Communication methods and apparatuses, communication device and system, storage medium, and program product

Abstract

The present disclosure relates to communication methods and apparatuses, a communication device and system, a storage medium, and a program product. A method comprises: receiving at least one of a first model identifier and first indication information, as well as a subset of model parameters, wherein the first model identifier indicates a first model existing in a first node, the first indication information indicates a first model structure, and the subset of model parameters comprises some model parameters in a model parameter set of a second model; and determining the second model on the basis of the first model indicated by the first model identifier or the first model structure indicated by the first indication information, and the subset of model parameters. The embodiments of the present disclosure can achieve model deployment on the basis of the transfer of some parameters of AI / ML models.

Description

Communication methods and apparatus, devices, systems, storage media and software products Technical Field

[0001] This disclosure relates to the field of wireless communication, and more particularly to a communication method, apparatus, device, system, storage medium, and program product. Background Technology

[0002] Artificial intelligence (AI) / machine learning (ML) models can be deployed in communication systems. These AI / ML models can be used for reasoning. Summary of the Invention

[0003] This disclosure provides a communication method and apparatus, communication equipment, communication system, storage medium, and program product.

[0004] According to a first aspect of the present disclosure, a communication method is provided. The method is executed by a first node. The method includes: receiving at least one of a first model identifier and first indication information, and a subset of model parameters, wherein the first model identifier indicates a first model already existing in the first node, the first indication information indicates a first model structure, and the subset of model parameters includes a portion of the model parameters in a set of model parameters of a second model; and determining a second model based on the first model indicated by the first model identifier or the first model structure indicated by the first indication information, and the subset of model parameters.

[0005] According to a second aspect of the present disclosure, a communication method is provided. The method is performed by a second node. The method includes: sending at least one of a first model identifier and first indication information, and a subset of model parameters, wherein the first model identifier indicates a first model already existing in the first node, the first indication information indicates a first model structure, and the subset of model parameters includes a portion of the model parameters from the model parameter set of the second model.

[0006] According to a third aspect of the present disclosure, a communication device is provided. The communication device is disposed at a first node. The device includes a transceiver module and a processing module. The transceiver module is configured to receive at least one of a first model identifier and first indication information, and a subset of model parameters, wherein the first model identifier indicates a first model already existing in the first node, the first indication information indicates a first model structure, and the subset of model parameters includes a portion of the model parameters in the model parameter set of a second model. The processing module is configured to determine a second model based on the first model indicated by the first model identifier or the first model structure indicated by the first indication information, and the subset of model parameters.

[0007] According to a fourth aspect of the present disclosure, a communication device is provided. The communication device is disposed at a second node. The device includes a transceiver module. The transceiver module is configured to: transmit at least one of a first model identifier and first indication information, and a subset of model parameters, wherein the first model identifier indicates a first model already existing in the first node, the first indication information indicates a first model structure, and the subset of model parameters includes a portion of the model parameters from the model parameter set of a second model.

[0008] According to a fifth aspect of the present disclosure, a communication device is provided. The communication device includes: one or more processors and a memory storing instructions. When executed by the communication device, the instructions cause the communication device to implement the communication method as described in the first or second aspect.

[0009] According to a sixth aspect of this disclosure, a communication system is provided. The communication system includes a first node and a second node. The first node is configured to perform the communication method as described in the first aspect. The second node is configured to perform the communication method as described in the second aspect.

[0010] According to a seventh aspect of the present disclosure, a storage medium is provided. The storage medium stores instructions. When executed on a communication device, the instructions cause the communication device to perform a communication method as described in the first or second aspect.

[0011] According to an eighth aspect of the present disclosure, a program product is provided. When executed by a communication device, the program product causes the communication device to perform the communication method as described in the first or second aspect.

[0012] According to a ninth aspect of the present disclosure, a computer program is provided. When the computer program is run on a computer, it causes the computer to perform the communication method as described in the first or second aspect.

[0013] According to a tenth aspect of this disclosure, a chip or chip system is provided. The chip or chip system includes processing circuitry. The processing circuitry is configured to perform the communication method as described in the first or second aspect.

[0014] According to embodiments of this disclosure, the deployment of an AI / ML model can be achieved by passing some parameters of the AI / ML model.

[0015] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and do not constitute a limitation on the embodiments of this disclosure. Attached Figure Description

[0016] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and, together with the description, serve to explain the principles of the embodiments of the invention.

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

[0018] Figure 2 is an interactive schematic diagram of the communication method provided according to an embodiment of the present disclosure.

[0019] Figure 3 is a schematic diagram of the architecture of a convolutional neural network provided according to an embodiment of the present disclosure.

[0020] Figure 4 is an interactive schematic diagram of the communication method provided according to an embodiment of the present disclosure.

[0021] Figure 5 is a schematic diagram of the structure of a communication device provided according to an embodiment of the present disclosure.

[0022] Figure 6A is a schematic diagram of the structure of a communication device provided according to an embodiment of the present disclosure.

[0023] Figure 6B is a schematic diagram of the structure of a chip provided according to an embodiment of the present disclosure. Detailed Implementation

[0024] This disclosure provides a communication method and apparatus, a communication device, a communication system, a storage medium, and a program product.

[0025] In a first aspect, embodiments of this disclosure provide a communication method. The method is executed by a first node. The method includes: receiving at least one of a first model identifier and first indication information, and a subset of model parameters, wherein the first model identifier indicates a first model already existing in the first node, the first indication information indicates a first model structure, and the subset of model parameters includes a portion of the model parameters in the model parameter set of a second model; and determining a second model based on the first model indicated by the first model identifier or the first model structure indicated by the first indication information, and the subset of model parameters.

[0026] According to this embodiment, the first node can receive a subset of model parameters, and at least one of a first model identifier and first indication information. Based on the subset of model parameters and either the first model identifier or the first indication information, the first node can determine the second model. Thus, this embodiment can achieve the transmission of some model parameters of the second model and determine the second model based on the transmitted partial model parameters. In this case, the first node only needs some model parameters of the second model to generate the second model, reducing the overhead of transmission and device resources for model sending / transmission and improving system efficiency.

[0027] In conjunction with some embodiments of the first aspect, in some embodiments, the above method may further include: receiving at least one of second identification information and second model identifier, wherein the second indication information indicates a subset of model parameters, and the second model identifier is assigned by the second node.

[0028] In conjunction with some embodiments of the first aspect, in some embodiments, the above method may further include: determining a third model identifier based on at least one of a first model identifier, a first indication information, a second indication information, and a second model identifier, wherein the third model identifier indicates a second model, the second indication information indicates a subset of model parameters, and the second model identifier is assigned by a second node.

[0029] In conjunction with some embodiments of the first aspect, in some embodiments, the operation of determining a third model identifier based on at least one of a first model identifier, a first instruction information, a second instruction information, and a second model identifier may include one of the following: determining the first model identifier as the third model identifier; determining the third model identifier based on the first instruction information and the second instruction information; determining the third model identifier based on the second instruction information; and determining the second model identifier as the third model identifier.

[0030] According to this embodiment, the first node can determine the third model identifier of the second model using different information. This enhances the flexibility of indicating the second model.

[0031] In conjunction with some embodiments of the first aspect, in some embodiments, the operation of determining the second model based on the first model indicated by the first model identifier or the first model structure indicated by the first indication information and the subset of model parameters may include: generating the second model based on the subset of model parameters and the first model structure indicated by the first indication information.

[0032] In conjunction with some embodiments of the first aspect, in some embodiments, the operation of generating a second model based on a subset of model parameters and a first model structure indicated by first indication information may include: applying model parameters from the subset of model parameters to the first model structure; and setting model parameters in the first model structure other than the subset of model parameters to 0 to obtain the second model.

[0033] According to this embodiment, the first node can generate a second model based on a subset of model parameters and a first model structure indicated by first indication information. After determining the first model structure adopted by the second model based on the first indication information, the model parameters from the subset of model parameters can be applied at the corresponding positions in the first model structure. In this way, the second model can be generated by utilizing a known model structure and applying a subset of model parameters.

[0034] In conjunction with some embodiments of the first aspect, in some embodiments, the operation of determining the second model based on the first model indicated by the first model identifier or the first model structure indicated by the first indication information and the subset of model parameters may include: generating the second model based on the subset of model parameters and the first model structure indicated by the first indication information when the first node receives the first indication information and the subset of model parameters but does not receive the first model identifier.

[0035] In conjunction with some embodiments of the first aspect, in some embodiments, the operation of determining the second model based on the first model indicated by the first model identifier or the first model structure indicated by the first indication information and the subset of model parameters may include: generating the second model based on the subset of model parameters and the first model indicated by the first model identifier.

[0036] According to this embodiment, the first node can generate a second model based on a subset of model parameters and a first model indicated by a first model identifier. After determining the first model used in the second model based on the first model identifier, the model parameter from the subset of model parameters can be applied at the corresponding position in the first model. In this way, the second model can be generated by utilizing the existing model in the first node and applying the subset of model parameters.

[0037] In conjunction with some embodiments of the first aspect, in some embodiments, the operation of generating a second model based on a subset of model parameters and a first model indicated by a first model identifier may include: replacing the model parameters in the first model corresponding to the subset of model parameters with model parameters in the subset of model parameters to obtain the second model.

[0038] In conjunction with some embodiments of the first aspect, in some embodiments, the second model is indicated by a third model identifier, which may be different from the first model identifier.

[0039] In conjunction with some embodiments of the first aspect, in some embodiments, the operation of determining the second model based on the first model indicated by the first model identifier or the first model structure indicated by the first indication information and the subset of model parameters may include: generating the second model based on the subset of model parameters and the first model indicated by the first model identifier when the first node receives the first model identifier and the first model identifier is different from the third model identifier indicating the second model.

[0040] In conjunction with some embodiments of the first aspect, in some embodiments, the second model is indicated by a third model identifier, which may be the same as the first model identifier.

[0041] In conjunction with some embodiments of the first aspect, in some embodiments, the operation of determining the second model based on the first model indicated by the first model identifier or the first model structure indicated by the first indication information and the subset of model parameters may include: generating the second model based on the subset of model parameters and the first model indicated by the first model identifier when the first node receives the first model identifier and the first model identifier is the same as the third model identifier indicating the second model.

[0042] In conjunction with some embodiments of the first aspect, in some embodiments, the above method may further include: receiving third indication information, wherein the third indication information indicates the determination method of the second model.

[0043] In conjunction with some embodiments of the first aspect, in some embodiments, the above method may further include: sending fourth indication information, wherein the fourth indication information indicates at least one of the following: the first node supports the transmission of a subset of model parameters; the determination method of the second model supported by the first node.

[0044] In conjunction with some embodiments of the first aspect, in some embodiments, the method of determining the second model may include at least one of the following: generating the second model based on a subset of model parameters and a first model structure indicated by first indication information; generating the second model based on a subset of model parameters and a first model identifier indicated by a first model.

[0045] In a second aspect, embodiments of this disclosure provide a communication method. This method is executed by a second node. The method includes: sending at least one of a first model identifier and first indication information, and a subset of model parameters, wherein the first model identifier indicates a first model already existing in the first node, the first indication information indicates a first model structure, and the subset of model parameters includes a portion of the model parameters from the model parameter set of the second model.

[0046] According to this embodiment, the second node can send a subset of model parameters, and at least one of a first model identifier and first indication information, to the first node. Based on the subset of model parameters and either the first model identifier or the first indication information, the first node can determine the second model. Thus, this embodiment can achieve the transmission of partial model parameters of the second model and the determination of the second model based on the transmitted partial model parameters. In this case, the second node only needs to send partial model parameters of the second model to generate the second model on the first node, reducing the overhead of transmission and device resources for model sending / transmission and improving system efficiency.

[0047] In conjunction with some embodiments of the second aspect, in some embodiments, the above method may further include: sending at least one of a second identification information and a second model identifier, wherein the second indication information indicates a subset of model parameters, and the second model identifier is assigned by the second node.

[0048] In conjunction with some embodiments of the second aspect, in some embodiments, the above method may further include: sending third indication information, wherein the third indication information indicates the determination method of the second model.

[0049] In conjunction with some embodiments of the second aspect, in some embodiments, the above method may further include: receiving fourth indication information, wherein the fourth indication information indicates at least one of the following: the first node supports the transmission of a subset of model parameters; the determination method of the second model supported by the first node.

[0050] In conjunction with some embodiments of the second aspect, in some embodiments, the determination of the second model includes at least one of the following: generating the second model based on a subset of model parameters and a first model structure indicated by first indication information; generating the second model based on a subset of model parameters and a first model identifier indicated by a first model.

[0051] In conjunction with some embodiments of the second aspect, in some embodiments, the operation of generating a second model based on a subset of model parameters and a first model structure indicated by first indication information may include: applying model parameters from the subset of model parameters to the first model structure; and setting model parameters in the first model structure other than the subset of model parameters to 0 to obtain the second model.

[0052] In conjunction with some embodiments of the second aspect, in some embodiments, the operation of generating a second model based on a subset of model parameters and a first model indicated by a first model identifier may include: replacing the model parameters in the first model corresponding to the subset of model parameters with model parameters in the subset of model parameters to obtain the second model.

[0053] In a third aspect, embodiments of this disclosure provide a communication device. This communication device is disposed at a first node. The device includes a transceiver module and a processing module. The transceiver module is configured to receive at least one of a first model identifier and first indication information, and a subset of model parameters, wherein the first model identifier indicates a first model already existing in the first node, the first indication information indicates a first model structure, and the subset of model parameters includes a portion of the model parameters in the model parameter set of a second model. The processing module is configured to determine a second model based on the first model indicated by the first model identifier or the first model structure indicated by the first indication information, and the subset of model parameters.

[0054] In conjunction with some embodiments of the third aspect, in some embodiments, the transceiver module may also be configured to: receive at least one of a second identification information and a second model identifier, wherein the second indication information indicates a subset of model parameters, and the second model identifier is assigned by the second node.

[0055] In conjunction with some embodiments of the third aspect, in some embodiments, the processing module may also be configured to: determine a third model identifier based on at least one of a first model identifier, a first indication information, a second indication information, and a second model identifier, wherein the third model identifier indicates a second model, the second indication information indicates a subset of model parameters, and the second model identifier is assigned by a second node.

[0056] In conjunction with some embodiments of the third aspect, in some embodiments, the processing module may be configured to perform one of the following: determining a first model identifier as a third model identifier; determining a third model identifier based on first instruction information and second instruction information; determining a third model identifier based on second instruction information; and determining a second model identifier as a third model identifier.

[0057] In conjunction with some embodiments of the third aspect, in some embodiments, the processing module can be configured to generate a second model based on a subset of model parameters and a first model structure indicated by first indication information.

[0058] In conjunction with some embodiments of the third aspect, in some embodiments, the processing module may be configured to: apply model parameters from a subset of model parameters to a first model structure; and set model parameters in the first model structure other than the subset of model parameters to 0 to obtain a second model.

[0059] In conjunction with some embodiments of the third aspect, in some embodiments, the processing module can be configured to: generate a second model based on the first model structure indicated by the model parameter subset and the first indication information when the first node receives the first indication information and the subset of model parameters, but does not receive the first model identifier.

[0060] In conjunction with some embodiments of the third aspect, in some embodiments, the processing module may be configured to generate a second model based on a subset of model parameters and a first model indicated by a first model identifier.

[0061] In conjunction with some embodiments of the third aspect, in some embodiments, the processing module can be configured to: replace the model parameters in the first model corresponding to the subset of model parameters with the model parameters in the subset of model parameters to obtain the second model.

[0062] In conjunction with some embodiments of the third aspect, in some embodiments, the second model is indicated by a third model identifier, and the third model identifier may be different from the first model identifier.

[0063] In conjunction with some embodiments of the third aspect, in some embodiments, the processing module can be configured to: generate a second model based on a subset of model parameters and the first model indicated by the first model identifier when the first node receives a first model identifier and the first model identifier is different from a third model identifier indicating a second model.

[0064] In conjunction with some embodiments of the third aspect, in some embodiments, the second model is indicated by a third model identifier, and the third model identifier may be the same as the first model identifier.

[0065] In conjunction with some embodiments of the third aspect, in some embodiments, the processing module can be configured to: generate a second model based on a subset of model parameters and the first model indicated by the first model identifier when the first node receives a first model identifier and the first model identifier is the same as a third model identifier indicating a second model.

[0066] In conjunction with some embodiments of the third aspect, in some embodiments, the transceiver module may also be configured to: receive third indication information, wherein the third indication information indicates the determination method of the second model.

[0067] In conjunction with some embodiments of the third aspect, in some embodiments, the transceiver module may also be configured to: send fourth indication information, wherein the fourth indication information indicates at least one of the following: the first node supports the transmission of a subset of model parameters; the determination method of the second model supported by the first node.

[0068] In conjunction with some embodiments of the third aspect, in some embodiments, the method of determining the second model may include at least one of the following: generating the second model based on a subset of model parameters and a first model structure indicated by a first indication information; generating the second model based on a subset of model parameters and a first model identifier indicated by a first model.

[0069] In a fourth aspect, embodiments of this disclosure provide a communication device. This communication device is disposed at a second node. The device includes a transceiver module. The transceiver module is configured to: transmit at least one of a first model identifier and first indication information, and a subset of model parameters, wherein the first model identifier indicates a first model already existing in the first node, the first indication information indicates a first model structure, and the subset of model parameters includes a portion of the model parameters from the model parameter set of the second model.

[0070] In conjunction with some embodiments of the fourth aspect, in some embodiments, the transceiver module may also be configured to: send at least one of a second identification information and a second model identifier, wherein the second identification information indicates a subset of model parameters, and the second model identifier is assigned by the second node.

[0071] In conjunction with some embodiments of the fourth aspect, in some embodiments, the transceiver module may also be configured to: send third indication information, wherein the third indication information indicates the determination method of the second model.

[0072] In conjunction with some embodiments of the fourth aspect, in some embodiments, the transceiver module may also be configured to: receive fourth indication information, wherein the fourth indication information indicates at least one of the following: the first node supports the transmission of a subset of model parameters; the determination method of the second model supported by the first node.

[0073] In conjunction with some embodiments of the fourth aspect, in some embodiments, the determination of the second model includes at least one of the following: generating the second model based on a subset of model parameters and a first model structure indicated by a first indication information; generating the second model based on a subset of model parameters and a first model identifier indicated by a first model.

[0074] In conjunction with some embodiments of the fourth aspect, in some embodiments, the operation of generating a second model based on a subset of model parameters and a first model structure indicated by first indication information may include: applying model parameters from the subset of model parameters to the first model structure; and setting model parameters in the first model structure other than the subset of model parameters to 0 to obtain the second model.

[0075] In conjunction with some embodiments of the fourth aspect, in some embodiments, the operation of generating a second model based on a subset of model parameters and a first model indicated by a first model identifier may include: replacing the model parameters in the first model corresponding to the subset of model parameters with model parameters in the subset of model parameters to obtain the second model.

[0076] In a fifth aspect, embodiments of this disclosure provide a communication device. The communication device includes one or more processors and a memory storing instructions. When executed by the communication device, the instructions cause the communication device to implement the communication method as described in any of the first aspect, the second aspect, and their possible embodiments.

[0077] In a sixth aspect, embodiments of this disclosure provide a communication system. The communication system includes a first node and a second node. The first node is configured to perform the communication method as described in any of the first aspect and its possible embodiments. The second node is configured to perform the communication method as described in any of the second aspect and its possible embodiments.

[0078] In a seventh aspect, embodiments of this disclosure provide a storage medium storing instructions. When executed on a communication device, the instructions cause the communication device to perform the communication method as described in any of the first, second, and possible embodiments thereof.

[0079] In an eighth aspect, embodiments of this disclosure provide a program product. When executed by a communication device, the program product causes the communication device to perform the communication method as described in any of the first aspect, the second aspect, and their possible embodiments.

[0080] In a ninth aspect, embodiments of this disclosure provide a computer program. When this computer program is run on a computer, it causes the computer to perform the communication methods described in any of the first, second, and possible implementations thereof.

[0081] In a tenth aspect, embodiments of this disclosure provide a chip or chip system. The chip or chip system includes processing circuitry. The processing circuitry is configured to perform the communication methods described in any of the first, second, and possible embodiments thereof.

[0082] It is understood that the aforementioned communication devices, communication equipment, communication systems, storage media, program products, computer programs, chips, and chip systems are all used to execute the methods provided in the embodiments of this disclosure. Therefore, the beneficial effects they can achieve can be referred to the beneficial effects in the corresponding methods, and will not be repeated here.

[0083] This disclosure provides a communication method and apparatus, a communication device, a communication system, a storage medium, and a program product. In some embodiments, terms such as communication method, information processing method, and information transmission method can be used interchangeably; terms such as communication device, communication device, node, terminal, network device, network function, and network entity can be used interchangeably; and terms such as communication system and information processing system can be used interchangeably.

[0084] This disclosure is not exhaustive, but merely illustrative of some embodiments, and is not intended to limit the scope of protection of this disclosure. Unless otherwise specified, each step in a particular embodiment can be implemented as an independent embodiment, and the steps can be arbitrarily combined. For example, a solution after removing some steps in a particular embodiment can also be implemented as an independent embodiment, and the order of the steps in a particular embodiment can be arbitrarily interchanged. Furthermore, the optional implementation methods in a particular embodiment can be arbitrarily combined; moreover, the embodiments can be arbitrarily combined, for example, some or all steps of different embodiments can be arbitrarily combined, and a particular embodiment can be arbitrarily combined with the optional implementation methods of other embodiments.

[0085] In the embodiments disclosed herein, unless otherwise specified or in case of logical conflict, the terminology and / or descriptions of the various 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.

[0086] 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.

[0087] In the embodiments of this disclosure, unless otherwise stated, elements expressed in the singular form, such as “a,” “one,” “a kind,” “the,” “the,” “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 articles such as “a,” “an,” and “the” are used in translation, the noun following the article can be understood as either a singular or a plural expression.

[0088] In the embodiments of this disclosure, "a plurality of" means two or more.

[0089] In some embodiments, terms such as “at least one (at least one, at least one item, at least one)” and “one or more” may be used interchangeably.

[0090] 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.

[0091] 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.

[0092] The prefixes "first," "second," etc., used in the embodiments of this disclosure are merely for distinguishing different descriptive objects and do not impose restrictions on the position, order, priority, quantity, or content of the descriptive objects. The description of the descriptive objects is found in the claims or the context of the embodiments, and the use of prefixes should not constitute unnecessary restrictions. For example, if the descriptive object is a "field," the ordinal numbers preceding "field" in "first field" and "second field" do not restrict the position or order of the "fields." "First" and "second" do not restrict whether the "fields" they modify are in the same message, nor do they restrict the order of "first field" and "second field." Similarly, if the descriptive object is a "level," the ordinal numbers preceding "level" in "first level" and "second level" do not restrict the priority between "levels." Furthermore, the number of descriptive objects is not limited by ordinal numbers and can be one or more. For example, in "first device," the number of "devices" can be one or more. Furthermore, the objects modified by different prefixes can be the same or different. For example, if the object being described is "device", then "first device" and "second device" can be the same device or different devices, and their types can be the same or different. As another example, if the object being described is "information", then "second information" and "first information" can be the same information or different information, and their content can be the same or different.

[0093] In some embodiments, “including A,” “containing A,” “for indicating A,” and “carrying A” can be interpreted as directly carrying A or indirectly indicating A.

[0094] In some embodiments, the terms “in response to…”, “in response to determining…”, “in the case of…”, “when…”, “if…”, “if…”, etc., can be used interchangeably.

[0095] In some embodiments, the terms "greater than", "more than", "higher than", and "exceeding" can be used interchangeably. In some embodiments, the terms "greater than or equal to", "not less than", "more than or equal to", "not less than", "higher than or equal to", "not lower than", and "above" can be used interchangeably. In some embodiments, the terms "less than", "less than", and "lower than" can be used interchangeably. In some embodiments, the terms "less than or equal to", "not greater than", "less than or equal to", "not more than", "lower than or equal to", "not higher than", and "below" can be used interchangeably.

[0096] In some embodiments, devices, etc., can be interpreted as physical or virtual, and their names are not limited to the names recorded in the embodiments. Terms such as “device”, “equipment”, “circuit”, “network element”, “node”, “function”, “unit”, “section”, “system”, “network”, “chip”, “chip system”, “entity”, and “subject” can be used interchangeably.

[0097] In some embodiments, "network" can be interpreted as devices included in a network (e.g., access network devices, core network devices, etc.).

[0098] 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," and "bandwidth part (BWP)" can be used interchangeably.

[0099] 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", and "client" can be used interchangeably.

[0100] In some embodiments, access network devices, core network devices, or network devices can be replaced by terminals. For example, embodiments of this disclosure can also be applied to structures where communication between access network devices, core network devices, or network devices and terminals is replaced by communication between multiple terminals (e.g., device-to-device (D2D), vehicle-to-everything (V2X), etc.). In this case, the structure can also be configured such that the terminal has all or part of the functions of the access network device. Furthermore, terms such as "uplink" and "downlink" can be replaced with terms corresponding to communication between terminals (e.g., "sidelink"). For example, uplink channel, downlink channel, etc., can be replaced with sidelink channel, and uplink link, downlink, etc., can be replaced with sidelink link.

[0101] In some embodiments, the terminal may be replaced by an access network device, a core network device, or a network device. In this case, the access network device, core network device, or network device may also be configured to have all or some of the functions of the terminal.

[0102] In some embodiments, the acquisition of data, information, etc., may comply with the laws and regulations of the country where the location is situated.

[0103] In some embodiments, data, information, etc., may be obtained with the user's consent.

[0104] Furthermore, each element, each row, or each column in the table of this 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.

[0105] Figure 1 is a schematic diagram of the architecture of a communication system provided according to an embodiment of the present disclosure. As shown in Figure 1, the communication system 100 includes a first node 101 and a second node 102.

[0106] In some embodiments, the first node 101 may be a terminal, an access network device, a core network device, etc. In some embodiments, the first node 101 may be deployed with an AI / ML model and may perform inference based on the AI / ML model.

[0107] In some embodiments, the second node 102 may be an access network device, a core network device, or the like. In some embodiments, the second node 102 may be used to deploy AI / ML models to the first node 101 and to train the AI / ML models.

[0108] In some embodiments, the terminal includes, but is not limited to, at least one of the following: mobile phone, wearable device, Internet of Things device, car with communication function, smart car, tablet computer, computer with wireless transceiver function, virtual reality (VR) terminal device, augmented reality (AR) terminal device, wireless terminal device in industrial control, wireless terminal device in self-driving, wireless terminal device in remote medical surgery, wireless terminal device in smart grid, wireless terminal device in transportation safety, wireless terminal device in smart city, and wireless terminal device in smart home.

[0109] In some embodiments, the access network device is, for example, a node or device that connects a terminal to a wireless network. In some embodiments, the access network device may include, but is not limited to, at least one of the following in a 5G communication system: evolved Node B (eNB), next-generation eNB (ng-eNB), next-generation Node B (gNB), node B (NB), home node B (HNB), home evolved node B (HeNB), radio backhaul device, radio network controller (RNC), base station controller (BSC), base transceiver station (BTS), base band unit (BBU), mobile switching center, base station in a 6G communication system, open RAN, cloud RAN, base station in other communication systems, and access node in a Wi-Fi system.

[0110] In some embodiments, the technical solutions of this disclosure can be applied to Open Radio Access Network (Open RAN) architectures. In this case, the interfaces between or within access network devices involved in the embodiments of this disclosure can be transformed into internal interfaces of Open RAN. The processes and information interactions between these internal interfaces can be implemented by software or programs.

[0111] In some embodiments, the access network device may be composed of a central unit (CU) and a distributed unit (DU). The CU may also be called a control unit. The CU-DU structure can separate the protocol layer of the access network device. Some of the protocol layer functions are centrally controlled by the CU, while the remaining part or all of the protocol layer functions are distributed in the DU and centrally controlled by the CU. However, this is not the only possibility.

[0112] It is understood that the communication system described in this disclosure is for the purpose of more clearly illustrating the technical solutions of this disclosure, and does not constitute a limitation on the technical solutions proposed in this disclosure. As those skilled in the art will know, with the evolution of system architecture and the emergence of new business scenarios, the technical solutions proposed in this disclosure are also applicable to similar technical problems.

[0113] The following embodiments of this disclosure can be applied to the communication system 100 shown in FIG1, or to some of the main bodies, but are not limited thereto. The main bodies shown in FIG1 are illustrative. The communication system may include all or some of the main bodies in FIG1, or may include other main bodies outside of FIG1. ​​The number and form of each main body are arbitrary. Each main body may be physical or virtual. The connection relationship between the main bodies is illustrative. The main bodies may not be connected or may be connected. The connection can be in any way, it can be a direct connection or an indirect connection, it can be a wired connection or a wireless connection.

[0114] The embodiments disclosed herein can be applied to Long Term Evolution (LTE), LTE-Advanced (LTE-A), LTE-Beyond (LTE-B), SUPER 3G, IMT-Advanced, 4th generation mobile communication system (4G), 5th generation mobile communication system (5G), 5G New Radio (NR), Future Radio Access (FRA), New-Radio Access Technology (RAT), New Radio (NR), New Radio access (NX), Future generation radio access (FX), Global System for Mobile communications (GSM), CDMA2000, Ultra Mobile Broadband (UMB), IEEE 802.11 (Wi-Fi), IEEE 802.16 (WiMAX), and IEEE 802.20, Ultra-Wideband (UWB), Bluetooth (a registered trademark), Public Land Mobile Network (PLMN) networks, Device-to-Device (D2D) systems, Machine-to-Machine (M2M) systems, Internet of Things (IoT) systems, Vehicle-to-Everything (V2X) systems, systems utilizing other communication methods, and next-generation systems built upon them, etc. Furthermore, multiple systems can be combined (e.g., a combination of LTE or LTE-A with 5G).

[0115] AI / ML models can be deployed in communication systems. These models can then be used for inference.

[0116] In the AI / ML project of the 3rd generation partnership project (3GPP), model transfer / model delivery was studied.

[0117] In some embodiments, the network device can perform model training, store the trained AI / ML model in the communication network, and send the AI / ML model to the terminal. During model transmission, the network device sends model parameters to the terminal, along with two indications: a first indication and a second indication. The first indication indicates a first model structure, which can be a known model structure. The second indication indicates the transmitted model parameters. In some embodiments, the known model structure can be a standardized model structure. Furthermore, the known model structure can be known to both the network device and the terminal. Based on the first indication, the terminal can determine the model structure used by the model sent to it by the network device. In some embodiments, since one first model structure can correspond to at least one set of model parameters, even using the same model structure but different sets of model parameters can generate different models.

[0118] In some embodiments, different models may include the following two cases: models with different model structures, and models with the same model structure but different model parameters.

[0119] In some cases, when sending a model, it is possible to send only or transmit a portion of the model's parameters, rather than sending all of the model's parameters.

[0120] Therefore, how to send some of the model parameters is an urgent problem to be solved.

[0121] Figure 2 is an interactive schematic diagram of the communication method provided according to an embodiment of the present disclosure. The communication method involved in this embodiment can be applied to a communication system 100. As shown in Figure 2, the communication method of this embodiment includes steps S201 to S204.

[0122] In step S201, the first node 101 sends the first information to the second node 102.

[0123] In some embodiments, the first node 101 may send first information. In some embodiments, the first information may be sent by the first node 101, but is not limited thereto, and may also be sent by other entities.

[0124] In some embodiments, the second node 102 may receive the first information. In some embodiments, the first information may be received by the second node 102, but is not limited thereto, and may also be received by other entities.

[0125] In some embodiments, the first information can be used to report the first node 101's support capability for model transmission.

[0126] In some embodiments, the name of the first information is not limited, and it may be, for example, reporting information, capability information, support information, etc.

[0127] In some embodiments, the first information may include at least one of the following: model support information and fourth instruction information.

[0128] In some embodiments, model support information may be used to indicate to the second node 102 the number of first model structures and / or the number of model parameter subsets supported by the first node 101.

[0129] In some embodiments, the first information may indicate at least one of the following: M, N, L.

[0130] In some embodiments, N can be the maximum number of first model structures supported by the first node 101.

[0131] In some embodiments, M can be the maximum number of subsets of model parameters supported by the first node 101.

[0132] In some embodiments, L can be the maximum number of model parameter subsets supported by the first node 101 for a first model structure.

[0133] In some embodiments, the first model structure may include a convolutional neural network (CNN), a residual network (ResNet), a transformer, etc. It is understood that the first model structure may also include other model structures, and this disclosure does not specifically limit these.

[0134] In some embodiments, the first information may include M and N. In some embodiments, the first information may include M and L. In some embodiments, the first information may include M, N, and L.

[0135] In one example, M, N, and L are all positive integers.

[0136] In some embodiments, the fourth indication information may be used to indicate the first node 101's ability to support the transmission of a subset of model parameters.

[0137] In some embodiments, the fourth indication information may be used to indicate at least one of the following: the first node 101 supports the transmission of a subset of model parameters, and the method of determining the second model supported by the first node 101.

[0138] In some embodiments, the fourth indication information may indicate that the first node 101 supports receiving a subset of model parameters. In some embodiments, the fourth indication information may indicate that the first node 101 receives a subset of model parameters and generates a second model based on the subset of model parameters.

[0139] In some embodiments, the method for determining the second model supported by the first node 101 may include at least one of the following: a first method, a second method, and a third method.

[0140] It is understood that in some embodiments, the fourth indication information may be independent of the first information. For example, the first node 101 may send the first information and the fourth indication information separately.

[0141] In step S202, the second node 102 sends the second information to the first node 101.

[0142] In some embodiments, the second node 102 may send second information. In some embodiments, the second information may be sent by the second node 102, but is not limited thereto, and may also be sent by other entities.

[0143] In some embodiments, the first node 101 may receive the second information. In some embodiments, the second information may be received by the first node 101, but is not limited thereto, and may also be received by other entities.

[0144] In some embodiments, the second information may be used to instruct the first node 101 on the second model. In some embodiments, the second information may be used to deploy the second model on the first node 101.

[0145] In some embodiments, the second model may include an AI / ML model.

[0146] In some embodiments, the name of the second information is not limited, and it may be, for example, model configuration information, model deployment information, model information, etc.

[0147] In some embodiments, the second information may include at least one of the following: a subset of model parameters, first indication information, second indication information, first model identifier, and second model identifier.

[0148] In some embodiments, the subset of model parameters may include a portion of the model parameters in the model parameter set of the second model. In some embodiments, the model parameter set of the second model may include all the model parameters of the second model to be deployed. The subset of model parameters may include a portion of the model parameters from the total model parameters in the model parameter set of the second model.

[0149] In some embodiments, the first indication information may indicate a first model structure. In some embodiments, the first indication information may be used to indicate a first model structure.

[0150] In some embodiments, the first model structure indicated by the first indication information may be a model structure adopted by the first model. In one example, the first model structure indicated by the first indication information may be one of the following: a convolutional neural network, a residual network, or a transformer.

[0151] In some embodiments, the first model structure indicated by the first indication information may be one of a plurality of standardized first model structures. In some embodiments, one first indication information may correspond to one first model structure; conversely, one first model structure may correspond to one indication information. The first indication information and the first model structure may have a one-to-one correspondence.

[0152] In some embodiments, the first indication information can be an integer. For example, the value of the first indication information can be an integer. In some embodiments, the value range of the first indication information can be 0 to N-1. For example, the first indication information can indicate any integer from 0 to N-1.

[0153] In one example, N can be equal to 3. Therefore, the first indication information can take values ​​ranging from 0, 1, to 2.

[0154] In one example, the value of the first indication information can be 0, 1, or 2. For example, if the value of the first indication information is 0, the first model structure indicated by the first indication information can be a convolutional neural network. For example, if the value of the first indication information is 1, the first model structure indicated by the first indication information can be a residual network. If the value of the first indication information is 2, the first model structure indicated by the first indication information can be a transformer.

[0155] It is understandable that the first indication information can be considered as the index value of the first model structure. Different index values ​​can be used to indicate different first model structures.

[0156] In some embodiments, a first model structure may correspond to one or more subsets of model parameters; conversely, a subset of model parameters may correspond to one first model structure. In some embodiments, a first indication information may correspond to one or more subsets of model parameters; conversely, a subset of model parameters may correspond to one first indication information. This is because there is a one-to-one correspondence between the first indication information and the first model structure.

[0157] In some embodiments, the second indication information may indicate a subset of model parameters.

[0158] In some embodiments, the subset of model parameters indicated by the second indication information may be a subset of model parameters corresponding to the first model structure adopted by the first model. In one example, the first model structure indicated by the first indication information may be a convolutional neural network, a residual network, or a converter, then the subset of model parameters indicated by the second indication information may be a subset of model parameters of the convolutional neural network, a subset of model parameters of the residual network, or a subset of model parameters of the converter.

[0159] In some embodiments, the second indication information can be used to indicate a subset of model parameters corresponding to all the first indication information. In some embodiments, the second indication information can be used to indicate a subset of model parameters corresponding to all the first model structures.

[0160] In some embodiments, one second indication information may correspond to a subset of model parameters; conversely, a subset of model parameters may correspond to one second indication information. In some embodiments, different second indication information may correspond to different subsets of model parameters, and different subsets of model parameters may correspond to different second indication information. In some embodiments, the second indication information and the subset of model parameters may have a one-to-one correspondence. For example, a one-to-one mapping relationship may be satisfied between the second indication information and the subset of model parameters.

[0161] In some embodiments, the second indication information can be an integer. For example, the value of the second indication information can be an integer. In some embodiments, the value range of the second indication information can be 0 to M-1. For example, the second indication information can indicate any integer from 0 to M-1.

[0162] In one example, M can be equal to 4. Then, the value range of the second indication information can be 0, 1, 2, or 3.

[0163] In some embodiments, a first model structure may correspond to one or more subsets of model parameters, and the number of model parameter subsets may be greater than or equal to the number of first model structures. In one example, each first model structure may correspond to one subset of model parameters, and the number of model parameter subsets may be equal to the number of first model structures.

[0164] In some embodiments, a second indication may correspond to a first indication; conversely, a first indication may correspond to one or more second indications. In one example, a first model structure may correspond to a subset of model parameters, in which case the first indication indicating the first model structure may correspond to a second indication. In another example, a first model structure may correspond to multiple subsets of model parameters, in which case the first indication indicating the first model structure may correspond to multiple second indications.

[0165] It is understood that the second indication information can be "global" indication information. The second indication information can be used to uniquely indicate a subset of model parameters corresponding to all first model structures. In some embodiments, a second indication information can indicate a subset of model parameters for a single first model structure. The second indication information for different subsets of model parameters for different first model structures is different, and the second indication information for different subsets of model parameters for the same first model structure is also different.

[0166] In one example, the maximum number of first model structures supported by the first node 101 can be equal to 3 (i.e., N=3), and the maximum number of model parameter subsets supported by the first node 101 can be equal to 8 (i.e., M=8). The first first model structure can correspond to 3 model parameter subsets. The second first model structure can correspond to 3 model parameter subsets. The third first model structure can correspond to 2 model parameter subsets. Then, the value of the first indication information can be 0, 1, or 2, and the value of the second indication information can be 0, 1, 2, 3, 4, 5, 6, or 7. For example, the first indication information with a value of 0 can indicate the first first model structure, and the value of the second indication information used to indicate the model parameter subset corresponding to the first first model structure can be 0, 1, or 2. For example, the first indication information with a value of 1 can indicate the second first model structure, and the value of the second indication information used to indicate the model parameter subset corresponding to the second first model structure can be 3, 4, or 5. For example, a first indication with a value of 2 can indicate a third first model structure, and a second indication used to indicate the subset of model parameters corresponding to the second first model structure can have a value of 6 or 7. In this case, a second indication can indicate a specific first model structure and a subset of model parameters. For example, if the value of the second indication is 5, then the second indication can indicate the third subset of model parameters in the second first model structure.

[0167] In some embodiments, the second indication information may be used to indicate a subset of model parameters corresponding to the first indication information. In some embodiments, the second indication information may be used to indicate a subset of model parameters corresponding to a first model structure.

[0168] In some embodiments, a second indication may correspond to a subset of model parameters in at least one subset of model parameters corresponding to a first indication; conversely, a subset of model parameters in at least one subset of model parameters corresponding to a first indication may correspond to a second indication. In some embodiments, different second indications may correspond to different subsets of model parameters in at least one subset of model parameters corresponding to a first indication, and different subsets of model parameters in at least one subset of model parameters corresponding to a first indication may correspond to different second indications. In some embodiments, the second indication and the subsets of model parameters corresponding to the first indication may have a one-to-one correspondence. For example, a one-to-one mapping relationship may exist between the second indication and the subsets of model parameters corresponding to the first indication.

[0169] In some embodiments, the second indication information can be an integer. For example, the value of the second indication information can be an integer. In some embodiments, the value range of the second indication information can be 0 to L-1. For example, the second indication information can indicate any integer from 0 to L-1.

[0170] In one example, L can be equal to 3. Therefore, the value of the second indication information can be 0, 1, or 2.

[0171] In some embodiments, a first model structure may correspond to one or more subsets of model parameters, and the number of model parameter subsets may be greater than or equal to the number of first model structures. In one example, each first model structure may correspond to one subset of model parameters, and the number of model parameter subsets may be equal to the number of first model structures.

[0172] In some embodiments, a second indication information may correspond to one or more first indication information; conversely, a first indication information may correspond to one or more second indication information. In one example, a first model structure may correspond to a subset of model parameters, then the first indication information indicating the first model structure may correspond to one second indication information. In one example, a first model structure may correspond to multiple subsets of model parameters, then the first indication information indicating the first model structure may correspond to multiple second indication information. It is understood that at least one subset of model parameters corresponding to a first model structure and the second indication information can satisfy a one-to-one mapping relationship. In some embodiments, model parameter subsets in different first model structures may correspond to the same or different second indication information. In one example, model parameter subsets in different first model structures may correspond to the same second indication information.

[0173] It is understood that the second indication information can be "local" indication information. The second indication information can be used to uniquely indicate a subset of model parameters corresponding to a first model structure. In some embodiments, a second indication information can indicate a subset of model parameters for a first model structure. The second indication information for different subsets of model parameters for different first model structures may be the same or different. The second indication information for different subsets of model parameters for the same first model structure is different.

[0174] In one example, the maximum number of first model structures supported by the first node 101 can be equal to 3 (i.e., N = 3), and the maximum number of model parameter subsets supported by the first node 101 for a first model structure can be equal to 2 (i.e., L = 2). Each first model structure can correspond to 2 model parameter subsets. Therefore, the value of the first indication information can be 0, 1, or 2, and the value of the second indication information can be 0 or 1. For example, a first indication information with a value of 0 can indicate the first first model structure, and the value of the second indication information used to indicate the model parameter subset corresponding to the first first model structure can be 0 or 1. For example, a first indication information with a value of 1 can indicate the second first model structure, and the value of the second indication information used to indicate the model parameter subset corresponding to the second first model structure can be 0 or 1. For example, a first indication information with a value of 2 can indicate the third first model structure, and the value of the second indication information used to indicate the model parameter subset corresponding to the second first model structure can be 0 or 1. It should be noted that in this example, the maximum number of model parameter subsets supported for each first model structure can be the same. However, in some embodiments, the maximum number of model parameter subsets supported for each first model structure may be different, and this disclosure does not specifically limit this.

[0175] In some embodiments, M, N, and L can satisfy the following relationship: M = N × L. In other words, the maximum number of model parameter subsets supported by the first node 101 can be equal to the product between the maximum number of first model structures supported by the first node 101 and the maximum number of model parameter subsets supported for a first model structure.

[0176] In some embodiments, a first model identifier may indicate a first model already existing in a first node. In some embodiments, a first model identifier may be used to indicate a first model already existing in a first node. In some embodiments, a first model may be a model already deployed on a first node, and a first model identifier may be used to identify the first model.

[0177] In some embodiments, the first model may include an AI / ML model.

[0178] In some embodiments, the model structure of the first model can be one of the following: a convolutional neural network, a residual network, or a converter. It is understood that the first model can also have other model structures, and this disclosure does not specifically limit these.

[0179] In some embodiments, the second model identifier may be assigned by the second node. In some embodiments, the second model identifier may be an identifier assigned to the second model by the second node. It is understood that in some embodiments, the second model identifier may also be assigned to the second model by another node, and may be obtained by the second node and carried in the first information; this disclosure does not specifically limit this aspect.

[0180] In some embodiments, the first information may include a subset of model parameters, and may further include at least one of the following: a first model identifier, first indication information, second indication information, and a second model identifier. In one example, the first information may include a subset of model parameters and a first model identifier. In another example, the first information may include a subset of model parameters, a first model identifier, first indication information, and second indication information. In another example, the first information may include a subset of model parameters, a first model identifier, and a second model identifier. In another example, the first information may include a subset of model parameters, first indication information, and second indication information. In another example, the first information may include a subset of model parameters, first indication information, second indication information, and a second model identifier.

[0181] It should be noted that the content of the second information can be sent together or separately. In one example, step S202 may include: the second node 102 sending a first model identifier and / or first indication information, and a subset of model parameters to the first node 101. In one example, step S202 may include: the second node 102 sending second identifier information and / or a second model identifier to the first node 101. In one example, step S202 may include: the second node 102 sending at least one of a first model identifier, first indication information, second indication information, and a second model identifier, and a subset of model parameters to the first node 101.

[0182] In some embodiments, the second information may include third indication information. In some embodiments, the third information may indicate the method of determining the second model. In some embodiments, the third information may be used to indicate the method of determining the second model.

[0183] In some embodiments, the method for determining the second model indicated by the third indication information may include at least one of the following: a first method, a second method, and a third method.

[0184] It is understood that in some embodiments, the third indication information may be independent of the first information. For example, the first node 101 may send the second information and the third indication information separately.

[0185] In step S203, the second node 102 determines the third model identifier.

[0186] In some embodiments, upon receiving the second information, the first node 101 may determine the third model identifier. In some embodiments, the third model identifier may be determined based on the second information.

[0187] In some embodiments, a third model identifier may indicate a second model.

[0188] In some embodiments, step S203 may include: determining a third model identifier based on at least one of the first indication information and the second indication information.

[0189] In some embodiments, the first node 101 may obtain first indication information and / or second indication information based on second information. Then, the first node 101 may determine a third model identifier based on at least one of the first and second indication information.

[0190] In some embodiments, step S203 may be implemented as: determining a third model identifier based on the second indication information.

[0191] In some embodiments, the second indication information can be used to indicate a subset of model parameters corresponding to all of the first indication information. In some embodiments, the second indication information and the subset of model parameters can have a one-to-one correspondence. In this case, the third model identifier can be determined based on the second indication information.

[0192] In some embodiments, determining the third model identifier based on the second indication information may include: determining the third model identifier as the second indication information. In some implementations, the first node 101 may use the second indication information as the third model identifier. In other words, the third model identifier may be equal to the second indication information.

[0193] In some embodiments, determining a third model identifier based on the second indication information may include: determining a third model identifier associated with the second indication information. In some embodiments, the first node 101 may assign a third model identifier associated with the second indication information to the second model.

[0194] In some embodiments, step S203 can be implemented as: determining a third model identifier based on the first indication information and the second indication information.

[0195] In some embodiments, a second indication may correspond to a subset of model parameters within at least one subset of model parameters corresponding to a first indication. In some embodiments, the combination of the first and second indications corresponds one-to-one with a subset of model parameters. In this case, the third model identifier can be determined based on the first and second indications.

[0196] It is understandable that one subset of model parameters corresponds to one first indication, but one first indication corresponds to at least one subset of model parameters. Therefore, the combination of the first and second indications satisfies a one-to-one mapping relationship with the subset of model parameters, meaning the combination of the first and second indications can uniquely indicate the subset of model parameters. Considering that different first model structures correspond to different first indications, and the third model identifier is determined jointly by the first and second indications, even if different model structures correspond to the same subset of model parameters, it is impossible for different first model structures to correspond to the same model identifier.

[0197] In some embodiments, the third model identifier can be determined as follows: Third model identifier = First indication information × L + Second indication information. It should be noted that the value range of the third model identifier determined in this way can be from 0 to M-1.

[0198] In some embodiments, step S203 may include: determining a third model identifier based on a second model identifier.

[0199] In some embodiments, the first node 101 may obtain a second model identifier based on the second information. Then, the first node 101 may determine a third model identifier based on the second model identifier. In one example, the first node 101 may determine the second model identifier as the third model identifier.

[0200] In some embodiments, step S203 may include: determining a third model identifier based on a first model identifier.

[0201] In some embodiments, if the second information includes a first model identifier but does not include a second model identifier, first indication information, or second indication information, the first model identifier may be determined as a third model identifier. In this case, the first node 101 may determine the second model using a third method.

[0202] In step S204, the first node 101 determines the second model.

[0203] In some embodiments, upon receiving the second information, the first node 101 can determine the second model. In some embodiments, the second model may be determined by the first node 101 based on the second information.

[0204] In some embodiments, step S203 may include: determining a first model based on the set of model parameters in the second information and the first indication information.

[0205] In some embodiments, the first node 101 can obtain a set of model parameters and first indication information from the received second information. Then, the first node 101 can determine the first model structure indicated by the first indication information and apply the set of model parameters to the first model structure. In this way, the first node 101 can determine the first model.

[0206] In some embodiments, the way in which the first node 101 determines the second model (i.e. the way in which the second model is determined) may include: a first way, a second way, and a third way.

[0207] In some embodiments, the first node 101 can determine the second model through a first method.

[0208] In some embodiments, the first approach may refer to generating a second model based on a subset of model parameters and a first model structure indicated by first indication information. In some embodiments, when using the first approach, step S204 may include: generating a second model based on a subset of model parameters and a first model structure indicated by first indication information.

[0209] In some embodiments, the received second information may include a subset of model parameters and first indication information. In this case, the first node 101 can generate a second model based on the subset of model parameters and the first model structure indicated by the first indication information. For example, the second information may include a subset of model parameters, first indication information, and second indication information. The second information may include a subset of model parameters, first indication information, and a second model identifier. The second information may include a subset of model parameters, first indication information, second indication information, and a second model identifier.

[0210] In some embodiments, the first node 101 may determine, based on an explicit instruction, to use a first approach to determine the second model. In one example, the second information may include third instruction information, and the third instruction information indicates that the first approach is used. In this case, the first node 101 may use the first approach to determine the second model.

[0211] In some embodiments, the first node 101 can determine the second model using a first method based on implicit instructions. In one example, the second information may include first instruction information and a subset of model parameters, but does not include a first model identifier. In this case, the first node 101 can determine the second model using the first method. In one example, if the first node 101 receives the first instruction information and the subset of model parameters, but does not receive the first model identifier, the first node 101 can generate the second model based on the first model structure indicated by the subset of model parameters and the first instruction information.

[0212] In some embodiments, the first node 101 determining the second model in a first manner can be implemented by: applying model parameters from a subset of model parameters to a first model structure; and setting model parameters in the first model structure other than the subset of model parameters to 0 to obtain the second model.

[0213] Figure 3 is a schematic diagram of the architecture of a convolutional neural network according to an embodiment of the present disclosure. As shown in Figure 3, the convolutional neural network 300 may include an input layer 301, a convolutional layer 302, a pooling layer 303, and a fully connected layer 304. In the convolutional neural network 300, each of the input layer 301, the convolutional layer 302, the pooling layer 303, and the fully connected layer 304 has one or more model parameters. In one example, the first model structure indicated by the first indication information may be a convolutional neural network. In one example, a subset of model parameters may include the model parameters corresponding to the convolutional layer 302.

[0214] In one example, referring to Figure 3, in the first approach, the first node 101 can determine that the first model structure is a convolutional neural network 300 based on the first indication information. Then, the first node 101 can apply the model parameters included in the subset of model parameters to the convolutional layer 302 of the convolutional neural network 300. Next, the first node 101 can set the model parameters of the input layer 301, pooling layer 303, and fully connected layer 304 in the convolutional neural network 300 to 0. The convolutional neural network 300 generated in this manner is the second model.

[0215] In some embodiments, the first node 101 may determine the second model through a second method.

[0216] In some embodiments, the second approach may refer to generating a second model based on a subset of model parameters and a first model indicated by a first model identifier. In some embodiments, when the second approach is adopted, step S204 may include: generating a second model based on a subset of model parameters and a first model indicated by a first model identifier.

[0217] In some embodiments, the received second information may include a subset of model parameters and a first model identifier. In this case, the first node 101 can generate a second model based on the subset of model parameters and the first model indicated by the first model identifier. For example, the second information may include a subset of model parameters, a first model identifier, first indication information, and second indication information.

[0218] In some embodiments, the first node 101 may determine, based on an explicit instruction, to use a second approach to determine the second model. In one example, the second information may include third instruction information, and the third instruction information indicates that the second approach is used. In this case, the first node 101 may use the second approach to determine the second model.

[0219] In some embodiments, the first node 101 can determine the second model using a second method based on implicit instructions. In one example, if the first node 101 receives a first model identifier and the first model identifier is different from the third model identifier, the first node 101 can generate a second model based on a subset of model parameters and the first model indicated by the first model identifier. In this case, the first node 101 can determine the second model using the second method. For example, the second information may include a subset of model parameters, a first model identifier, first instruction information, and second instruction information, and if the third model identifier determined based on the first instruction information and / or the second instruction information is different from the first model identifier, then the first node 101 can determine the second model using the second method. For example, the second information may include a subset of model parameters, a first model identifier, and a second model identifier, and if the second model identifier is different from the first model identifier, then the first node 101 can determine the second model using the second method.

[0220] In some embodiments, the first node 101 can determine the second model in a second manner by replacing the model parameters in the first model corresponding to the subset of model parameters with the model parameters in the subset of model parameters to obtain the second model.

[0221] In one example, the first node 101 can copy the first model indicated by the first model identifier to obtain another first model; then, the first node 101 can apply the model parameters in the model parameter subset to the other first model, and retain the other model parameters in the other first model except for the model parameter subset, to obtain a second model.

[0222] In one example, referring to Figure 3, in the second approach, the first node 101 can determine the first model based on the first model identifier, and the first model is a convolutional neural network 300. The first node 101 can copy the convolutional neural network 300. Then, the first node 101 can apply the model parameters included in the subset of model parameters to the convolutional layer 302 of the copied convolutional neural network 300. The first node 101 can retain the model parameters of the input layer 301, pooling layer 303, and fully connected layer 304 in the copied convolutional neural network 300. The convolutional neural network 300 generated in this manner is the second model.

[0223] In one example, the first node 101 can copy the first model indicated by the first model identifier to obtain another first model; then, the first node 101 can apply the model parameters in the model parameter subset to the other first model, and set the other model parameters in the other first model except for the model parameter subset to 0 to obtain a second model.

[0224] In one example, referring to Figure 3, in the second approach, the first node 101 can determine the first model based on the first model identifier, and the first model is a convolutional neural network 300. The first node 101 can copy the convolutional neural network 300. Then, the first node 101 can apply the model parameters included in the subset of model parameters to the convolutional layer 302 of the copied convolutional neural network 300. Furthermore, the first node 101 can set the model parameters of the input layer 301, pooling layer 303, and fully connected layer 304 in the copied convolutional neural network 300 to 0. The convolutional neural network 300 generated in this manner is the second model.

[0225] In one example, the first node 101 can copy the first model indicated by the first model identifier to obtain another first model; then, the first node 101 can apply the model parameters in the model parameter subset to the original first model, and retain the other model parameters in the other first model except for the model parameter subset, to obtain a second model.

[0226] In one example, referring to Figure 3, in the second approach, the first node 101 can determine the first model based on the first model identifier, and the first model is a convolutional neural network 300. The first node 101 can copy the convolutional neural network 300. Then, the first node 101 can apply the model parameters included in the subset of model parameters to the convolutional layer 302 of the original convolutional neural network 300. The first node 101 can retain the model parameters of the input layer 301, pooling layer 303, and fully connected layer 304 in the original convolutional neural network 300. The convolutional neural network 300 generated in this manner is the second model.

[0227] Understandably, in the second method, the first node 101 can utilize the existing model structure of the first model in the first node 101 to generate the second model. Furthermore, during the process of obtaining the second model through the second method, the first model is retained in the first node 101. Therefore, the first model identifier of the first model and the third model identifier of the second model are different.

[0228] In some embodiments, the first node 101 may determine the second model through a third method.

[0229] In some embodiments, the third approach may refer to generating a second model based on a subset of model parameters and a first model indicated by a first model identifier. In some embodiments, when the third approach is adopted, step S204 may include: generating a second model based on a subset of model parameters and a first model indicated by a first model identifier.

[0230] In some embodiments, the received second information may include a subset of model parameters and a first model identifier. In this case, the first node 101 can generate a second model based on the subset of model parameters and the first model indicated by the first model identifier. For example, the second information may include a subset of model parameters, a first model identifier, first indication information, and second indication information. For example, the second information may include a subset of model parameters, a first model identifier, and a second model identifier. For example, the second information may include a subset of model parameters and a first model identifier.

[0231] In some embodiments, the first node 101 may determine, based on an explicit instruction, to use a third approach to determine the second model. In one example, the second information may include third instruction information, and the third instruction information indicates the use of a third approach. In this case, the first node 101 may use the third approach to determine the second model.

[0232] In some embodiments, the first node 101 can determine the second model using a second method based on implicit instructions. In one example, when the first node 101 receives a first model identifier and the first model identifier is the same as a third model identifier, the first node 101 can generate a second model based on a subset of model parameters and the first model indicated by the first model identifier. In this case, the first node 101 can determine the second model using a third method. For example, the second information may include a subset of model parameters, a first model identifier, first instruction information, and second instruction information, and if the third model identifier determined based on the first instruction information and / or the second instruction information is the same as the first model identifier, then the first node 101 can determine the second model using a third method. For example, the second information may include a subset of model parameters, a first model identifier, and a second model identifier, and if the second model identifier is the same as the first model identifier, then the first node 101 can determine the second model using a third method. For example, the second information may include a subset of model parameters and a first model identifier, then the first node 101 can determine that the first model identifier will be used as the third model identifier, and can determine the second model using a third method.

[0233] In some embodiments, the first node 101 determining the second model in a third manner can be implemented by replacing the model parameters in the first model corresponding to the subset of model parameters with the model parameters in the subset of model parameters to obtain the second model.

[0234] It is understandable that in the third approach, the first node 101 can utilize the existing model structure of the first model in the first node 101 to generate the second model.

[0235] In one example, the first node 101 can apply the model parameters from the subset of model parameters to the first model, and retain the other model parameters in the first model besides the subset of model parameters, to obtain the second model.

[0236] In one example, referring to Figure 3, in the third approach, the first node 101 can determine the first model based on the first model identifier, and the first model is a convolutional neural network 300. The first node 101 can apply the model parameters included in the subset of model parameters to the convolutional layer 302 of the convolutional neural network 300. At the same time, the first node 101 can retain the model parameters of the input layer 301, pooling layer 303, and fully connected layer 304 in the convolutional neural network 300. The convolutional neural network 300 generated in this way is the second model.

[0237] It is understandable that in the third method, the first node 101 can utilize the existing model structure of the first model in the first node 101 to generate the second model. Furthermore, in the process of obtaining the second model through the third method, if model parameters from the subset of model parameters are directly applied to the first model, the original first model will no longer exist. Therefore, the first model identifier of the first model and the third model identifier of the second model are the same.

[0238] It should be noted that steps S203 and S204 can be executed sequentially or simultaneously, and this embodiment does not specifically limit this. For example, step S203 can be executed before step S204. For example, step S203 can be executed after step S204. For example, step S203 can be executed simultaneously with step S204.

[0239] The communication method of this disclosure embodiment can be implemented through steps S201 to S204.

[0240] In some embodiments, the names of information, etc., are not limited to the names described in the embodiments. Terms such as "information", "message", "signal", "signaling", "report", "configuration", "indication", "instruction", "command", "channel", "parameter", "domain", "field", "symbol", "symbol", "codebook", "codeword", "codepoint", "bit", "data", "program", and "chip" can be used interchangeably.

[0241] In some embodiments, the terms “radio”, “wireless”, “radio access network (RAN)”, “access network (AN)”, and “RAN-based” can be used interchangeably.

[0242] In some embodiments, “get,” “obtain,” “receive,” “transmit,” “bidirectional transmission,” and “send and / or receive” can be used interchangeably and can be interpreted as receiving from other entities, obtaining from protocols, obtaining from higher layers, obtaining through self-processing, or autonomous implementation, among other meanings.

[0243] In some embodiments, terms such as “send,” “transmit,” “report,” “distribute,” “transfer,” “bidirectional transmission,” “send and / or receive” can be used interchangeably.

[0244] In some embodiments, terms such as "certain", "preset", "default", "set", "indicated", "a certain", "any", and "first" can be used interchangeably. "Certain A", "preset A", "default A", "set A", "indicated A", "a certain A", "any A", and "first A" can be interpreted as A pre-defined in a protocol or the like, or as A obtained through setting, configuration, or instruction, or as specific A, a certain A, any A, or first A, but are not limited thereto.

[0245] The communication method involved in this disclosure embodiment may include at least one of steps S201 and S204. For example, step S202 may be implemented as a standalone embodiment. For example, a combination of steps S202 and S204 may be implemented as a standalone embodiment. For example, a combination of steps S202, S203, and S204 may be implemented as a standalone embodiment. For example, a combination of steps S201, S202, S203, and S204 may be implemented as a standalone embodiment. It should be noted that the possible standalone embodiments consisting of one or more steps S201 to S204 are not limited thereto.

[0246] In some embodiments, at least two steps in steps S201 to S204 may be executed simultaneously or in a different order. For example, steps S203 and S204 may be executed simultaneously or in a different order.

[0247] In some embodiments, steps S201, S203, and S204 are optional, and one or more of these steps may be omitted or substituted in different embodiments.

[0248] In some embodiments, other optional implementations may be described before or after the embodiment corresponding to FIG2.

[0249] Figure 4 is an interactive schematic diagram of a communication method provided according to an embodiment of the present disclosure. This disclosure relates to a communication method. As shown in Figure 4, the method includes steps S401 and S403.

[0250] In step S401, the second node 102 sends the second information to the first node 101.

[0251] The optional implementation of step S401 can be found in the optional implementation of step S202 in Figure 2, as well as other related parts in the embodiments involved in Figure 2, which will not be repeated here.

[0252] In step S402, the first node 101 determines the third model identifier.

[0253] The optional implementation of step S402 can be found in the optional implementation of step S203 in Figure 2, as well as other related parts in the embodiments involved in Figure 2, which will not be repeated here.

[0254] In step S403, the first node 101 determines the second model.

[0255] The optional implementation of step S403 can be found in the optional implementation of step S204 in Figure 2, as well as other related parts in the embodiments involved in Figure 2, which will not be repeated here.

[0256] In the following, the technical solutions of the embodiments of this disclosure will be described by way of specific implementation.

[0257] This invention proposes a method for sending / transmitting partial model parameters, specifically including method 1 to method 3 (i.e. mode 1 to mode 3).

[0258] In some embodiments, in method 1, the network device (i.e., the second node) sends some model parameters to the terminal device (i.e., the first node), while carrying first indication information and second indication information, wherein the first indication information indicates a known model structure and the second indication information indicates some model parameters; the terminal device generates a new model based on the partial model parameters sent by the network device and the known model structure indicated by the first indication information, wherein the unindicated model parameters are 0.

[0259] In some embodiments, the model identifier of the new model is determined based on second indication information.

[0260] In some embodiments, the model identifier of the new model is determined based on first indication information and second indication information.

[0261] In some embodiments, the model identifier of the new model is a second model identifier, wherein the network device needs to send the second model identifier to the terminal device.

[0262] In some embodiments, in method 2, the network device sends some model parameters to the terminal device, while carrying a first model identifier, wherein the first model identifier indicates a model that the terminal device already has; the terminal device generates a new model based on the partial model parameters sent by the network device and the model indicated by the first model identifier, wherein the new model is based on the model indicated by the first model identifier, with the corresponding model parameters replaced by the partial model parameters sent by the network device.

[0263] In some embodiments, the remaining model parameters in the new model are the parameters corresponding to those in the model indicated by the first model identifier.

[0264] In some embodiments, the model identifier of the new model is determined based on second indication information, wherein the network device needs to send the second indication information to the terminal device.

[0265] In some embodiments, the model identifier of the new model is determined based on first indication information and second indication information, wherein the network device needs to send the first indication information and the second indication information to the terminal device.

[0266] In some embodiments, the model identifier of the new model is a second model identifier, wherein the network device needs to send the second model identifier to the terminal device.

[0267] In some embodiments, the second model identifier is not equal to the first model identifier.

[0268] In some embodiments, in method 3, the network device sends some model parameters to the terminal device, while carrying a first model identifier, wherein the first model identifier indicates a model that the terminal device already has; the terminal device updates the model indicated by the first model identifier according to the partial model parameters sent by the network device, wherein the model parameters corresponding to the model indicated by the first model identifier are replaced with the partial model parameters sent by the network device, while the remaining model parameters remain unchanged.

[0269] In some embodiments, the model identifier of the model remains unchanged, i.e., the first model identifier.

[0270] In some embodiments, the model identifier of the model is determined according to the second instruction information, wherein the network device needs to send the second instruction information to the terminal device, and the determined model identifier of the model is equal to the first model identifier.

[0271] In some embodiments, the model identifier of the model is determined based on the first instruction information and the second instruction information, wherein the network device needs to send the first instruction information and the second instruction information to the terminal device, and the determined model identifier of the model is equal to the first model identifier.

[0272] In some embodiments, the model identifier of the model is a second model identifier, wherein the network device needs to send the second model identifier to the terminal device, and the second model identifier is equal to the first model identifier.

[0273] In some embodiments, the indication methods of methods 1 to 3 may include explicit indication and implicit indication.

[0274] In some embodiments, when the network device sends some parameters to the terminal device in the case of explicit instruction, it carries third instruction information, which is used to indicate one of the methods 1 to 3 described above.

[0275] In some embodiments, implicit indications may include three cases.

[0276] In one example, for the first case, if the network device sends some model parameters to the terminal device without carrying the first model identifier, then method 1 is used.

[0277] In one example, for the second case, if the network device sends some model parameters to the terminal device with the first model identifier, and the model identifier of the new model (determined according to the first instruction information, the second instruction information and / or the second model parameters) is not equal to the first model identifier, then method 2 is used.

[0278] In one example, for the third case, if the network device sends some model parameters to the terminal device, carrying the first model identifier, and the model identifier of the new model (determined according to the first instruction information, the second instruction information, and / or the second model parameter) is equal to the first model identifier, then method 3 is used.

[0279] In some embodiments, the terminal device reports the transmission and transfer of some model parameters to the network device.

[0280] In some embodiments, the terminal device reports to the network device whether it supports methods 1 to 3.

[0281] In the embodiments disclosed herein, some or all of the steps and their optional implementations may be arbitrarily combined with some or all of the steps in other embodiments, or may be arbitrarily combined with the optional implementations in other embodiments.

[0282] This disclosure also provides communication devices for implementing any of the above methods. For example, this disclosure provides a communication device including units or modules for implementing the steps performed by the first node 101 in any of the above methods. For example, this disclosure provides a communication device including units or modules for implementing the steps performed by the second node 102 in any of the above methods.

[0283] It should be understood that the division of units or modules in the above device is only a logical functional division. In actual implementation, they can be fully or partially integrated into a single physical entity, or they can be physically separated. Furthermore, the units or modules in the device can be implemented by a processor calling software: for example, the device includes a processor connected to a memory containing instructions. The processor calls the instructions stored in the memory to implement any of the above methods or to implement the functions of the units or modules in the above device. The processor can be, for example, a general-purpose processor, such as a Central Processing Unit (CPU) or a microprocessor, and the memory can be internal or external to the device. Alternatively, the units or modules in the device can be implemented in the form of hardware circuits. The functionality of some or all of the units or modules can be achieved through the design of these hardware circuits, which can be understood as one or more processors. For example, in one implementation, the hardware circuit is an application-specific integrated circuit (ASIC). The functionality of some or all of the units or modules is achieved through the design of the logical relationships between the components within the circuit. In another implementation, the hardware circuit can be implemented using a programmable logic device (PLD). Taking a field-programmable gate array (FPGA) as an example, it can include a large number of logic gates. The connection relationships between the logic gates are configured through configuration files, thereby achieving the functionality of some or all of the units or modules. All units or modules of the above device can be implemented entirely through processor-called software, entirely through hardware circuits, or partially through processor-called software with the remaining parts implemented through hardware circuits.

[0284] In this embodiment, the processor is a circuit with signal processing capabilities. In one implementation, the processor can be a circuit with instruction read and execute capabilities, such as a central processing unit, microprocessor, graphics processing unit (GPU) (which can be understood as a type of microprocessor), or digital signal processor (DSP). In another implementation, the processor can implement certain functions through the logical relationships of hardware circuits. The logical relationships of the aforementioned hardware circuits are fixed or reconfigurable. For example, the processor is a hardware circuit implemented by an application-specific integrated circuit (ASIC) or a programmable logic device, such as an FPGA. In a reconfigurable hardware circuit, the process of the processor loading a configuration document and configuring the hardware circuit can be understood as the process of the processor loading instructions to implement the functions of some or all of the above units or modules. Furthermore, 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), tensor processing unit (TPU), deep learning processing unit (DPU), etc.

[0285] Figure 5 is a schematic diagram of the structure of a communication device provided according to an embodiment of the present disclosure. As shown in Figure 5, the communication device 500 may include at least one of the following: a transceiver module 501 and a processing module 502.

[0286] In some embodiments, the communication device 500 may be a first node 101. In some embodiments, the transceiver module 501 may be configured to: receive at least one of a first model identifier and a first indication information, and a subset of model parameters, wherein the first model identifier indicates a first model already existing in the first node, the first indication information indicates a first model structure, and the subset of model parameters includes a portion of the model parameters in the model parameter set of the second model. In some embodiments, the processing module 502 may be configured to: determine a second model based on the first model indicated by the first model identifier or the first model structure indicated by the first indication information, and the subset of model parameters. Optionally, the transceiver module 501 may be configured to perform at least one of the communication steps (e.g., steps S201, S202, but not limited thereto) performed by the first node 101 in any of the above methods, which will not be elaborated here. Optionally, the processing module 502 may be configured to perform at least one of the other steps (e.g., steps S203, S204, but not limited thereto) performed by the first node 101 in any of the above methods, excluding the communication steps such as sending and receiving.

[0287] In some embodiments, the communication device 500 may be the second node 102. In some embodiments, the transceiver module 501 may be configured to: send at least one of a first model identifier and a first indication information, and a subset of model parameters, wherein the first model identifier indicates a first model already existing in the first node, the first indication information indicates a first model structure, and the subset of model parameters includes a portion of the model parameters in the model parameter set of the second model. Optionally, the transceiver module 501 may be configured to perform at least one of the communication steps (e.g., steps S201, S202, but not limited thereto) performed by the second node 102 in any of the above methods, which will not be elaborated here.

[0288] In some embodiments, the transceiver module may include a transmitting module and / or a receiving module. The transmitting and receiving modules may be separate or integrated. Optionally, the transceiver module may be interchangeable with a transceiver.

[0289] In some embodiments, the processing module may be a single module or may include multiple sub-modules. Optionally, the multiple sub-modules may each perform all or part of the steps required by the processing module. Optionally, the processing module may be interchangeable with a processor.

[0290] Figure 6A is a schematic diagram of the structure of a communication device provided according to an embodiment of the present disclosure. The communication device 6100 can be a network device (e.g., access network device, core network device, etc.), a terminal (e.g., user equipment, etc.), a chip, chip system, or processor that supports the network device in implementing any of the above methods, or a chip, chip system, or processor that supports the terminal in implementing any of the above methods. The communication device 6100 can be used to implement the methods described in the above method embodiments; for details, please refer to the descriptions in the above method embodiments.

[0291] As shown in Figure 6A, the communication device 6100 includes one or more processors 6101. The processor 6101 can be a general-purpose processor or a dedicated processor, such as a baseband processor or a central processing unit (CPU). The baseband processor can be used to process communication protocols and communication data, while the CPU can be used to control the communication device (e.g., base station, baseband chip, terminal device, terminal device chip, DU or CU, etc.), execute programs, and process program data. Optionally, the communication device 6100 can be used to execute any of the above methods. Optionally, one or more processors 6101 can be used to invoke instructions to cause the communication device 6100 to execute any of the above methods.

[0292] In some embodiments, the communication device 6100 further includes one or more transceivers 6102. When the communication device 6100 includes one or more transceivers 6102, the transceivers 6102 perform at least one of the communication steps such as sending and / or receiving in the above method (e.g., steps S201, S202, but not limited thereto), and the processor 6101 performs at least one of other steps (e.g., steps S203, S204, but not limited thereto). In optional embodiments, the transceiver may include a receiver and / or a transmitter, which may be separate or integrated. Optionally, the terms transceiver, transceiver unit, transceiver, transceiver circuit, interface circuit, interface, etc., can be used interchangeably; the terms transmitter, transmitting unit, transmitter, transmitting circuit, etc., can be used interchangeably; and the terms receiver, receiving unit, receiver, receiving circuit, etc., can be used interchangeably.

[0293] In some embodiments, the communication device 6100 further includes one or more memories 6103 for storing data. Optionally, all or part of the memories 6103 may be located outside the communication device 6100. In optional embodiments, the communication device 6100 may include one or more interface circuits 6104. Optionally, the interface circuits 6104 are connected to the memories 6103 and can be used to receive data from the memories 6103 or other devices, and to send data to the memories 6103 or other devices. For example, the interface circuits 6104 can read data stored in the memories 6103 and send that data to the processor 6101.

[0294] The communication device 6100 described in the above embodiments may be a network device or a terminal, but the scope of the communication device 6100 described in this disclosure is not limited thereto, and the structure of the communication device 6100 may not be limited by FIG. 6A. The communication device may be a standalone device or a part of a larger device. For example, the communication device may be: (1) a standalone integrated circuit IC, or chip, or chip system or subsystem; (2) a collection of one or more ICs, optionally, the IC collection may also include storage components for storing data and programs; (3) an ASIC, such as a modem; (4) a module that can be embedded in other devices; (5) a receiver, terminal device, smart terminal device, cellular phone, wireless device, handheld device, mobile unit, vehicle device, network device, cloud device, artificial intelligence device, etc.; (6) others, etc.

[0295] Figure 6B is a schematic diagram of the structure of a chip provided according to an embodiment of the present disclosure. For cases where the communication device 6100 can be a chip or a chip system, please refer to the schematic diagram of the chip 6200 shown in Figure 6B, but it is not limited thereto.

[0296] Chip 6200 includes one or more processors 6201. Chip 6200 is used to perform any of the methods described above.

[0297] In some embodiments, chip 6200 further includes one or more interface circuits 6202. Optionally, terms such as interface circuit, interface, and transceiver pin can be used interchangeably. In some embodiments, chip 6200 further includes one or more memories 6203 for storing data. Optionally, all or part of the memories 6203 may be located outside chip 6200. Optionally, interface circuit 6202 is connected to memory 6203, and interface circuit 6202 can be used to receive data from memory 6203 or other devices, and interface circuit 6202 can be used to send data to memory 6203 or other devices. For example, interface circuit 6202 can read data stored in memory 6203 and send the data to processor 6201.

[0298] In some embodiments, the interface circuit 6202 performs at least one of the communication steps such as sending and / or receiving in the above-described method (e.g., steps S201, S202, but not limited thereto). For example, the interface circuit 6202 performing the communication steps such as sending and / or receiving in the above-described method means that the interface circuit 6202 performs data interaction between the processor 6201, the chip 6200, the memory 6203, or the transceiver device. In some embodiments, the processor 6201 performs at least one of other steps (e.g., steps S203, S204, but not limited thereto).

[0299] The modules and / or devices described in the various embodiments, such as virtual devices, physical devices, and chips, can be combined or separated arbitrarily as needed. Optionally, some or all steps can also be performed collaboratively by multiple modules and / or devices, which is not limited here.

[0300] This disclosure also proposes a storage medium storing instructions that, when executed on a communication device 6100, cause the communication device 6100 to perform any of the methods described above. Optionally, the storage medium is an electronic storage medium. Optionally, the storage medium is a computer-readable storage medium, but not limited thereto; it may also be a storage medium readable by other devices. Optionally, the storage medium may be a non-transitory storage medium, but not limited thereto; it may also be a temporary storage medium.

[0301] This disclosure also provides a program product that, when executed by a communication device 6100, causes the communication device 6100 to perform any of the above methods. Optionally, the program product is a computer program product.

[0302] This disclosure also proposes a computer program that, when run on a computer, causes the computer to perform any of the above methods.

[0303] Other embodiments of the invention will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This disclosure is intended to cover any variations, uses, or adaptations of the invention that follow the general principles of the invention and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of the invention are indicated by the following claims.

[0304] It should be understood that the present invention is not limited to the precise structure described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of the invention is limited only by the appended claims.

Claims

1. A communication method performed by a first node, wherein, The method includes: Receive at least one of a first model identifier and a first indication information, and a subset of model parameters, wherein the first model identifier indicates a first model already existing in the first node, the first indication information indicates a first model structure, and the subset of model parameters includes some model parameters in the model parameter set of the second model; The second model is determined based on the first model indicated by the first model identifier or the first model structure indicated by the first indication information, and the subset of model parameters.

2. The method of claim 1, wherein, The method further includes: Receive at least one of a second identification information and a second model identification, wherein the second identification information indicates the subset of model parameters, and the second model identification is assigned by the second node.

3. The method of claim 1 or 2, wherein, The method further includes: A third model identifier is determined based on at least one of the first model identifier, the first indication information, the second indication information, and the second model identifier, wherein the third model identifier indicates the second model, the second indication information indicates the subset of model parameters, and the second model identifier is assigned by the second node.

4. The method of claim 3, wherein, The step of determining the third model identifier based on at least one of the first model identifier, the first indication information, the second indication information, and the second model identifier includes one of the following: The first model identifier is determined as the third model identifier; The third model identifier is determined based on the first indication information and the second indication information; The third model identifier is determined based on the second indication information; The second model identifier is determined as the third model identifier.

5. The method of any one of claims 1 to 4, wherein, Determining the second model based on the first model indicated by the first model identifier or the first model structure indicated by the first indication information, and the subset of model parameters, includes: The second model is generated based on the subset of model parameters and the first model structure indicated by the first indication information.

6. The method of claim 5, wherein, The step of generating the second model based on the subset of model parameters and the first model structure indicated by the first indication information includes: Apply the model parameters from the subset of model parameters to the first model structure; Set all model parameters in the first model structure except for the subset of model parameters to 0 to obtain the second model.

7. The method of claim 5 or 6, wherein, Determining the second model based on the first model indicated by the first model identifier or the first model structure indicated by the first indication information, and the subset of model parameters, includes: If the first node receives the first indication information and the subset of model parameters, but does not receive the first model identifier, the second model is generated according to the first model structure indicated by the subset of model parameters and the first indication information.

8. The method of any one of claims 1 to 4, wherein, Determining the second model based on the first model indicated by the first model identifier or the first model structure indicated by the first indication information, and the subset of model parameters, includes: The second model is generated based on the subset of model parameters and the first model indicated by the first model identifier.

9. The method of claim 8, wherein, The step of generating the second model based on the subset of model parameters and the first model indicated by the first model identifier includes: The model parameters in the first model corresponding to the subset of model parameters are replaced with the model parameters in the subset of model parameters to obtain the second model.

10. The method of claim 8 or 9, wherein, The second model is indicated by a third model identifier, which is different from the first model identifier.

11. The method of any one of claims 8-10, wherein, Determining the second model based on the first model indicated by the first model identifier or the first model structure indicated by the first indication information, and the subset of model parameters, includes: When the first node receives the first model identifier and the first model identifier is different from the third model identifier indicating the second model, the second model is generated according to the subset of model parameters and the first model indicated by the first model identifier.

12. The method of claim 8 or 9, wherein, The second model is indicated by a third model identifier, which is the same as the first model identifier.

13. The method of any one of claims 8, 9, 12, wherein, Determining the second model based on the first model indicated by the first model identifier or the first model structure indicated by the first indication information, and the subset of model parameters, includes: When the first node receives the first model identifier and the first model identifier is the same as the third model identifier indicating the second model, the second model is generated according to the subset of model parameters and the first model indicated by the first model identifier.

14. The method of any one of claims 1 to 13, wherein, The method further includes: Receive third indication information, wherein the third indication information indicates the determination method of the second model.

15. The method of any one of claims 1 to 14, wherein, The method further includes: Send a fourth indication message, wherein the fourth indication message indicates at least one of the following: The first node supports the passing of a subset of model parameters; The method for determining the second model supported by the first node.

16. The method of claim 14 or 15, wherein, The second model is determined by at least one of the following methods: The second model is generated based on the subset of model parameters and the first model structure indicated by the first indication information; The second model is generated based on the subset of model parameters and the first model indicated by the first model identifier.

17. A communication method performed by a second node, wherein, The method includes: Send at least one of a first model identifier and a first indication information, as well as a subset of model parameters, wherein the first model identifier indicates a first model already existing in the first node, the first indication information indicates a first model structure, and the subset of model parameters includes some model parameters in the model parameter set of the second model.

18. The method of claim 17, wherein, The method further includes: Send at least one of a second identification information and a second model identifier, wherein the second identification information indicates the subset of model parameters, and the second model identifier is assigned by the second node.

19. The method of claim 17 or 18, wherein, The method further includes: Send a third instruction message, wherein the third instruction message indicates the determination method of the second model.

20. The method of any one of claims 17-19, wherein, The method further includes: Receive a fourth indication message, wherein the fourth indication message indicates at least one of the following: The first node supports the passing of a subset of model parameters; The method for determining the second model supported by the first node.

21. The method of claim 19 or 20, wherein, The second model is determined by at least one of the following methods: The second model is generated based on the subset of model parameters and the first model structure indicated by the first indication information; The second model is generated based on the subset of model parameters and the first model indicated by the first model identifier.

22. The method of claim 21, wherein, The step of generating the second model based on the subset of model parameters and the first model structure indicated by the first indication information includes: Apply the model parameters from the subset of model parameters to the first model structure; Set all model parameters in the first model structure except for the subset of model parameters to 0 to obtain the second model.

23. The method of claim 21, wherein, The step of generating the second model based on the subset of model parameters and the first model indicated by the first model identifier includes: The model parameters in the first model corresponding to the subset of model parameters are replaced with the model parameters in the subset of model parameters to obtain the second model.

24. A communications device arranged at a first node, wherein The device includes: The transceiver module is configured to receive at least one of a first model identifier and a first indication information, as well as a subset of model parameters, wherein the first model identifier indicates a first model already existing in the first node, the first indication information indicates a first model structure, and the subset of model parameters includes some model parameters in the model parameter set of the second model. The processing module is configured to determine the second model based on the first model indicated by the first model identifier or the first model structure indicated by the first indication information, and the subset of model parameters.

25. A communications device arranged at a second node, wherein The device includes: The transceiver module is configured to send at least one of a first model identifier and a first indication information, as well as a subset of model parameters, wherein the first model identifier indicates a first model already existing in the first node, the first indication information indicates a first model structure, and the subset of model parameters includes some model parameters in the model parameter set of the second model.

26. A communication device, comprising: One or more processors; A memory that stores instructions; When the instruction is executed by the communication device, it causes the communication device to implement the communication method as described in any one of claims 1 to 23.

27. A communication system, comprising: The first node is configured to perform the communication method as described in any one of claims 1 to 16; The second node is configured to perform the communication method as described in any one of claims 17 to 23.

28. A storage medium storing instructions, wherein, When the instruction is executed on the communication device, the communication device implements the communication method as described in any one of claims 1 to 23.

29. A computer program product comprising instructions, wherein, When the instruction is executed on the communication device, the communication device implements the communication method as described in any one of claims 1 to 23.

Images