of the AI model. And / or, the third identifier can be a function identifier of an AI functionality corresponding to the AI model.

[0164] 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 computing power ranges and / or different amounts of calculation. 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 features representing the computing power range and / or the amount of calculation, and the computing power range and / or the amount of calculation are not only determined by the model structure. Therefore, the size relationship in the above examples is only relative and is not limited.

[0165] 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 represented computing power range and / or the amount of calculation.

[0166] 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 represented computing power range and / or the amount of calculation.

[0167] Optionally, the model information can comprise a form of input data / output data of the AI model. For example, the more complex the form of input / output data, the greater the represented computing power range and / or the amount of calculation.

[0168] Optionally, the model information can include a data amount of AI model input / output. For example, the greater the data amount of input / output, the greater the range of computing power and / or the amount of calculation represented.

[0169] Optionally, the model information can include 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 greater the AI model, the greater the range of computing power and / or the amount of calculation represented.

[0170] Optionally, the model information can include a data amount of AI model training. For example, the greater the data amount of AI model training, the greater the range of computing power and / or the amount of calculation represented.

[0171] In some embodiments, the third identifier can include at least one of: a first device specific third identifier, different AI models deployed by the same first device having different third identifiers; a cell specific third identifier, different AI models deployed by at least one first device in the same cell having different third identifiers; an operator specific third identifier, different AI models deployed by at least one first device of the same operator having different third identifiers; and a global specific third identifier, any two AI models having different third identifiers.

[0172] Optionally, the third identifier can be a first device specific third identifier. The first device specific third identifier can be understood as the third identifier being relative to the first device, different AI models deployed by the same first device having different third identifiers. For example, the identifiers of AI models in the first device A are #0, #1, and #2, respectively. The identifiers of AI models in the first device B are #0, #1, and #2, respectively. That is, different AI models in the first device A and the first device B can have the same identifier.

[0173] Optionally, the third identifier can be a cell specific third identifier. The cell specific third identifier can be understood as the third identifier being relative to the cell, different AI models deployed by at least one first device in the same cell having different third identifiers. For example, the identifiers of AI models in the first device A in the same cell are #0 and #1, respectively, and the identifiers of AI models in the first device B are #2 and #3, respectively. That is, the first device A and the first device B in the same cell cannot have AI models with the same identifier.

[0174] Optionally, the third identifier can be an operator-specific third identifier. The operator-specific third identifier can be understood as the third identifier being relative to an operator, and the AI models deployed in at least one first device of the same operator have different third identifiers. For example, the identifiers of the AI models in the first device A of the same operator are #0, #1 respectively, and the identifiers of the AI models in the first device B of the same operator are #2, #3 respectively. That is, there cannot be AI models with the same identifier in the first device A and the first device B of the same operator.

[0175] Optionally, the third identifier can be a global-specific third identifier, and any two AI models have different third identifiers.

[0176] In some embodiments, the first information further includes a required computing power range and / or a required calculation amount of the first device.

[0177] In some embodiments, the disclosure takes the computing power range as an example, and the computing power range 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.

[0178] 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 can be interpreted as A obtained by setting, configuring, or indicating, or can be interpreted as certain A, arbitrary A, or first A, but is not limited thereto.

[0179] Optionally, the first device requested computing power can be represented based on a use corresponding to the first device requested computing power 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 inference, data processing, image processing, and the like, 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, DPU type, TPU type, and the like, which are not listed one by one.

[0180] Exemplarily, for the model training, the corresponding computing power range can be 0-300 million (M), and the quantization gradient can be 100M, that is, the computing power range corresponding to the model training 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 is model training, and then use the first number of bit positions to represent the computing power range in the plurality of computing power ranges. For example, the first number can be 2, the bit 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 0-100M of computing power. Correspondingly, the bit corresponding to 100M-200M can be 01, the bit corresponding to 200M-300M can be 10, and the bit 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.

[0181] Exemplarily, for the model derivation, the corresponding computing power range can be 0-30M, and the quantization gradient can be 10M, that is, the computing power range corresponding to the model derivation can include 0-10M, 100M-20M, 20M-30M, and greater than 30M. For example, the first number can be 2, the bit 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 0-10M of computing power. Correspondingly, the bit corresponding to 10M-20M can be 01, the bit corresponding to 20M-30M can be 10, and the bit 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.

[0182] Of course, the present disclosure is only exemplified by model training and model derivation, and is not limited thereto.

[0183] 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 bit positions. 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 bit positions are required, or the quantization gradient is greater.

[0184] 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.

[0185] In some embodiments, the first information is carried by at least one of the following: Radio Resource Control (RRC) including at least one of DL RRC, UL RRC and SL RRC; Medium Access Control Control Element (MAC CE) including at least one of Downlink (DL) MAC CE, uplink (UL) MAC CE and Sidelink (SL) MAC CE; Uplink Control Information (UCI); Downlink control information (DCI); Sidelink control information; Physical Random Access Channel (PRACH); Physical Uplink Control Channel (PUCCH); Physical Uplink Shared Channel (PUSCH); Physical Downlink Control Channel (PDCCH); Physical Downlink Shared Channel (PDSCH); Physical Side-link Control Channel (PSCCH); Physical Sidelink Shared Channel (PSSCH).

[0186] 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 RRC, MAC CE, UCI, PRACH, PUCCH, PUSCH, etc. Wherein, the RRC is the RRC of Uu interface. Wherein, Uu is the name of an interface. The Uu interface can refer to the wireless interface between the terminal and the network device. Wherein, the MAC CE can be an uplink MAC CE.

[0187] 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 RRC, MAC CE, DCI, PDCCH, PDSCH, etc. Wherein, the RRC is the RRC of Uu interface. Wherein, Uu is the name of an interface. The Uu interface can refer to the wireless interface between the terminal and the network device. Wherein, the MAC CE can be a downlink MAC CE.

[0188] Optionally, when the first device and the second device are both terminals, the first information can be carried by at least one of RRC, MAC CE, 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.

[0189] In some embodiments, the terms of “downlink control information (DCI)”, “downlink (DL) assignment”, “DL DCI”, “uplink (UL) grant”, “UL DCI”, etc. can be replaced with each other.

[0190] In some embodiments, the terms of “physical downlink shared channel (PDSCH)”, “DL data”, etc. can be replaced with each other, and the terms of “physical uplink shared channel (PUSCH)”, “UL data”, etc. can be replaced with each other.

[0191] In some embodiments, the terms of “radio”, “wireless”, “radio access network (RAN)”, “access network (AN)”, “RAN-based”, etc. can be replaced with each other.

[0192] In some embodiments, the first information name is not limited, which can be, for example, “request information” and the like.

[0193] Step S2102, the second device 102 sends the second information to the first device 101.

[0194] In some embodiments, the first device 101 receives the second information sent by the second device 102.

[0195] In some embodiments, the second information is used to instruct the first device to send the AI model.

[0196] In some embodiments, the second device can determine whether the corresponding AI model is deployed based on the model information. For example, whether the AI model corresponding to the model structure is deployed can be determined according to the model structure. Alternatively, whether the AI model corresponding to the third identifier is deployed can be determined according to the third identifier. The present disclosure does not enumerate all examples. If the corresponding AI model is not deployed in the second device, the second information can be sent to the first device to instruct the first device to send the AI model to the second device.

[0197] It can be understood that the second device can also send the second information to other devices, that is, the second device can request other devices to send the AI model.

[0198] In some embodiments, the name of the second information is not limited, which can be, for example, “indication information”.

[0199] In step S2103, the first device 101 sends the AI model to the second device 102.

[0200] 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 this is not limited, and the present disclosure does not enumerate all examples.

[0201] In step S2104, the second device 102 sends the third information to the first device 101.

[0202] In some embodiments, the first device 101 receives the third information sent by the second device 102.

[0203] In some embodiments, the third information includes response information to the first information. For example, the third information can indicate whether the second device accepts the request of the first device.

[0204] In some embodiments, the third information further includes at least one of the following: the first identifier, the first identifier being used to identify the request of the first device; the second identifier, the second identifier being used to identify the logical channel or the logical channel group; the third identifier, the third identifier being used to identify the AI model.

[0205] Optionally, the first 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. The second device can include the identifier of the request in the second information to identify which request is responded to. Correspondingly, the second identifier can also be included in the first information to identify the request. Only the second identifier can be carried to make the same request for computing power after the second device rejects the request of the first device.

[0206] Optionally, the third information can include the second identifier. For example, the first device can determine which service or services are accepted by the second device and provide computing power based on the second identifier. Or which service or services are rejected by the second device.

[0207] Optionally, the third information can include a third identifier. For example, the second device can send the third identifier corresponding to 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 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 third identifier corresponding to the started AI model. Correspondingly, the first information can also include the third identifier to indicate which AI model or models are requested.

[0208] In some embodiments, the name of the third information is not limited, which can be, for example, “feedback information”.

[0209] In step S2105, the first device 101 sends fourth information to the second device 102, or the second device 102 sends the fourth information to the first device 101.

[0210] In some embodiments, the second device 102 receives the fourth information sent by the first device 101. Or, the first device 101 receives the fourth information sent by the second device 102. For example, the first device is a terminal, and the second device is a network device, then the first device receives the fourth information sent by the second device. For another example, the first device is a network device, and the second device is a terminal, then the second device receives the fourth information sent by the first device. That is, whether the device sending the first information is a terminal or a network device, the network device sends the fourth information to the terminal, but it can be understood that this example is only exemplary and is not limited thereto. For another example, the first device and the second device are both terminals, which can be that the first device receives the fourth information sent by the second device, or the second device receives the fourth information sent by the first device.

[0211] In some embodiments, the fourth information is used to configure a first resource. 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 image corresponding to image processing, data corresponding to data processing, voice corresponding to online translation, data for AI model training, data for AI model derivation, and the like, which are not listed one by one but are not limited thereto. The data of the computing task corresponding to the computing power can also be referred to as data corresponding to the computing power. It can 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.

[0212] In some embodiments, the first device is a terminal and the second device is a network device. Alternatively, the first device is a network device and the second device is a terminal. The first resource allocation information can be an uplink transmission resource. When both the first device and the second device are terminals, the first resource allocation information can be a sidelink transmission resource.

[0213] The two dashed lines in step S2105 in FIG. 2a indicate that both are optional, i.e., the fourth information can be sent by the first device 101 to the second device 102. Alternatively, the fourth information can be sent by the second device 102 to the first device 101.

[0214] The communication method related to the embodiments of the present disclosure can include at least one of steps S2101-S2105. For example, step S2101 can be implemented as an independent embodiment, steps S2101-S2103 can be implemented as an independent embodiment, and steps S2101, S2102 and S2104 can be implemented as separate embodiments, but are not limited thereto.

[0215] In some embodiments, steps S2102-S2105 are optional, and one or more of these steps can be omitted or replaced in different embodiments.

[0216] In some embodiments, reference can be made to other optional implementations described before or after the description corresponding to FIG. 2a.

[0217] The present disclosure takes the first device as a terminal and the second device as a network device as an example to provide the following embodiments.

[0218] FIG. 2b is an interaction diagram of a communication method according to an embodiment of the present disclosure. As shown in FIG. 2b, the present disclosure relates to a communication method for a communication system 200, and the above method includes:

[0219] In step S2201, the terminal 201 sends first information to the network device 202.

[0220] Step S2201 can refer to the optional implementation of step S2101, and the present disclosure will not be repeated here.

[0221] In step S2202, the network device 202 sends second information to the terminal 201.

[0222] Step S2202 can refer to the optional implementation of step S2102, and the present disclosure will not be repeated here.

[0223] In step S2203, the terminal 201 sends an AI model to the network device 202.

[0224] Step S2203 can refer to the optional implementation of step S2103, and the disclosure will not elaborate here.

[0225] Step S2204, the network device 202 sends the third information to the terminal 201.

[0226] Step S2204 can refer to the optional implementation of step S2104, and the disclosure will not elaborate here.

[0227] Step S2205, the network device 202 sends the fourth information to the terminal 201.

[0228] Step S2205 can refer to the optional implementation of step S2105, and the disclosure will not elaborate here.

[0229] The communication method related to the embodiments of the disclosure can include at least one of steps S2201-S2205. For example, step S2201 can be implemented as an independent embodiment, steps S2201-S2203 can be implemented as an independent embodiment, steps S2201, S2202 and S2204 can be implemented as separate embodiments, but not limited thereto.

[0230] In some embodiments, steps S2202-S2205 are optional, and one or more of these steps can be omitted or replaced in different embodiments.

[0231] In some embodiments, other optional implementations described before or after the corresponding description of FIG. 2b can be referred to.

[0232] The disclosure takes the network device as the first device and the terminal as the second device as an example, and provides the following embodiments.

[0233] FIG. 2c is an interaction diagram of a communication method according to an embodiment of the disclosure. As shown in FIG. 2c, the embodiment of the disclosure relates to a communication method for a communication system 200, and the above method comprises:

[0234] Step S2301, the network device 202 sends the first information to the terminal 201.

[0235] Step S2301 can refer to the optional implementation of step S2101, and the disclosure will not elaborate here.

[0236] Step S2302, the terminal 201 sends the second information to the network device 202.

[0237] Step S2302 can refer to the optional implementation of step S2102, and the disclosure will not elaborate here.

[0238] At step S2303, the network device 202 sends the AI model to the terminal 201.

[0239] Step S2303 can refer to the optional implementation of step S2103, and the present disclosure will not be repeated here.

[0240] At step S2304, the terminal 201 sends the third information to the network device 202.

[0241] Step S2304 can refer to the optional implementation of step S2104, and the present disclosure will not be repeated here.

[0242] At step S2305, the network device 202 sends the fourth information to the terminal 201.

[0243] Step S2305 can refer to the optional implementation of step S2105, and the present disclosure will not be repeated here.

[0244] The communication method related to the embodiments 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-S2303 can be implemented as an independent embodiment, steps S2301, S2302 and S2304 can be implemented as separate embodiments, but not limited thereto.

[0245] In some embodiments, steps S2302-S2305 are optional, and one or more of these steps can be omitted or replaced in different embodiments.

[0246] In some embodiments, other optional implementations described before or after the corresponding description of FIG. 2c can be referred to.

[0247] The present disclosure takes the first device and the second device as terminals as an example, and provides the following embodiments.

[0248] FIG. 2d is an interaction schematic diagram of a communication method according to an embodiment of the present disclosure. As shown in FIG. 2d, the present disclosure relates to a communication method for a communication system 300, and the above method includes:

[0249] At step S2401, the terminal 301 sends the first information to the terminal 302.

[0250] Step S2401 can refer to the optional implementation of step S2101, and the present disclosure will not be repeated here.

[0251] At step S2402, the terminal 302 sends the second information to the terminal 301.

[0252] Step S2402 can refer to the optional implementation of step S2102, and the present disclosure will not be repeated here.

[0253] Step S2403, the terminal 301 sends the AI model to the terminal 302.

[0254] Step S2403 can refer to the optional implementation of step S2103, and the present disclosure will not be repeated here.

[0255] Step S2404, the terminal 302 sends the third information to the terminal 301.

[0256] Step S2404 can refer to the optional implementation of step S2104, and the present disclosure will not be repeated here.

[0257] Step S2405, the terminal 301 sends the fourth information to the terminal 302, or the terminal 302 sends the fourth information to the terminal 301.

[0258] The communication method related to the embodiments of the present disclosure can include at least one of steps S2401-S2405. For example, step S2401 can be implemented as an independent embodiment, steps S2401-S2403 can be implemented as an independent embodiment, steps S2401, S2402 and S2404 can be implemented as separate embodiments, but not limited thereto.

[0259] In some embodiments, steps S2402-S2405 are optional, and one or more of these steps can be omitted or replaced in different embodiments.

[0260] In some embodiments, other optional implementations described before or after the corresponding description of FIG. 2d can be referred to.

[0261] FIG. 3a is a flow diagram of a communication method according to an embodiment of the present disclosure. As shown in FIG. 3a, the embodiments of the present disclosure relate 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-mentioned method comprises:

[0262] Step S3101, sending first information.

[0263] The optional implementation of step S3101 can refer to the optional implementation of step S2101 of FIG. 2a and other related parts in the embodiments related to FIG. 2a, which will not be repeated here.

[0264] In some embodiments, the first device 101 sends the first information to the second device 102, but not limited thereto, and can also send the first information to other subjects.

[0265] In some embodiments, the terminal 201 sends the first information to the network device 202, but not limited thereto, and can also send the first information to other subjects.

[0266] 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.

[0267] 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.

[0268] Step S3102: Obtain the second information.

[0269] The optional implementation of step S3102 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 described herein.

[0270] In some embodiments, the first device 101 receives the second information sent by the second device 102, but is not limited thereto, and can also receive the second information sent by other subjects.

[0271] 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.

[0272] 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.

[0273] In some embodiments, the terminal 301 receives the second information sent by the terminal 302, but is not limited thereto, and can also receive the second information sent by other subjects.

[0274] In some embodiments, the first device 101 (or the terminal 201, or the network device 202, or the terminal 301) obtains the second information as specified by a protocol.

[0275] In some embodiments, the first device 101 (or the terminal 201, or the network device 202, or the terminal 301) obtains the second information from an upper layer.

[0276] In some embodiments, the first device 101 (or the terminal 201, or the network device 202, or the terminal 301) processes to obtain the second information.

[0277] In some embodiments, 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.

[0278] Step S3103: transmitting the AI model.

[0279] 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.

[0280] In some embodiments, the first device 101 transmits the AI model to the second device 102, but is not limited thereto, and can also transmit the AI model to other subjects.

[0281] In some embodiments, the terminal 201 transmits the AI model to the network device 202, but is not limited thereto, and can also transmit the AI model to other subjects.

[0282] In some embodiments, the network device 202 transmits the AI model to the terminal 201, but is not limited thereto, and can also transmit the AI model to other subjects.

[0283] In some embodiments, the terminal 301 transmits the AI model to the terminal 302, but is not limited thereto, and can also transmit the AI model to other subjects.

[0284] Step S3104: obtaining third information.

[0285] 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.

[0286] In some embodiments, the first device 101 receives the third information transmitted by the second device 102, but is not limited thereto, and can also receive the third information transmitted by other subjects.

[0287] In some embodiments, the terminal 201 receives the third information transmitted by the network device 202, but is not limited thereto, and can also receive the third information transmitted by other subjects.

[0288] In some embodiments, the network device 202 receives the third information transmitted by the terminal 201, but is not limited thereto, and can also receive the third information transmitted by other subjects.

[0289] In some embodiments, the terminal 301 receives the third information transmitted by the terminal 302, but is not limited thereto, and can also receive the third information transmitted by other subjects.

[0290] In some embodiments, the first device 101 (or the terminal 201, or the network device 202, or the terminal 301) obtains the third information specified by a protocol.

[0291] In some embodiments, the first device 101 (or the terminal 201, or the network device 202, or the terminal 301) obtains the third information from an upper layer.

[0292] In some embodiments, the first device 101 (or the terminal 201, or the network device 202, or the terminal 301) performs processing to obtain the third information.

[0293] In some embodiments, the step S3104 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.

[0294] In step S3105, the fourth information is sent or obtained.

[0295] The optional implementation of the step S3105 can refer to the optional implementation of the step S2105 in FIG. 2a and other associated parts in the embodiments involved in FIG. 2a, which will not be repeated here.

[0296] The communication method involved in the embodiments of the present disclosure can include at least one of the steps S3101-S3105. For example, the step S3101 can be implemented as an independent embodiment, the steps S3101-S3103 can be implemented as an independent embodiment, and the steps S3101, S3102 and S3104 can be implemented as separate embodiments, but are not limited thereto.

[0297] In some embodiments, the steps S3102-S3105 are optional, and one or more of the steps can be omitted or replaced in different embodiments.

[0298] In some embodiments, other optional implementations can be recorded before or after the description corresponding to FIG. 3a.

[0299] 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 the first device 101 (or the terminal 201, or the network device 202, or the terminal 301), and the above method includes:

[0300] In step S3201, the first information is sent.

[0301] The optional implementation of the step S3201 can refer to the optional implementation of the step S2101 in FIG. 2a and other associated parts in the embodiments involved in FIG. 2a, which will not be repeated here.

[0302] In some embodiments, the first device 101 sends the first information to the second device 102, but is not limited thereto, and can send the first information to other subjects.

[0303] In some embodiments, the terminal 201 sends the first information to the network device 202, but is not limited thereto, and can send the first information to other subjects.

[0304] In some embodiments, the network device 202 sends the first information to the terminal 201, but is not limited thereto, and can send the first information to other subjects.

[0305] In some embodiments, the terminal 301 sends the first information to the terminal 302, but is not limited thereto, and can send the first information to other subjects.

[0306] 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:

[0307] In step S4101, the first information is acquired.

[0308] 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.

[0309] In some embodiments, the second device 102 receives the first information sent by the first device 101, but is not limited thereto, and can receive the first information sent by other subjects.

[0310] In some embodiments, the network device 202 receives the first information sent by the terminal 201, but is not limited thereto, and can receive the first information sent by other subjects.

[0311] In some embodiments, the terminal 201 receives the first information sent by the network device 202, but is not limited thereto, and can receive the first information sent by other subjects.

[0312] In some embodiments, the terminal 302 receives the first information sent by the terminal 301, but is not limited thereto, and can receive the first information sent by other subjects.

[0313] 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.

[0314] In some embodiments, the second device 102 (or the network device 202, or the terminal 201, or the terminal 302) obtains the first information from an upper layer.

[0315] 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.

[0316] 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 above function is default or default.

[0317] Step S4102, sending the second information.

[0318] The optional implementation of the step S4102 can refer to the optional implementation of the step S2102 in FIG. 2a, and other associated parts in the embodiments involved in FIG. 2a, which will not be repeated here.

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

[0320] 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.

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

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

[0323] Step S4103, obtaining an AI model.

[0324] The optional implementation of the step S4103 can refer to the optional implementation of the step S2103 in FIG. 2a, and other associated parts in the embodiments involved in FIG. 2a, which will not be repeated here.

[0325] In some embodiments, the second device 102 receives the AI model sent by the first device 101, but is not limited thereto, and can also receive the AI model sent by other subjects.

[0326] 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.

[0327] 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.

[0328] 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.

[0329] 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.

[0330] 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).

[0331] 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.

[0332] In some embodiments, step S4103 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.

[0333] Step S4104, sending the third information.

[0334] 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.

[0335] In some embodiments, the second device 102 sends the third information to the first device 101, but is not limited thereto, and can also send the third information to other subjects.

[0336] In some embodiments, the network device 202 sends the third information to the terminal 201, but is not limited thereto, and can also send the third information to other subjects.

[0337] In some embodiments, the terminal 201 sends the third information to the network device 202, but is not limited thereto, and can also send the third information to other subjects.

[0338] In some embodiments, the terminal 302 sends the third information to the terminal 301, but is not limited thereto, and can also send the third information to other subjects.

[0339] Step S4105, acquiring or sending the fourth information.

[0340] 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 related to FIG. 2a, which will not be repeated here.

[0341] The communication method related to 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-S4103 can be implemented as an independent embodiment, steps S4101, S4102 and S4104 can be implemented as separate embodiments, but are not limited thereto.

[0342] In some embodiments, steps S4102-S4105 are optional, and one or more of these steps can be omitted or replaced in different embodiments.

[0343] In some embodiments, other optional implementations can be described before or after the description of FIG. 4a.

[0344] FIG. 4b is a flow chart of a communication method according to an embodiment of the present disclosure. As shown in FIG. 4b, the embodiments of the present disclosure relate to a communication method performed by the second device 102 (or the network device 202, or the terminal 201, or the terminal 302), and the above method includes:

[0345] Step S4201, obtaining first information.

[0346] The optional implementation of step S4201 can refer to the optional implementation of step S2101 in FIG. 2a and other associated parts in the embodiments related to FIG. 2a, which will not be repeated here.

[0347] 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.

[0348] 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.

[0349] 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.

[0350] 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.

[0351] 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 the protocol.

[0352] 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 upper layer(s).

[0353] 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.

[0354] In some embodiments, the 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.

[0355] 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 above method comprises:

[0356] In step S5101, the first device 101 sends first information to the second device 102.

[0357] 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 will not be repeated here.

[0358] In some embodiments, the above method can include the method of the above-mentioned embodiments of the communication system side, the first device (or terminal, or network device) side, the second device (or network device, or terminal) side, and the like, which will not be repeated here.

[0359] The present disclosure provides a communication method, which is as follows:

[0360] In some embodiments, the terminal sends the first information, and the first information includes model information.

[0361] In some embodiments, the model information includes at least one of: structure of the model, number of layers of the model, number of hidden nodes of each layer, number of parameters of each layer, form of output (dimension: such as rows and columns, real number including real part and imaginary part), form of input (dimension), ID of the model (the base station can uniquely identify the model based on the model ID, which can be UE specific, cell specific, operator specific, or global).

[0362] In some embodiments, the first information further includes a required computing amount and / or computing power range.

[0363] In some embodiments, the first information can further include a request identity (ID).

[0364] In some embodiments, the base station gives a response, and the response includes at least one of:

[0365] The response can indicate that the network side device can activate the model.

[0366] The response can include a model ID or a request ID or a functionality ID.

[0367] The response can indicate that the base station has reserved computing power.

[0368] Of course, reserving computing power also means that the network side can activate the model

[0369] In some embodiments, the response can also indicate that the network side device needs the terminal to provide the model, i.e., instructing the terminal to send the model to the network side device.

[0370] In some embodiments, the terminal transmits the model to the network side device (if the network side device does not indicate that the model is needed, this step is ignored).

[0371] In some embodiments, the network side device configures uplink resources to the terminal, and the uplink resources are used to upload input data for model inference.

[0372] In some embodiments, the computing amount / computing power range indication method includes at least one of:

[0373] 1) can first indicate the type of use of the amount of calculation / computing power: is used for data processing, model training or model inference; then indicate the range of the amount of calculation / computing power under the corresponding use, such as the quantization gradient and range of the amount of calculation / computing power under each use are different.

[0374] For example, model training:

[0375] Bit 00 corresponds to 0-100M;

[0376] Bit 01 corresponds to 100M-200M;

[0377] Bit 10 corresponds to 200M-300M;

[0378] Bit 11 corresponds to 300M-∞. Where ∞ represents positive infinity. 300M-∞ represents the computing power range greater than or equal to 300M.

[0379] For example, model inference:

[0380] Bit 00 corresponds to 0-10M;

[0381] Bit 01 corresponds to 10M-20M;

[0382] Bit 10 corresponds to 20M-30M;

[0383] Bit 11 corresponds to 30M-∞. 30M-∞ represents the computing power range greater than or equal to 30M.

[0384] 2) Directly indicate the range of the amount of calculation / computing power, which is equivalent to not needing to distinguish different uses and directly indicating. Then compared to first distinguishing the use, either the number of bits is more or the quantization gradient is greater.

[0385] In some embodiments, the first information can be sent based on RRC, MAC CE, UCI.

[0386] In some embodiments, the first information can also be referred to as computing power state information, that is, the computing power request is also one of the computing power states, such as when the computing power request, the computing power of the terminal is negative.

[0387] The embodiments of the present disclosure also propose a device for implementing any of the above methods, for example, a device is proposed, the above device includes units or modules to implement each step performed by the terminal in any of the above methods. For another example, another device is also proposed, which includes units or modules to implement each step performed by the network equipment (such as access network equipment, core network function node, core network equipment, etc.) in any of the above methods.

[0388] 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 any of the above methods or realize the functions of each unit or module 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 the 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 above 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.

[0389] 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), and the like. In another implementation, the processor can implement certain functions through a logical relationship of hardware circuits, and the logical relationship of the hardware circuits is fixed or can be reconfigured. For example, the processor is a hardware circuit implemented by an application-specific integrated circuit (ASIC) or a programmable logic device (PLD), such as an FPGA. In the reconfigurable hardware circuit, the processor loads a configuration document to implement the configuration of the hardware circuit. It can be understood that the processor loads instructions to implement the functions of the above part or all units or modules. In addition, it can also be a hardware circuit designed for artificial intelligence, which can be understood as an ASIC, such as a neural network processing unit (NPU), a tensor processing unit (TPU), a deep learning processing unit (DPU), and the like.

[0390] 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, and the first information includes model information of an artificial intelligence (AI) model.

[0391] In some embodiments, the model information of the AI model includes at least one of the following: a first identifier for identifying a request of the first device; a second identifier for identifying a logical channel or a logical channel group; a third identifier for identifying the AI model; 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 output data of the AI model; a form of input data of the AI model; a size of the AI model; and a data volume corresponding to the AI model.

[0392] In some embodiments, the third identifier includes a model identifier of the AI model and / or a function identifier of an AI function corresponding to the AI model.

[0393] In some embodiments, the third identifier comprises at least one of: a third identifier specific to the first device, different AI models deployed by the same first device having different third identifiers; a third identifier specific to a cell, different AI models deployed by at least one first device of the same cell having different third identifiers; a third identifier specific to an operator, different AI models deployed by at least one first device of the same operator having different third identifiers; a third identifier specific to the world, any two AI models having different third identifiers.

[0394] In some embodiments, the first information further comprises a range of computing power required by the first device and / or a computing amount.

[0395] In some embodiments, the transceiver 6101 is further configured to receive second information, the second information being used to instruct the first device to send the AI model; and the first device sends the AI model.

[0396] In some embodiments, the transceiver 6101 is further configured to receive third information, the third information comprising response information to the first information.

[0397] In some embodiments, the third information further comprises at least one of: a first identifier used to identify the request of the first device; a second identifier used to identify a logical channel or a logical channel group; and a third identifier used to identify the AI model.

[0398] In some embodiments, the transceiver 6101 is further configured to send or receive fourth information, the fourth information being used to configure a first resource, the first resource being used to transmit data of a computing task corresponding to the computing power.

[0399] In some embodiments, the range of computing power and / or the computing amount is indicated in the following manner: indicating a use of computing power required by the first device, and a range of computing power and / or a computing amount of a first number of bits; or, indicating a range of computing power and / or a computing amount of a second number of bits; the first number being less than or equal to the second number.

[0400] In some embodiments, the first information is carried by at least one of: radio resource control information; a medium access control control element; uplink control information; downlink control information; 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).

[0401] 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 computing power, and the first information includes model information of an artificial intelligence (AI) model.

[0402] In some embodiments, the model information of the AI model includes at least one of the following: a first identifier for identifying the request; a second identifier for identifying a logical channel or a logical channel group; a third identifier for identifying the AI model; 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 output data of the AI model; a form of input data of the AI model; a size of the AI model; and a data volume corresponding to the AI model.

[0403] In some embodiments, the third identifier includes a model identifier of the AI model and / or a function identifier of an AI function corresponding to the AI model.

[0404] In some embodiments, the third identifier includes at least one of the following: a third identifier specific to a first device, different AI models deployed by the same first device having different third identifiers; a third identifier specific to a cell, different AI models deployed by at least one first device in the same cell having different third identifiers; a third identifier specific to an operator, different AI models deployed by at least one first device of the same operator having different third identifiers; and a third identifier specific to the world, any two AI models having different third identifiers.

[0405] In some embodiments, the first information further includes a range of computing power required by the first device and / or a computing volume.

[0406] In some embodiments, the transceiver module 6201 is further configured to send second information, the second information being used to indicate sending of the AI model, and the second device receives the AI model.

[0407] In some embodiments, the transceiver module 6201 is further configured to send third information, the third information including response information to the first information.

[0408] In some embodiments, the third information further includes at least one of the following: a first identifier for identifying the request of the first device; a second identifier for identifying a logical channel or a logical channel group; and a third identifier for identifying the AI model.

[0409] In some embodiments, the transceiver module 6201 is further configured to receive or send fourth information, where the fourth information is used to configure the first resource, and the first resource is used to transmit data of the computing task corresponding to the computing power.

[0410] In some embodiments, the computing power range and / or the computing amount are indicated in the following manners: indicating the use of the computing power required by the first device, and the computing power range and / or the computing amount of the first number of bits; or, directly indicating the computing power range and / or the computing amount of the second number of bits; the first number is less than or equal to the second number.

[0411] In some embodiments, the first information is carried by at least one of the following: radio resource control information; media access control control element; uplink control information; physical random access channel (PRACH); physical uplink control channel (PUCCH); and physical uplink shared channel (PUSCH).

[0412] 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, or a processor supporting the implementation of the network device or the terminal of any of the above methods, and can also be a chip, a chip system, or a processor supporting the implementation of any of the above methods. Optionally, the network device can be an access network device, a core network device, etc. Optionally, the terminal can be a user equipment, etc. The communication device 7100 can be used to implement the methods described in the above method embodiments, and specific implementation can be referred to the descriptions in the above method embodiments.

[0413] As shown in FIG. 7a, the communication device 7100 includes one or more processors 7101. The processor 7101 can be a general-purpose processor or a special-purpose processor, etc., which can be 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 or a CU, etc.

[0414] In some embodiments, the communication device 7100 further includes one or more memories 7102 for storing instructions. Optionally, all or part of the memory 7102 can also be outside the communication device 7100.

[0415] 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 sending and / or receiving in the above methods, and the processor 7101 performs other steps.

[0416] In some embodiments, the transceiver can include a receiver and / or a transmitter, which can be separate or integrated together. Optionally, the terms transceiver, transceiving unit, transceiver, transceiving circuit, etc. can be replaced by each other, the terms transmitter, transmitting unit, transmitter, transmitting circuit, etc. can be replaced by each other, and the terms receiver, receiving unit, receiver, receiving circuit, etc. can be replaced by each other.

[0417] 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 instructions stored in the memory 7102 and send the instructions to the processor 7101.

[0418] 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, terminal device, intelligent terminal device, cellular phone, wireless device, handset, mobile unit, vehicle-mounted device, network device, cloud device, artificial intelligence device, etc.; (6) other, etc.

[0419] Figure 7b is a schematic diagram of the structure 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 structure of the chip 7200 can be as shown in Figure 7b, but is not limited thereto.

[0420] The chip 7200 includes one or more processors 7201, and the chip 7200 is configured to execute any of the above methods.

[0421] In some embodiments, the chip 7200 further includes one or more interface circuits 7202. Optionally, the interface circuit 7202 is connected with the memory 7203, and the interface circuit 7202 can be used to receive signals from the memory 7203 or other devices, and can be used to send signals to the memory 7203 or other devices. For example, the interface circuit 7202 can read instructions stored in the memory 7203 and send the instructions to the processor 7201.

[0422] In some embodiments, the interface circuit 7202 performs communication steps S2101 such as transmitting and / or receiving in the above-described methods, and the processor 7201 performs other steps.

[0423] In some embodiments, the terms interface circuit, interface, transceiver pin, transceiver, and the like can be replaced by each other.

[0424] 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.

[0425] The present disclosure further proposes a storage medium having instructions stored thereon, which, when executed on the communication device 7100, causes 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.

[0426] 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.

[0427] 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 in that, The method includes: The first device sends first information for requesting computing power, the first information including model information of an artificial intelligence (AI) model.

2. The method according to claim 1, characterized in that, The model information of the AI ​​model includes at least one of the following: A first identifier, used to identify the request from the first device; The second identifier is used to identify a logical channel or a group of logical channels; The third identifier is used to identify the AI ​​model; The structure of the AI ​​model; The number of layers in the AI ​​model; The number of hidden nodes in each layer of the AI ​​model; The number of parameters in each layer of the AI ​​model; The form in which the AI ​​model outputs data; The form of input data to the AI ​​model; The size of the AI ​​model; The amount of data corresponding to the AI ​​model.

3. The method according to claim 2, characterized in that, The third identifier includes the model identifier of the AI ​​model and / or the function identifier of the AI ​​function corresponding to the AI ​​model.

4. The method according to claim 3, characterized in that, The third identifier includes at least one of the following: The third identifier is specific to the first device level, and different AI models deployed on the same first device have different third identifiers; A cell-specific third identifier, where each AI model deployed on at least one first device in the same cell has a different third identifier; Operator-specific third identifiers: AI models deployed on at least one first device of the same operator have different third identifiers. A globally specific third identifier, where any two AI models have different third identifiers.

5. The method according to claim 1, characterized in that, The first information also includes the computing power range and / or computing volume required by the first device.

6. The method according to claim 1 or 5, characterized in that, The method further includes: The first device receives second information, which instructs the first device to send the AI ​​model; The first device sends the AI ​​model.

7. The method according to claim 1, characterized in that, The method further includes: The first device receives third information, which includes response information to the first information.

8. The method according to claim 7, characterized in that, The third information also includes at least one of the following: A first identifier, used to identify the request from the first device; The second identifier is used to identify a logical channel or a group of logical channels; The third identifier is used to identify the AI ​​model.

9. The method according to any one of claims 5-8, characterized in that, The method further includes: The first device sends or receives fourth information, which is used to configure the first resource, and the first resource is used to transmit data of the computing task corresponding to the computing power.

10. The method according to claim 5, characterized in that, The computing power range and / or computing load are indicated in the following manner: Indicates the intended use of the computing power required by the first device, and the computing power range and / or computational load of the first number of bits; or, Indicates the computing power range and / or computational load of the second number of bits; The first quantity is less than or equal to the second quantity.

11. The method according to any one of claims 1-10, characterized in that, The first information is carried by at least one of the following: Wireless resource control information; Media access control unit; Uplink control information; Downlink control information; Sidelink control information; Physical Random Access Channel (PRACH); Physical uplink control channel (PUCCH); Physical Uplink Shared Channel (PUSCH); Physical Downlink Control Channel (PDCCH); Physical Downlink Shared Channel (PDSCH); Physical side row control channel (PSCCH); Physical Side-Shared Channel (PSSCH).

12. A communication method, characterized in that, The method includes: The second device receives first information for requesting computing power, the first information including model information of an artificial intelligence (AI) model.

13. The method according to claim 12, characterized in that, The model information of the AI ​​model includes at least one of the following: A first identifier, used to identify the request; The second identifier is used to identify a logical channel or a group of logical channels; The third identifier is used to identify the AI ​​model; The structure of the AI ​​model; The number of layers in the AI ​​model; The number of hidden nodes in each layer of the AI ​​model; The number of parameters in each layer of the AI ​​model; The form in which the AI ​​model outputs data; The form of input data to the AI ​​model; The size of the AI ​​model; The amount of data corresponding to the AI ​​model.

14. The method according to claim 13, characterized in that, The third identifier includes the model identifier of the AI ​​model and / or the function identifier of the AI ​​function corresponding to the AI ​​model.

15. The method according to claim 14, characterized in that, The third identifier includes at least one of the following: The third identifier is specific to the first device level, and different AI models deployed on the same first device have different third identifiers; A cell-specific third identifier, where each AI model deployed on at least one first device in the same cell has a different third identifier; Operator-specific third identifiers: AI models deployed on at least one first device of the same operator have different third identifiers. A globally specific third identifier, where any two AI models have different third identifiers.

16. The method according to claim 12, characterized in that, The first information also includes the computing power range and / or computing volume required by the first device.

17. The method according to claim 12 or 16, characterized in that, The method further includes: The second device sends a second message, which instructs the sending of the AI ​​model; The second device receives the AI ​​model.

18. The method according to claim 12, characterized in that, The method further includes: The second device sends a third message, which includes a response to the first message.

19. The method according to claim 18, characterized in that, The third information also includes at least one of the following: A first identifier, wherein the first identifier is used to identify a request from a first device; The second identifier is used to identify a logical channel or a group of logical channels; The third identifier is used to identify the AI ​​model.

20. The method according to any one of claims 16-19, characterized in that, The method further includes: The second device receives or sends fourth information, which is used to configure the first resource, and the first resource is used to transmit data of the computing task corresponding to the computing power.

21. The method according to claim 16, characterized in that, The computing power range and / or computing load are indicated in the following manner: Indicates the intended use of the computing power required by the first device, and the computing power range and / or computational load of the first number of bits; or, Directly indicates the computing power range and / or computational load of the second number of bits; The first quantity is less than or equal to the second quantity.

22. The method according to any one of claims 12-21, characterized in that, The first information is carried by at least one of the following: Wireless resource control information; Media access control unit; Uplink control information; Physical Random Access Channel (PRACH); Physical uplink control channel (PUCCH); Physical uplink shared channel (PUSCH).

23. A communication method, characterized in that, The method includes: The first device sends first information to the second device to request computing power, the first information including model information of an artificial intelligence (AI) model; The second device receives the first information.

24. A first device, characterized in that, include: The transceiver module is used to send first information for requesting computing power, the first information including model information of an artificial intelligence (AI) model.

25. A second device, characterized in that, include: The transceiver module is used to receive first information for requesting computing power, the first information including model information of an artificial intelligence (AI) model.

26. A first device, characterized in that, include: One or more processors; The processor is used to execute the communication method according to any one of claims 1-11.

27. A second device, characterized in that, include: One or more processors; The processor is used to execute the communication method according to any one of claims 12-22.

28. A communication system, characterized in that, include: A first device and a second device, wherein the first device is configured to implement the communication method according to any one of claims 1-11, and the second device is configured to implement the communication method according to any one of claims 12-22.

29. A storage medium, characterized in that, include: The storage medium stores instructions that, when executed on a communication device, cause the communication device to perform the communication method as described in any one of claims 1-11 or 12-22.

30. A program product, characterized in that, include: A computer program, when executed by a communication device, causes the communication device to perform the communication method as described in any one of claims 1-11 or 12-22.

Images