Model registration method and device and storage medium

Abstract

The invention provides a model registration method and device and a storage medium, and relates to the technical field of communication. The method comprises: a first entity sends a first message to a second entity, the first message being used for requesting to register a model, the first message comprising a first model identifier and / or model information, the first model identifier being an identifier of a model in the first entity; a second message sent by the second entity in response to the first message is received, the second message comprises a second model identifier and first indication information, the second model identifier is a network identifier allocated by the second entity for the model, and the first indication information indicates a registration decision or registration decision related information; and sending a third message to the second entity based on the registration decision related information, the third message including the second model identification and the registration decision. A model registration function and a corresponding registration process are added in a network, so that the network can provide services such as model registration for a user, the network or a third party as required, and a basis is provided for intelligent endogenesis.

Description

Technical Field

[0001] This application relates to the field of communication technologies, and in particular, to a method, apparatus, and storage medium for model registration. Background Art

[0002] The intelligent in-situ of the 6th Generation Mobile Networks (6G) may refer to that the 6G network natively supports Artificial Intelligence (AI), takes the AI capability as the basic service of the network, realizes AI as a Service (AIaaS), enables the network to self-learn and self-evolve, and thus can provide AI training services, AI inference services, AI deployment and open services, etc. for users, the network, or third parties.

[0003] However, the network architecture and network processes of existing mobile communication systems can only provide connection and data transmission services for users, and cannot provide intelligent in-situ services such as AI model registration and storage. Summary of the Invention

[0004] This application provides a method, apparatus, and storage medium for model registration, which solves the technical problem that the communication system cannot provide intelligent in-situ services such as AI model registration and storage.

[0005] In a first aspect, an embodiment of this application provides a method for model registration, which is applied to a first entity. The method includes:

[0006] Sending a first message to a second entity, where the first message is used to request model registration, and the first message includes a first model identifier and / or model information, and the first model identifier is the identifier of the model in the first entity;

[0007] Receiving a second message sent by the second entity in response to the first message, where the second message includes a second model identifier and first indication information, the second model identifier is the network identifier assigned by the second entity to the model, and the first indication information indicates a registration decision or registration decision-related information;

[0008] Sending a third message to the second entity based on the registration decision-related information, where the third message includes the second model identifier and a registration decision.

[0009] In one implementation, the model is a common model.

[0010] In one embodiment, the model information includes at least one of the following: model type, model modality, model algorithm, model accuracy, model security, model privacy, model description information, model deployment requirements, model inference performance, model open range, model version, model owner information, or automated deployment script.

[0011] In one embodiment, the model description information includes at least one of the following: model accuracy rate, variance of the model accuracy rate, data input format, data output format, model size, full model identifier corresponding to the compressed model, number of model parameters, model recall rate, or model F1 value;

[0012] The model deployment requirements include at least one of the following: model dependencies, minimum resource requirements, or recommended resource configurations, where the resources include computing power resources and storage resources.

[0013] In one embodiment, the model information further includes at least one of the following: model application scenario, model segmentation information, model compression information, or model training information.

[0014] In one embodiment, the model training information includes at least one of the following: training data set, metadata corresponding to the training data set, data preprocessing method, model features, model hyperparameters, or model structure.

[0015] In one embodiment, the method further includes:

[0016] Receiving second indication information sent by the second entity, where the second indication information includes the first model identifier, the second model identifier, and a model information template.

[0017] In one embodiment, the method further includes:

[0018] Sending a fourth message to the second entity;

[0019] Receiving a fifth message sent by the second entity in response to the fourth message;

[0020] Or,

[0021] Sending a fourth message to a third entity;

[0022] Receiving a fifth message sent by the third entity in response to the fourth message;

[0023] Wherein, the fourth message is used to request storing the model, and the fourth message includes at least one of the following: the second model identifier, model transmission method, model security certificate, model address, or the model; the fifth message is used to indicate the model storage result.

[0024] In one embodiment, the method further includes:

[0025] Send the model to the second entity or the third entity.

[0026] In one embodiment, the method further includes:

[0027] Send a sixth message to the second entity, where the sixth message includes the second model identifier and model update information;

[0028] Receive a seventh message sent by the second entity in response to the sixth message, where the seventh message is used to indicate the model update result.

[0029] In one embodiment, the method further includes:

[0030] Send an eighth message to the second entity;

[0031] Receive a ninth message sent by the second entity in response to the eighth message;

[0032] Or,

[0033] Send an eighth message to a third entity;

[0034] Receive a ninth message sent by the third entity in response to the eighth message;

[0035] Or,

[0036] Send an eighth message to a fourth entity;

[0037] Receive a ninth message sent by the fourth entity in response to the eighth message;

[0038] Wherein, the eighth message is used to request verification of the model, and the eighth message includes the second model identifier and the model; the ninth message is used to indicate the model verification result.

[0039] In one embodiment, the first entity is a first terminal, a first access network device, or a first core network device;

[0040] The second entity is deployed in a second terminal, a second access network device, or a second core network device;

[0041] The third entity is deployed in a third terminal, a third access network device, or a third core network device;

[0042] The fourth entity is deployed in a fourth access network device or a fourth core network device;

[0043] The first terminal, the second terminal, and the third terminal are the same or different from each other. The first access network device, the second access network device, the third access network device, and the fourth access network device are the same or different from each other. The first core network device, the second core network device, the third core network device, and the fourth core network device are the same or different from each other.

[0044] In a second aspect, an embodiment of the present application provides a model registration method, which is applied to a second entity. The method includes:

[0045] Receiving a first message sent by a first entity, where the first message is used to request model registration, and the first message includes a first model identifier and / or model information. The first model identifier is the identifier of the model in the first entity;

[0046] Responding to the first message by sending a second message to the first entity. The second message includes a second model identifier and first indication information. The second model identifier is the network identifier assigned by the second entity to the model, and the first indication information indicates a registration decision or registration decision-related information;

[0047] Receiving a third message sent by the first entity. The third message is a message determined based on the registration decision-related information, and the third message includes the second model identifier and the registration decision.

[0048] In an implementation, the model is a common model.

[0049] In an implementation, the model information includes at least one of the following: model type, model modality, model algorithm, model accuracy, model security, model privacy, model description information, model deployment requirements, model inference performance, model open range, model version, model owner information, or automated deployment script.

[0050] In an implementation, the model description information includes at least one of the following: model accuracy rate, variance of the model accuracy rate, data input format, data output format, model size, full model identifier corresponding to the compressed model, number of model parameters, model recall rate, or model F1 value;

[0051] The model deployment requirements include at least one of the following: model dependencies, minimum resource requirements, or recommended resource configurations. The resources include computing power resources and storage resources.

[0052] In an implementation, the first model information further includes at least one of the following: model application scenario, model segmentation information, model compression information, or model training information.

[0053] In one implementation, the model training information includes at least one of the following: a training data set, metadata corresponding to the training data set, a data preprocessing method, model features, model hyperparameters, or a model structure.

[0054] In one implementation, the method further includes:

[0055] Sending second indication information to the first entity, where the second indication information includes the first model identifier, the second model identifier, and a model information template.

[0056] In one implementation, the method further includes:

[0057] Receiving a fourth message sent by the first entity, where the fourth message is used to request storing the model, and the fourth message includes at least one of the following: the second model identifier, a model transmission method, a model security certificate, a model address, or the model;

[0058] Responding to the fourth message by sending a fifth message to the first entity, where the fifth message is used to indicate a model storage result.

[0059] In one implementation, the method further includes:

[0060] Receiving the model.

[0061] In one implementation, the method further includes:

[0062] Sending a tenth message to a third entity;

[0063] Receiving an eleventh message sent by the third entity in response to the tenth message;

[0064] Or,

[0065] Sending a tenth message to a fourth entity;

[0066] Receiving an eleventh message sent by the fourth entity in response to the tenth message;

[0067] The tenth message is used to request storing the model, and the tenth message includes at least one of the following: the second model identifier, a model transmission method, a model security certificate, or the model; the eleventh message is used to indicate a model storage result.

[0068] In one implementation, the method further includes:

[0069] Sending the model to the third entity or the fourth entity.

[0070] In one implementation, the method further includes:

[0071] Receive a sixth message sent by the first entity, where the sixth message includes the second model identifier and model update information;

[0072] In response to the sixth message, send a seventh message to the first entity, where the seventh message is used to indicate the model update result.

[0073] In one implementation, the method further includes:

[0074] Receive an eighth message sent by the first entity, where the eighth message is used to request verification of the model, and the eighth message includes the second model identifier and the model;

[0075] In response to the eighth message, send a ninth message to the first entity, where the ninth message is used to indicate the model verification result.

[0076] In a third aspect, an embodiment of the present application provides a model registration method applied to a third entity, and the method includes:

[0077] Receive a model storage request message, where the model storage request message includes at least one of the following: a second model identifier, a model transmission method, a model security certificate, a model address, or a model. The second model identifier is a network identifier assigned by the second entity to the model, and the model storage request message is a fourth message sent by the first entity, a tenth message sent by the second entity, or a twelfth message sent by the fourth entity;

[0078] Send a model storage response message, where the model storage response message is used to indicate the model storage result, and the storage response message is a fifth message sent to the first entity, an eleventh message sent to the second entity, or a thirteenth message sent to the fourth entity.

[0079] In one implementation, the method further includes:

[0080] Receive the model.

[0081] In one implementation, the method further includes:

[0082] Receive an eighth message sent by the first entity, where the eighth message is used to request verification of the model, and the eighth message includes the second model identifier and the model;

[0083] In response to the eighth message, send a ninth message to the first entity, where the ninth message is used to indicate the model verification result.

[0084] In a fourth aspect, an embodiment of the present application provides a model registration method applied to a fourth entity, and the method includes:

[0085] Receive an eighth message sent by a first entity, where the eighth message is used to request model verification, and the eighth message includes a second model identifier and the model, and the second model identifier is a network identifier assigned by a second entity to the model;

[0086] In response to the eighth message, send a ninth message to the first entity, where the ninth message is used to indicate the model verification result.

[0087] In one implementation, the method further includes:

[0088] Receive a tenth message sent by the second entity, where the tenth message is used to request storing the model, and the tenth message includes the second model identifier;

[0089] In response to the tenth message, send an eleventh message to the second entity, where the eleventh message is used to indicate the model storage result.

[0090] In one implementation, the method further includes:

[0091] Send a twelfth message to a third entity, where the twelfth message is used to request storing the model, and the twelfth message includes at least one of the following: the second model identifier, the model transmission method, the model security certificate, or the model;

[0092] Receive a thirteenth message sent by the third entity, where the thirteenth message is used to indicate the model storage result.

[0093] In a fifth aspect, an embodiment of the present application provides a model registration device, which is applied to a first entity, and the device includes:

[0094] A first sending unit, configured to send a first message to a second entity, where the first message is used to request model registration, and the first message includes a first model identifier and / or model information, and the first model identifier is an identifier of the model in the first entity;

[0095] A first receiving unit, configured to receive a second message sent by the second entity in response to the first message, where the second message includes a second model identifier and first indication information, the second model identifier is a network identifier assigned by the second entity to the model, and the first indication information indicates a registration decision or registration decision-related information;

[0096] A second sending unit, configured to send a third message to the second entity based on the registration decision-related information, where the third message includes the second model identifier and the registration decision.

[0097] In one implementation, the model is a public model.

[0098] In one embodiment, the model information includes at least one of the following: model type, model modality, model algorithm, model accuracy, model security, model privacy, model description information, model deployment requirements, model inference performance, model open range, model version, model owner information, or automated deployment script.

[0099] In one embodiment, the model description information includes at least one of the following: model accuracy rate, variance of the model accuracy rate, data input format, data output format, model size, full model identifier corresponding to the compressed model, number of model parameters, model recall rate, or model F1 value;

[0100] The model deployment requirements include at least one of the following: model dependencies, minimum resource requirements, or recommended resource configurations, where the resources include computing power resources and storage resources.

[0101] In one embodiment, the model information further includes at least one of the following: model application scenario, model segmentation information, model compression information, or model training information.

[0102] In one embodiment, the model training information includes at least one of the following: training data set, metadata corresponding to the training data set, data preprocessing method, model features, model hyperparameters, or model structure.

[0103] In one embodiment, the apparatus further includes:

[0104] A second receiving unit, configured to receive second indication information sent by the second entity, where the second indication information includes the first model identifier, the second model identifier, and a model information template.

[0105] In one embodiment, the apparatus further includes:

[0106] A third sending unit, configured to send a fourth message to the second entity;

[0107] A third receiving unit, configured to receive a fifth message sent by the second entity in response to the fourth message;

[0108] Or,

[0109] A third sending unit, configured to send a fourth message to a third entity;

[0110] A third receiving unit, configured to receive a fifth message sent by the third entity in response to the fourth message;

[0111] Wherein, the fourth message is used to request storing the model, and the fourth message includes at least one of the following: the second model identifier, model transmission mode, model security certificate, model address, or the model; the fifth message is used to indicate the model storage result.

[0112] In one embodiment, the apparatus further includes:

[0113] A fourth sending unit, configured to send the model to the second entity or the third entity.

[0114] In one embodiment, the apparatus further includes:

[0115] A fifth sending unit, configured to send a sixth message to the second entity, where the sixth message includes the second model identifier and model update information;

[0116] A fourth receiving unit, configured to receive a seventh message sent by the second entity in response to the sixth message, where the seventh message is used to indicate the model update result.

[0117] In one embodiment, the apparatus further includes:

[0118] A sixth sending unit, configured to send an eighth message to the second entity;

[0119] A fifth receiving unit, configured to receive a ninth message sent by the second entity in response to the eighth message;

[0120] Or,

[0121] A sixth sending unit, configured to send an eighth message to the third entity;

[0122] A fifth receiving unit, configured to receive a ninth message sent by the third entity in response to the eighth message;

[0123] Or,

[0124] A sixth sending unit, configured to send an eighth message to the fourth entity;

[0125] A fifth receiving unit, configured to receive a ninth message sent by the fourth entity in response to the eighth message;

[0126] Wherein, the eighth message is used to request verifying the model, and the eighth message includes the second model identifier and the model; the ninth message is used to indicate the model verification result.

[0127] In one embodiment, the first entity is a first terminal, a first access network device, or a first core network device;

[0128] The second entity is deployed in a second terminal, a second access network device, or a second core network device;

[0129] The third entity is deployed in a third terminal, a third access network device, or a third core network device;

[0130] The fourth entity is deployed in a fourth access network device or a fourth core network device;

[0131] The first terminal, the second terminal, and the third terminal are the same or different from each other, the first access network device, the second access network device, the third access network device, and the fourth access network device are the same or different from each other, and the first core network device, the second core network device, the third core network device, and the fourth core network device are the same or different from each other.

[0132] In a sixth aspect, an embodiment of the present application provides a model registration device, which is applied to a second entity. The device includes:

[0133] A first receiving unit, configured to receive a first message sent by a first entity. The first message is used to request model registration. The first message includes a first model identifier and / or model information. The first model identifier is the identifier of the model in the first entity;

[0134] A first sending unit, configured to send a second message to the first entity in response to the first message. The second message includes a second model identifier and first indication information. The second model identifier is the network identifier assigned by the second entity to the model. The first indication information indicates a registration decision or registration decision-related information;

[0135] A second receiving unit, configured to receive a third message sent by the first entity. The third message is a message determined based on the registration decision-related information. The third message includes the second model identifier and a registration decision.

[0136] In one implementation, the model is a common model.

[0137] In one implementation, the model information includes at least one of the following: model type, model modality, model algorithm, model accuracy, model security, model privacy, model description information, model deployment requirements, model inference performance, model open range, model version, model owner information, or automated deployment script.

[0138] In one implementation, the model description information includes at least one of the following: model accuracy rate, variance of model accuracy rate, data input format, data output format, model size, full model identifier corresponding to the compressed model, number of model parameters, model recall rate, or model F1 value;

[0139] The model deployment requirements include at least one of the following: model dependencies, minimum resource requirements, or recommended resource configurations, where the resources include computing power resources and storage resources.

[0140] In one implementation, the first model information further includes at least one of the following: model application scenarios, model segmentation information, model compression information, or model training information.

[0141] In one implementation, the model training information includes at least one of the following: training data sets, metadata corresponding to the training data sets, data preprocessing methods, model features, model hyperparameters, or model structures.

[0142] In one implementation, the device further includes:

[0143] A second sending unit, configured to send second indication information to the first entity, where the second indication information includes the first model identifier, the second model identifier, and a model information template.

[0144] In one implementation, the device further includes:

[0145] A third receiving unit, configured to receive a fourth message sent by the first entity, where the fourth message is used to request storing the model, and the fourth message includes at least one of the following: the second model identifier, model transmission method, model security certificate, model address, or the model;

[0146] A third sending unit, configured to send a fifth message to the first entity in response to the fourth message, where the fifth message is used to indicate the model storage result.

[0147] In one implementation, the device further includes:

[0148] A fourth receiving unit, configured to receive the model.

[0149] In one implementation, the device further includes:

[0150] A fourth sending unit, configured to send a tenth message to a third entity;

[0151] A fifth receiving unit, configured to receive an eleventh message sent by the third entity in response to the tenth message;

[0152] Or,

[0153] A fourth sending unit, configured to send a tenth message to a fourth entity;

[0154] A fifth receiving unit, configured to receive an eleventh message sent by the fourth entity in response to the tenth message;

[0155] The tenth message is used to request storing the model, and the tenth message includes at least one of the following: the second model identifier, the model transmission method, the model security certificate, or the model; the eleventh message is used to indicate the model storage result.

[0156] In one embodiment, the device further includes:

[0157] A fifth sending unit, configured to send the model to the third entity or the fourth entity.

[0158] In one embodiment, the device further includes:

[0159] A sixth receiving unit, configured to receive a sixth message sent by the first entity, where the sixth message includes the second model identifier and model update information;

[0160] A sixth sending unit, configured to send a seventh message to the first entity in response to the sixth message, where the seventh message is used to indicate the model update result.

[0161] In one embodiment, the device further includes:

[0162] A seventh receiving unit, configured to receive an eighth message sent by the first entity, where the eighth message is used to request to verify the model, and the eighth message includes the second model identifier and the model;

[0163] A seventh sending unit, configured to send a ninth message to the first entity in response to the eighth message, where the ninth message is used to indicate the model verification result.

[0164] In a seventh aspect, an embodiment of the present application provides a model registration device, which is applied to a third entity, and the device includes:

[0165] A first receiving unit, configured to receive a model storage request message, where the model storage request message includes at least one of the following: a second model identifier, a model transmission method, a model security certificate, a model address, or a model, the second model identifier is a network identifier assigned by a second entity to the model, and the model storage request message is a fourth message sent by a first entity, a tenth message sent by the second entity, or a twelfth message sent by a fourth entity;

[0166] A first sending unit, configured to send a model storage response message, where the model storage response message is used to indicate the model storage result, and the storage response message is a fifth message sent to the first entity, an eleventh message sent to the second entity, or a thirteenth message sent to the fourth entity.

[0167] In one embodiment, the device further includes:

[0168] A second receiving unit, configured to receive the model.

[0169] In one embodiment, the apparatus further includes:

[0170] A third receiving unit, configured to receive an eighth message sent by a first entity, where the eighth message is used to request verification of the model, and the eighth message includes the second model identifier and the model;

[0171] A second sending unit, configured to send a ninth message to the first entity in response to the eighth message, where the ninth message is used to indicate a model verification result.

[0172] In an eighth aspect, an embodiment of the present application provides a model registration apparatus, which is applied to a fourth entity, and the apparatus includes:

[0173] A first receiving unit, configured to receive an eighth message sent by a first entity, where the eighth message is used to request verification of a model, the eighth message includes a second model identifier and the model, and the second model identifier is a network identifier assigned by a second entity to the model;

[0174] A first sending unit, configured to send a ninth message to the first entity in response to the eighth message, where the ninth message is used to indicate a model verification result.

[0175] In one embodiment, the apparatus further includes:

[0176] A second receiving unit, configured to receive a tenth message sent by the second entity, where the tenth message is used to request storage of the model, and the tenth message includes the second model identifier;

[0177] A second sending unit, configured to send an eleventh message to the second entity in response to the tenth message, where the eleventh message is used to indicate a model storage result.

[0178] In one embodiment, the apparatus further includes:

[0179] A third sending unit, configured to send a twelfth message to a third entity, where the twelfth message is used to request storage of the model, and the twelfth message includes at least one of the following: the second model identifier, a model transmission method, a model security certificate, or the model;

[0180] A third receiving unit, configured to receive a thirteenth message sent by the third entity, where the thirteenth message is used to indicate a model storage result.

[0181] In a ninth aspect, an embodiment of the present application provides a model registration apparatus, which is applied to a first entity, and the apparatus includes a memory, a transceiver, and a processor:

[0182] The memory is used to store computer programs; the transceiver is used to send and receive data under the control of the processor; the processor is used to read the computer programs in the memory and perform the following operations:

[0183] Send a first message to a second entity, where the first message is used to request model registration, and the first message includes a first model identifier and / or model information, and the first model identifier is the identifier of the model in the first entity;

[0184] Receive a second message sent by the second entity in response to the first message, where the second message includes a second model identifier and first indication information, the second model identifier is the network identifier assigned by the second entity to the model, and the first indication information indicates a registration decision or registration decision-related information;

[0185] Based on the registration decision-related information, send a third message to the second entity, where the third message includes the second model identifier and the registration decision.

[0186] In one embodiment, the model is a common model.

[0187] In one embodiment, the model information includes at least one of the following: model type, model modality, model algorithm, model accuracy, model security, model privacy, model description information, model deployment requirements, model inference performance, model open range, model version, model owner information, or automated deployment script.

[0188] In one embodiment, the model description information includes at least one of the following: model accuracy rate, variance of model accuracy rate, data input format, data output format, model size, full model identifier corresponding to the compressed model, number of model parameters, model recall rate, or model F1 value;

[0189] The model deployment requirements include at least one of the following: model dependencies, minimum resource requirements, or recommended resource configurations, where the resources include computing power resources and storage resources.

[0190] In one embodiment, the model information further includes at least one of the following: model application scenario, model segmentation information, model compression information, or model training information.

[0191] In one embodiment, the model training information includes at least one of the following: training data set, metadata corresponding to the training data set, data preprocessing method, model features, model hyperparameters, or model structure.

[0192] In one embodiment, the processor is further used to perform the following operations:

[0193] Receive the second indication information sent by the second entity, where the second indication information includes the first model identifier, the second model identifier, and the model information template.

[0194] In one implementation, the processor is further configured to perform the following operations:

[0195] Send a fourth message to the second entity;

[0196] Receive a fifth message sent by the second entity in response to the fourth message;

[0197] Or,

[0198] Send a fourth message to a third entity;

[0199] Receive a fifth message sent by the third entity in response to the fourth message;

[0200] Wherein, the fourth message is used to request storing the model, and the fourth message includes at least one of the following: the second model identifier, the model transmission method, the model security certificate, the model address, or the model; the fifth message is used to indicate the model storage result.

[0201] In one implementation, the processor is further configured to perform the following operations:

[0202] Send the model to the second entity or the third entity.

[0203] In one implementation, the processor is further configured to perform the following operations:

[0204] Send a sixth message to the second entity, where the sixth message includes the second model identifier and model update information;

[0205] Receive a seventh message sent by the second entity in response to the sixth message, where the seventh message is used to indicate the model update result.

[0206] In one implementation, the processor is further configured to perform the following operations:

[0207] Send an eighth message to the second entity;

[0208] Receive a ninth message sent by the second entity in response to the eighth message;

[0209] Or,

[0210] Send an eighth message to a third entity;

[0211] Receive a ninth message sent by the third entity in response to the eighth message;

[0212] Or,

[0213] Send an eighth message to a fourth entity;

[0214] Receive a ninth message sent by the fourth entity in response to the eighth message;

[0215] Wherein, the eighth message is used to request verification of the model, and the eighth message includes the second model identifier and the model; the ninth message is used to indicate the model verification result.

[0216] In a tenth aspect, an embodiment of the present application provides a model registration device, which is applied to a second entity. The device includes a memory, a transceiver, and a processor:

[0217] The memory is used to store computer programs; the transceiver is used to send and receive data under the control of the processor; the processor is used to read the computer programs in the memory and perform the following operations:

[0218] Receive a first message sent by a first entity. The first message is used to request model registration, and the first message includes a first model identifier and / or model information. The first model identifier is the identifier of the model in the first entity;

[0219] Respond to the first message by sending a second message to the first entity. The second message includes a second model identifier and first indication information. The second model identifier is the network identifier assigned by the second entity to the model, and the first indication information indicates a registration decision or registration decision-related information;

[0220] Receive a third message sent by the first entity. The third message is a message determined based on the registration decision-related information, and the third message includes the second model identifier and the registration decision.

[0221] In one implementation, the model is a common model.

[0222] In one implementation, the model information includes at least one of the following: model type, model modality, model algorithm, model accuracy, model security, model privacy, model description information, model deployment requirements, model inference performance, model open range, model version, model owner information, or automated deployment script.

[0223] In one implementation, the model description information includes at least one of the following: model accuracy rate, variance of the model accuracy rate, data input format, data output format, model size, full model identifier corresponding to the compressed model, number of model parameters, model recall rate, or model F1 value;

[0224] The model deployment requirements include at least one of the following: model dependencies, minimum resource requirements, or recommended resource configurations, where the resources include computing power resources and storage resources.

[0225] In one implementation, the model information further includes at least one of the following: model application scenarios, model segmentation information, model compression information, or model training information.

[0226] In one implementation, the model training information includes at least one of the following: training data sets, metadata corresponding to the training data sets, data preprocessing methods, model features, model hyperparameters, or model structures.

[0227] In one implementation, the processor is further configured to perform the following operations:

[0228] Send second indication information to the first entity, where the second indication information includes the first model identifier, the second model identifier, and a model information template.

[0229] In one implementation, the processor is further configured to perform the following operations:

[0230] Receive a fourth message sent by the first entity, where the fourth message is used to request storing the model, and the fourth message includes at least one of the following: the second model identifier, model transmission method, model security certificate, model address, or the model;

[0231] Send a fifth message in response to the fourth message to the first entity, where the fifth message is used to indicate the model storage result.

[0232] In one implementation, the processor is further configured to perform the following operations:

[0233] Receive the model.

[0234] In one implementation, the processor is further configured to perform the following operations:

[0235] Send a tenth message to a third entity;

[0236] Receive an eleventh message sent by the third entity in response to the tenth message;

[0237] Or,

[0238] Send a tenth message to a fourth entity;

[0239] Receive an eleventh message sent by the fourth entity in response to the tenth message;

[0240] The tenth message is used to request storing the model, and the tenth message includes at least one of the following: the second model identifier, the model transmission method, the model security certificate, or the model; the eleventh message is used to indicate the model storage result.

[0241] In one implementation, the processor is further configured to perform the following operations:

[0242] Send the model to the third entity or the fourth entity.

[0243] In one implementation, the processor is further configured to perform the following operations:

[0244] Receive a sixth message sent by the first entity, where the sixth message includes the second model identifier and model update information;

[0245] In response to the sixth message, send a seventh message to the first entity, where the seventh message is used to indicate the model update result.

[0246] In one implementation, the processor is further configured to perform the following operations:

[0247] Receive an eighth message sent by the first entity, where the eighth message is used to request verifying the model, and the eighth message includes the second model identifier and the model;

[0248] In response to the eighth message, send a ninth message to the first entity, where the ninth message is used to indicate the model verification result.

[0249] In an eleventh aspect, an embodiment of the present application provides a model registration device applied to a third entity. The device includes a memory, a transceiver, and a processor:

[0250] The memory is used to store a computer program; the transceiver is used to send and receive data under the control of the processor; the processor is used to read the computer program in the memory and perform the following operations:

[0251] Receive a model storage request message, where the model storage request message includes at least one of the following: a second model identifier, a model transmission method, a model security certificate, a model address, or a model. The second model identifier is a network identifier assigned by a second entity to the model, and the model storage request message is a fourth message sent by a first entity, a tenth message sent by a second entity, or a twelfth message sent by a fourth entity;

[0252] Send a model storage response message, where the model storage response message is used to indicate the model storage result, and the storage response message is a fifth message sent to the first entity, an eleventh message sent to the second entity, or a thirteenth message sent to the fourth entity.

[0253] In one embodiment, the processor is further configured to perform the following operations:

[0254] Receive the model.

[0255] In one embodiment, the processor is further configured to perform the following operations:

[0256] Receive an eighth message sent by a first entity, where the eighth message is used to request verification of the model, and the eighth message includes the second model identifier and the model;

[0257] In response to the eighth message, send a ninth message to the first entity, where the ninth message is used to indicate the model verification result.

[0258] In a twelfth aspect, an embodiment of the present application provides a model registration device, which is applied to a fourth entity. The device includes a memory, a transceiver, and a processor:

[0259] The memory is used to store a computer program; the transceiver is used to send and receive data under the control of the processor; the processor is used to read the computer program in the memory and perform the following operations:

[0260] Receive an eighth message sent by a first entity, where the eighth message is used to request verification of a model, and the eighth message includes a second model identifier and the model, and the second model identifier is a network identifier assigned by a second entity to the model;

[0261] In response to the eighth message, send a ninth message to the first entity, where the ninth message is used to indicate the model verification result.

[0262] In one embodiment, the processor is further configured to perform the following operations:

[0263] Receive a tenth message sent by the second entity, where the tenth message is used to request storage of the model, and the tenth message includes the second model identifier;

[0264] In response to the tenth message, send an eleventh message to the second entity, where the eleventh message is used to indicate the model storage result.

[0265] In one embodiment, the processor is further configured to perform the following operations:

[0266] Send a twelfth message to a third entity, where the twelfth message is used to request storage of the model, and the twelfth message includes at least one of the following: the second model identifier, the model transmission method, the model security certificate, or the model;

[0267] Receive a thirteenth message sent by the third entity, where the thirteenth message is used to indicate the model storage result.

[0268] In a thirteenth aspect, an embodiment of the present application provides a non-transitory readable storage medium storing a computer program for causing a processor to execute the method according to any one of the first aspect.

[0269] In a fourteenth aspect, an embodiment of the present application provides a non-transitory readable storage medium storing a computer program for causing a processor to execute the method according to any one of the second aspect.

[0270] In a fifteenth aspect, an embodiment of the present application provides a non-transitory readable storage medium storing a computer program for causing a processor to execute the method according to any one of the third aspect.

[0271] In a sixteenth aspect, an embodiment of the present application provides a non-transitory readable storage medium storing a computer program for causing a processor to execute the method according to any one of the fourth aspect.

[0272] An embodiment of the present application provides a model registration method, apparatus, and storage medium. The method includes: a first entity sending a first message to a second entity, where the first message is used to request model registration, and the first message includes a first model identifier and / or model information, and the first model identifier is the identifier of the model in the first entity; receiving a second message sent by the second entity in response to the first message, where the second message includes a second model identifier and a first indication information, the second model identifier is the network identifier assigned by the second entity to the model, and the first indication information indicates a registration decision or registration decision-related information; based on the registration decision-related information, sending a third message to the second entity, where the third message includes the second model identifier and a registration decision. By adding a model registration function and corresponding registration process in the network, the network can provide services such as public model registration for users, networks, or third parties as needed, providing a basis for intelligent in-situ.

[0273] It should be understood that the content described in the above invention content part is not intended to limit the key or important features of the embodiments of the present invention, nor is it used to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. Description of the Drawings

[0274] To more clearly illustrate the technical solutions in the present application or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0275] Figure 1 It is a schematic diagram of an architecture of a communication system in the related art;

[0276] Figure 2 It is a schematic diagram of an architecture of a communication system provided by an embodiment of the present application;

[0277] Figure 3 It is another schematic diagram of an architecture of a communication system provided by an embodiment of the present application;

[0278] Figure 4 It is the flow of a model registration method provided by an embodiment of the present application Figure 1 ;

[0279] Figure 5 It is a flowchart of a model verification method provided by an embodiment of the present application;

[0280] Figure 6 It is a flowchart of a model storage method provided by an embodiment of the present application;

[0281] Figure 7 It is a flowchart of a model update method provided by an embodiment of the present application;

[0282] Figure 8 It is the flow of a model registration method provided by an embodiment of the present application Figure 2 ;

[0283] Figure 9 It is the flow of a model registration method provided by an embodiment of the present application Figure 3 ;

[0284] Figure 10 It is the flow of a model registration method provided by an embodiment of the present application Figure 4 ;

[0285] Figure 11 It is the flow of a model registration method provided by an embodiment of the present application Figure 5 ;

[0286] Figure 12 It is the flow of a model registration method provided by an embodiment of the present application Figure 6 ;

[0287] Figure 13 It is the flow of a model registration method provided by an embodiment of the present application Figure 7 ;

[0288] Figure 14 It is a schematic diagram of the structure of a model registration device 1400 provided by an embodiment of the present application;

[0289] Figure 15Schematic diagram of the model registration device 1500 provided by an embodiment of the present application;

[0290] Figure 16 Schematic diagram of the model registration device 1600 provided by an embodiment of the present application;

[0291] Figure 17 Schematic diagram of the model registration device 1700 provided by an embodiment of the present application;

[0292] Figure 18 Schematic diagram of the model registration device 1800 provided by an embodiment of the present application;

[0293] Figure 19 Schematic diagram of the model registration device 1900 provided by an embodiment of the present application;

[0294] Figure 20 Schematic diagram of the model registration device 2000 provided by an embodiment of the present application;

[0295] Figure 21 Schematic diagram of the model registration device 2100 provided by an embodiment of the present application. Detailed implementation manners

[0296] In the embodiments of the present invention, the term "and / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B may represent: A exists alone, A and B exist simultaneously, and B exists alone. The character " / " generally represents an "or" relationship between the associated objects before and after.

[0297] In the embodiments of the present application, the term "a plurality of" refers to two or more, and other quantifiers are similar.

[0298] In the embodiments of the present application, descriptions such as "first" and "second" are only used for illustration and to distinguish the described objects, without an order, and do not represent a special limitation on the number of objects in the embodiments of the present application, and cannot constitute any limitation to the embodiments of the present application. For example, the first model identifier is the identifier of the model in the first entity, and the second model identifier is the identifier of the model in the network. Using descriptions such as "first" and "second" is only to distinguish different model identifiers, rather than indicating differences in the size, priority, or importance of these two model identifiers.

[0299] Next, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present application.

[0300] An embodiment of the present application provides a model registration method and apparatus for providing services such as public model registration for users, networks, or third parties as needed.

[0301] Among them, the method and the apparatus are based on the same application concept. Since the principles of solving problems by the method and the apparatus are similar, the implementation of the apparatus and the method can be referred to each other, and the repeated parts will not be elaborated.

[0302] The terminal device involved in the embodiment of the present application may be a device that provides voice and / or data connectivity to users, a handheld device with a wireless connection function, or other processing devices connected to a wireless modem, etc. In different systems, the name of the terminal device may also be different. For example, in a 5G system, the terminal device may be called a user equipment (UE). The wireless terminal device may be a USB storage device, other personal computer memory devices, and dongles, and may also communicate with one or more core networks (CNs) via a radio access network (RAN). The wireless terminal device may be a mobile terminal device, such as a mobile phone (or a "cellular" phone) and a computer with a mobile terminal device. For example, it may be a portable, pocket-sized, handheld, computer-integrated, or vehicle-mounted mobile device that exchanges language and / or data with the wireless access network. For example, personal communication service (PCS) phones, cordless phones, session initiated protocol (SIP) phones, wireless local loop (WLL) stations, personal digital assistants (PDAs), personal computers, tablet computers, machine-type communication (MTC) terminal devices, etc. The wireless terminal device may also be referred to as a system, a subscriber unit, a subscriber station, a mobile station, a mobile, a remote station, an access point, a remote terminal device, an access terminal device, a user terminal device, a user agent, a user device, and wireless access points and routers / modems that meet the limitations of this definition, which are not limited in the embodiment of the present application.

[0303] The access network device involved in the embodiments of the present application may be a base station, which may include multiple cells that provide services to terminals. Depending on specific application scenarios, the base station may also be referred to as an access point, or may be a device in the access network that communicates with wireless terminal devices through one or more sectors over the air interface, or other names. The network device can be used to mutually replace the received air frames and Internet Protocol (IP) packets, and act as a router between the wireless terminal device and the rest of the access network, where the rest of the access network may include an Internet Protocol (IP) communication network. The network device can also coordinate the management of the attributes of the air interface. For example, the network device involved in the embodiments of the present application may be an evolved network device (eNB or e-NodeB) in a Long Term Evolution (LTE) system, a 5G base station (gNB) in a 5G network architecture (next generation system), etc., or may also be a Home evolved Node B (HeNB), a relay node, a femto, a pico, a network test device, etc. The embodiments of the present application do not limit this. In some network architectures, the network device may include a centralized unit (CU) node and a distributed unit (DU) node, and the centralized unit and the distributed unit may also be geographically separated.

[0304] Figure 1 It is a schematic diagram of an architecture of a communication system in the related art. As Figure 1 shown, the architecture includes a terminal device, an access network device, a core network device, and a Data Network (DN) part.

[0305] Among them, the core network device can also be referred to as a core network element or a core network functional entity. As an example, the core network functional entity can include any one of the following: Policy Control Function (PCF) entity, Network Slice Selection Function (NSSF) entity, Unified Data Management (UDM) entity, Network Repository Function (NRF) entity, Session Management Function (SMF) entity, Access and Mobility Management Function (AMF) entity, and User Plane Function (UPF) entity. As an example, the functions of the above functional entities are as follows:

[0306] The PCF entity is mainly used for the unified policy framework that guides network behavior and provides policy rule information for control plane entities (such as AMF, SMF, etc.).

[0307] The AMF entity is mainly used for functions such as access control, mobility management, registration, and deregistration.

[0308] The SMF entity is mainly used for user plane network element selection, user plane network element redirection, IP address allocation for terminal devices, and establishment, modification, and release of sessions as well as Quality of Service (QoS) control.

[0309] The UPF entity is mainly used for receiving and forwarding user plane data. For example, the UPF entity can receive user plane data from the service server and send the user plane data to the terminal device through the access network device. The UPF entity can also receive user plane data from the terminal device through the access network device and forward it to the service server.

[0310] The NSSF entity is mainly used for network slice selection.

[0311] The UDM entity is mainly used for the subscription data management of terminal devices, including the storage and management of terminal device identifiers, access authorization of terminal devices, etc.

[0312] The data network part can be a data network that provides business services for users. Generally, the client is located at the terminal device, and the server is located in the data network. The data network can be a private network, such as a local area network, or an external network not controlled by the operator, such as the Internet, or a proprietary network jointly deployed by operators.

[0313] The network architecture of the current 5G mobile communication system can be as Figure 1 shown. Similar to previous generations of mobile communication systems, it is designed centered around connection and data transmission, and can only provide users with connection and data transmission services, but cannot provide intelligent endogenous services such as model registration services and model storage services.

[0314] Based on the technical problems in the prior art, the embodiments of the present application provide a model registration method, which can construct a common model registration process through the interaction among multiple entities in a communication system, so that the communication system can provide services such as common model registration and storage for users, networks or third parties as needed.

[0315] In the embodiments of the present application, providing a common model registration service through a communication system may refer to completing the common model registration process through the interaction among multiple entities in the communication system; the common model registration service may refer to the entire common model registration process.

[0316] The architecture of the communication system provided by the embodiments of the present application can be as Figure 2 or Figure 3 shown, where Figure 2 the architecture shown is the architecture after the RAN is service-oriented, Figure 3 and the architecture shown is the architecture where the RAN is not service-oriented. As Figure 2 or Figure 3 shown, this architecture includes a Require Analysing Function (RAF) entity, a Network Adaptability Function (NAF) entity, a Network Collaboration Function (NCF) entity, at least one Network Execution Function (NEF) entity, a second entity, a third entity, and a fourth entity.

[0317] The RAF entity is mainly used to determine service requirements.

[0318] Exemplarily, the RAF entity can determine service requirements by receiving a user's request; the RAF entity can also sense changes in scenario requirements and determine service requirements by analyzing the sensed data; the RAF entity can also analyze current data / third-party data and historical data through an AI algorithm to determine service requirements.

[0319] The NAF entity can be used to determine a list of execution operations for a target service according to service requirements. The list of execution operations is a series of execution operations, and the execution operations include connection establishment and guarantee, task calculation, data processing, AI training / inference, etc.

[0320] The NCF entity can be used to coordinate the execution progress, functions, and / or resources of at least one NEF entity; it can also be used to determine the list of execution operations for the target service.

[0321] Each NEF entity can be used to implement a type of function, such as a control plane network function, a user plane network function, a data plane network function, a computing network function, etc. That is, a NEF entity can execute a single network service operation, such as connection establishment, data calculation, etc.; it can also execute collaborative operations to complete the provision of complex services, such as the establishment of a subnet, AI joint training, etc. In other words, the execution operations of a service can be executed by a single NEF entity or by multiple NEF entities in collaboration.

[0322] The second entity is mainly used for the registration of various AI models.

[0323] The second entity can also be referred to as the AI Model Registration Function (AIMRF) entity.

[0324] The third entity is mainly used for storing AI models, and the AI models stored in the third entity are the AI models that have been successfully registered in the second entity.

[0325] The third entity can also be referred to as the AI Model Storage Function (AIMSF) entity.

[0326] The fourth entity is mainly used for verifying the security, privacy protection, and performance of AI models.

[0327] The fourth entity can also be referred to as the AI Model Authentication Function (AIMAF) entity.

[0328] The second entity can be deployed on a second terminal, a second access network device, or a second core network device; the third entity can be deployed on a third terminal, a third access network device, or a third core network device; the fourth entity is deployed on a fourth access network device or a fourth core network device; the second terminal and the third terminal can be the same or different from each other, the second access network device, the third access network device, and the fourth access network device can be the same or different from each other, and the second core network device, the third core network device, and the fourth core network device can be the same or different from each other.

[0329] When the second entity is deployed on the second terminal, it can be deployed on the second terminal through software, through hardware, or through a combination of software and hardware.

[0330] When the third entity is deployed on the third terminal, it can be deployed on the third terminal through software, or through hardware, or through a combination of software and hardware.

[0331] When the above-mentioned entity is deployed on the access network device, it may mean that the above-mentioned entity is deployed on existing functional entities such as a Network Function (NF) entity and an Operation Administration and Maintenance (OAM) entity, or the above-mentioned entity can be deployed as a separate device in the access network.

[0332] When the above-mentioned entity is deployed on the core network device, it may mean that the above-mentioned entity is deployed on existing functional entities such as an NF entity and an OAM entity, or the above-mentioned entity can be deployed as a separate device in the core network.

[0333] The architecture of the communication system according to the embodiments of the present application not only includes the above-mentioned entities, but may also include other functional entities, such as a Network-resource Registration and Collection Function (NRCF) entity (which can be used to register network resources and receive updates on the status of network function resources), a Network Service Policy Function (NSPF) entity (which can be used to generate QoS metric parameters and save QoS metric parameters generated by other network elements), a PCF entity, an AMF entity, an SMF entity, and / or a UPF entity. The embodiments of the present application do not limit this.

[0334] It should be noted that the names of the above entities are only examples. The embodiments of the present application do not limit the specific names of each entity. As long as the functions implemented are the same or similar, they can be considered the same entity.

[0335] Based on the above communication system architecture, how multiple entities in the architecture interact to achieve the on-demand supply of services such as model registration will be described in detail below.

[0336] Figure 4 The flow of the model registration method provided by the embodiments of the present application Figure 1 . As Figure 4 shown, the method includes:

[0337] S401. The first entity sends a first message to the second entity, and the first message is used to request model registration.

[0338] In other words, the second entity receives the first message sent by the first entity.

[0339] The first entity may be a first terminal, a first access network device, or a first core network device.

[0340] The first terminal, the second terminal, and the third terminal may be the same or different from each other, the first access network device, the second access network device, the third access network device, and the fourth access network device may be the same or different from each other, and the first core network device, the second core network device, the third core network device, and the fourth core network device may be the same or different from each other.

[0341] When the first entity is a first access network device, it may be an OAM deployed in the access network or an NF deployed in the access network.

[0342] When the first entity is a first core network device, it may be an OAM deployed in the core network or an NF deployed in the core network.

[0343] The model may be an existing model in the first entity or a model trained by the first entity.

[0344] In one possible implementation, the model in the embodiments of the present application may be a common model.

[0345] Exemplarily, the model may be a common AI model.

[0346] The first message may also be referred to as a model registration request message.

[0347] The first message may include a first model identifier and / or model information.

[0348] Exemplarily, the first message includes a first model identifier and model information.

[0349] In another example, the first message includes a first model identifier.

[0350] In one possible implementation, when the first message includes a first model identifier, after receiving the first message, the second entity may send second indication information to the first entity, and the second indication information may include a first model identifier, a second model identifier, and a model information template.

[0351] The second indication information may indicate the model information that the first entity needs to report.

[0352] The first model identifier may be the identifier of the model in the first entity, and may also be referred to as the model local identifier.

[0353] The second model identifier may be the network identifier assigned by the second entity to the model.

[0354] After receiving the second indication information, the first entity may send the first message to the second entity again based on the model information template. At this time, the model information and the second model identifier are carried in the first message.

[0355] In a possible implementation, the model information may include at least one of the following: model type, model modality, model algorithm, model accuracy, model security, model privacy, model description information, model deployment requirements, model inference performance, model open range, model version, model owner information, or automated deployment script.

[0356] The model type may indicate that the model is a basic algorithm model or an industry-specific model, etc.

[0357] The model modality may include speech, text, image, multi-modal, etc.

[0358] The model algorithm may indicate the algorithm type of the model. The algorithm type may include supervised learning, deep learning, reinforcement learning, etc.; the model algorithm may also be used to indicate the model algorithm, and the model algorithm may include DeepQ-Leaning Network (DQN) algorithm, Support Vector Machine (SVM) algorithm, etc.

[0359] When the model algorithm type is reinforcement learning, the model algorithm may be the DQN algorithm; when the model algorithm type is supervised learning, the model algorithm may be the SVM algorithm.

[0360] The model accuracy may indicate the average accuracy rate of model inference.

[0361] The model security may describe the characteristics and capabilities of the model in terms of security protection, including model security authentication, security level, encryption algorithm, etc.

[0362] The model privacy may describe the characteristics and capabilities of the model in terms of privacy protection, including data privacy protection authentication, privacy protection level, etc.

[0363] The model inference performance may indicate the model performance under the recommended configuration.

[0364] Exemplarily, the model inference performance may include the single inference latency and / or the concurrent performance. Among them, the single inference latency may refer to the latency of a single model inference when the running recommended resources do not exceed 70%; the concurrent performance may refer to the maximum concurrent performance of the running recommended resources.

[0365] The model open range may indicate the open range of the model.

[0366] Exemplarily, the model open range can be public across the network, for internal network use, a group of users, etc.; among them, a group of users can refer to the users in a community, that is, the model is only open to the users in a certain community.

[0367] The model version can indicate the version of the model.

[0368] The model owner information can indicate the model owner.

[0369] The automated deployment script can indicate whether an automated deployment script is provided.

[0370] In one possible implementation, the model description information can include at least one of the following: model accuracy, variance of model accuracy, data input format, data output format, model size, full model identifier corresponding to the compressed model, number of model parameters, model recall rate, or model F1 value.

[0371] The model accuracy can indicate the average accuracy of the model.

[0372] The variance of model accuracy can refer to the degree of fluctuation of the model accuracy.

[0373] The model input format can indicate the format and structure of the model input data.

[0374] The model output format can indicate the format and structure of the model output data.

[0375] The model size can refer to the size of the model, and the units include KB, MB, GB, etc.

[0376] When the model is a compressed model, the model description information can include the full model identifier corresponding to the compressed model, which can be used to indicate the uncompressed model identifier.

[0377] The number of model parameters can indicate the number of model parameters.

[0378] The model recall rate can indicate the average recall rate of the model.

[0379] In one possible implementation, the model deployment requirements include at least one of the following: model dependencies, minimum resource requirements, or recommended resource configurations, where resources include computing power resources and storage resources.

[0380] The model dependencies can indicate the dependencies during model deployment.

[0381] Exemplarily, the model dependencies may include a dependency framework, a computing power type, and a dependency library [optional]. Among them, the dependency framework may indicate the framework on which the model depends and may also indicate the framework version; the computing power type may indicate the type of computing power used by the model, such as a Graphics Processing Unit (GPU), a Central Processing Unit (CPU), etc.; the dependency library may indicate the functional library on which the model depends.

[0382] The minimum resource requirements may indicate the minimum resource requirements for model inference.

[0383] Exemplarily, the minimum resource requirements may include minimum computing power resource requirements, minimum memory requirements, and minimum storage requirements; among them, the minimum computing power resource requirements may indicate the type and size of the computing power to be used during model inference, the minimum memory requirements may indicate the type and size of the memory to be used during model inference, and the minimum storage requirements may indicate the size of the storage to be used during model inference.

[0384] The recommended resource configuration may indicate the recommended configuration for model inference.

[0385] Exemplarily, the recommended resource configuration may include the recommended number of computing power resources, the recommended amount of memory, and the recommended amount of storage; among them, the recommended number of computing power resources may indicate the type and size of the computing power recommended for use during model inference, the recommended amount of memory may indicate the type and size of the memory recommended for use during model inference, and the recommended amount of storage may indicate the size of the storage recommended for use during model inference.

[0386] In a possible implementation, the model information may further include at least one of the following: model application scenario, model segmentation information, model compression information, or model training information.

[0387] The model application scenario may indicate the scenario in which the model is applied, including wireless communication, medical, education, transportation, etc.

[0388] The model application scenario may also indicate the model application field, and the model application field may indicate the field of the model in the corresponding scenario. For example, in the wireless communication scenario, the model application field may include resource scheduling, mobility management, etc. In the transportation scenario, the model application field may include image recognition, route navigation, etc.

[0389] The model segmentation information may indicate whether the model is a part after model segmentation or an unsegmented model.

[0390] The model compression information may indicate whether the model is a compressed model.

[0391] In a possible implementation, the model training information may include at least one of the following: training data set, metadata corresponding to the training data set, data preprocessing method, model features, model hyperparameters, or model structure.

[0392] The model training data set may indicate the data set information for model training and may include at least one of a data set identifier, a data set format, or a data set label name.

[0393] After receiving the model information, the second entity may query the model registration information saved by itself and may also query the third entity to check if there is already a model with the same performance.

[0394] Exemplarily, the model registration information may be as shown in Table 1:

[0395] Table 1 Model registration information

[0396]

[0397]

[0398]

[0399] The model information may be a part of the model registration information or may be all of the model registration information.

[0400] S402. In response to the first message, the second entity sends a second message to the first entity.

[0401] In other words, the first entity receives the second message sent by the second entity in response to the first message.

[0402] The second message may also be referred to as a model registration response message.

[0403] The second message may include a second model identifier and a first indication information.

[0404] In a possible implementation, if the first message includes a first model identifier and model information, the second message may further include the first model identifier.

[0405] The first indication information may indicate a registration decision or information related to the registration decision.

[0406] The registration decision may be registration, non-registration, or deregistration.

[0407] The information related to the registration decision may include a model query result.

[0408] If it is the second entity that decides whether to register, the first indication information indicates the registration decision.

[0409] If the first entity decides whether to register, the first indication information indicates information related to the registration decision. After receiving the first indication information, the first entity may execute S403.

[0410] S403. The first entity sends a third message to the second entity based on the information related to the registration decision.

[0411] In other words, the second entity receives the third message sent by the first entity.

[0412] The third message may include the second model identifier and the registration decision.

[0413] When the information related to the registration decision includes the model query result, if the model query result is that there is no similar model, the registration decision in the third message may be registration; if the model query result is that there is an existing similar model, the registration decision in the third message may be cancellation of registration.

[0414] In Figure 4 In the illustrated embodiment, the communication system constructs a common model registration process through the interaction between entities, enabling the communication system to provide common model registration services for users, networks, or third parties intelligently based on the common model registration requirements during the communication process.

[0415] Figure 4 The illustrated embodiment illustrates the common model registration process. Next, in combination with Figure 5 The common model verification process will be described in detail. Model verification can be performed before model registration or during the model registration process.

[0416] Figure 5 This is a flowchart of a model verification method provided by an embodiment of the present application. As Figure 5 shown, the method includes:

[0417] S501. The first entity sends an eighth message to the second entity, and the eighth message is used to request model verification.

[0418] In other words, the second entity receives the eighth message sent by the first entity.

[0419] The eighth message may also be referred to as a model verification request message.

[0420] The eighth message may include the second model identifier and the model.

[0421] After receiving the eighth message, the second entity may verify the performance, security, privacy protection, etc. of the model.

[0422] In the embodiment of the present application, the second entity has the functions of model registration and model verification.

[0423] S502. The second entity sends a ninth message to the first entity in response to the eighth message, and the ninth message is used to indicate the model verification result.

[0424] The ninth message can be referred to as a model verification response message.

[0425] The model verification result can be that the model verification passes or the model verification fails, etc.

[0426] In a possible implementation, if the model verification result is that the model verification passes, the ninth message may further include a model security certificate.

[0427] In Figure 5 Based on the embodiments shown, model verification can also be performed in the following various ways.

[0428] 1. The third entity performs model verification, that is, the first entity sends the eighth message to the third entity, and after the third entity verifies the model, it sends the ninth message to the first entity.

[0429] In this way, the third entity has the model verification function and the model storage function.

[0430] 2. The fourth entity performs model verification, that is, the first entity sends the eighth message to the fourth entity, and after the fourth entity verifies the model, it sends the ninth message to the first entity.

[0431] In this way, the third entity has the model verification function.

[0432] 3. The second entity initiates model verification, and the third entity performs model verification, that is, the second entity sends the eighth message to the third entity, and after the third entity verifies the model, it sends the ninth message to the second entity.

[0433] In this way, the third entity has the model verification function and the model storage function.

[0434] 4. The second entity initiates model verification, and the fourth entity performs model verification, that is, the second entity sends the eighth message to the fourth entity, and after the fourth entity verifies the model, it sends the ninth message to the second entity.

[0435] In this way, the third entity has the model verification function.

[0436] For the specific verification process and the content included in the eighth message and the ninth message, reference can be made to Figure 5 the relevant descriptions in the embodiments shown, which will not be elaborated here.

[0437] If the model verification is performed during the model registration process, the registration decision-related information may further include the model verification result.

[0438] In Figure 5 In the illustrated embodiment, the communication system constructs a common model verification process through the interaction between various entities, enabling the communication system to intelligently provide common model verification services for users, networks, or third parties based on common model verification requirements during the communication process.

[0439] Based on any of the above embodiments, hereinafter, in combination with Figure 6 the common model storage process will be described in detail.

[0440] Figure 6 It is a flowchart of a model storage method provided by an embodiment of the present application. As Figure 6 shown, the method includes:

[0441] S601. The first entity sends a fourth message to the second entity, and the fourth message is used to request to store a model.

[0442] In other words, the second entity receives the fourth message sent by the first entity.

[0443] The fourth message may be referred to as a model storage request message.

[0444] The fourth message may include at least one of the following: a second model identifier, a model transmission method, a model security certificate, a model address, or a model.

[0445] The model transmission method may be determined based on the model size.

[0446] The model address may be the storage address of the model.

[0447] If the model is carried in the fourth message, the second entity may directly execute S602; if the model is not carried in the fourth message and the model is stored locally, the first entity may send the model to the second entity, and the second entity executes S602 after receiving the model; if the model is not carried in the fourth message and the model is not stored locally, the model address may be carried in the fourth message, and the second entity may interact with the network element storing the model based on the model address to obtain the model, and the second entity executes S602 after receiving the model.

[0448] After receiving the model, the second entity stores the model.

[0449] In the embodiment of the present application, the second entity has a model registration function and a model storage function.

[0450] S602. The second entity sends a fifth message to the first entity in response to the fourth message.

[0451] In other words, the first entity receives the fifth message sent by the second entity in response to the fourth message.

[0452] The fifth message can be referred to as the model storage response message.

[0453] The fifth message can be used to indicate the model storage result.

[0454] The model storage result can be that the model storage is completed.

[0455] The fifth message can include the second model identifier and the model storage result.

[0456] In Figure 6 Based on the illustrated embodiments, model verification can also be performed in the following various ways:

[0457] 1. The third entity performs model storage, that is, the first entity sends the fourth message to the third entity, and after the third entity stores the model, it sends the fifth message to the first entity.

[0458] In this way, the third entity has the model storage function.

[0459] 2. The second entity initiates model storage and the third entity performs model storage, that is, the second entity sends the tenth message to the third entity, and after the third entity stores the model, it sends the eleventh message to the second entity.

[0460] In this way, the third entity has the model storage function and the model verification function.

[0461] Among them, the tenth message can be used to request storing the model.

[0462] The tenth message can be referred to as the model storage request message;

[0463] The tenth message can include at least one of the following: the second model identifier, the model transmission method, the model security certificate, or the model.

[0464] If the model is carried in the tenth message, the third entity can send the eleventh message to the second entity after storing the model; if the model is not carried in the tenth message and the model is stored locally, the second entity can send the model to the third entity, and the third entity sends the eleventh message to the second entity after receiving the model.

[0465] The eleventh message can be used to indicate the model storage result.

[0466] The eleventh message can be referred to as the model storage response message.

[0467] The eleventh message can include the second model identifier and the model storage result.

[0468] III. The second entity initiates model storage. After the fourth entity verifies it, the third entity performs model storage, that is, the second entity sends the tenth message to the fourth entity, the fourth entity sends the twelfth message to the third entity. After the third entity stores the model, it sends the thirteenth message to the fourth entity; the fourth entity sends the eleventh message to the second entity.

[0469] In this way, the fourth entity has the functions of model storage and model verification.

[0470] For the relevant descriptions of the tenth message and the eleventh message, reference can be made to the above-mentioned Method 2, which will not be elaborated here.

[0471] The twelfth message can be used to request model storage.

[0472] The twelfth message can be called the model storage request message;

[0473] The twelfth message may include at least one of the following: the second model identifier, the model transmission method, the model security certificate, or the model.

[0474] If the model is carried in the twelfth message, the third entity can send the thirteenth message to the fourth entity after storing the model; if the model is not carried in the twelfth message and the model is stored in the fourth entity, the fourth entity can send the model to the third entity, and the third entity sends the thirteenth message to the fourth entity after receiving the model.

[0475] The thirteenth message can be used to indicate the model storage result.

[0476] The thirteenth message can be called the model storage response message.

[0477] The thirteenth message may include the second model identifier and the model storage result.

[0478] In this way, the model in the fourth entity can be obtained during the model verification process.

[0479] In Figure 6 In the illustrated embodiment, the communication system constructs a common model storage process through the interaction between various entities, enabling the communication system to intelligently provide common model storage services for users, networks, or third parties based on common model storage requirements during communication.

[0480] Based on any of the above embodiments, below, in combination with Figure 7 The common model update process will be described in detail.

[0481] Figure 7 This is a flowchart of a model update method provided by an embodiment of the present application. As Figure 7 shown, the method includes:

[0482] S701. The first entity sends a sixth message to the second entity.

[0483] In other words, the second entity receives the sixth message sent by the first entity.

[0484] The sixth message can be used to indicate the registration information of the updated model.

[0485] The sixth message may include a second model identifier and model update information.

[0486] If the model information is part of the model registration information during model registration, the model update information can be used to complete the model registration information. At this time, the model update information includes the information that is not mentioned in the model information but exists in the model registration information.

[0487] If the first entity optimizes the registered model, the model update information includes the optimized model information.

[0488] S702. In response to the sixth message, the second entity sends a seventh message to the first entity.

[0489] In other words, the first entity receives the seventh message sent by the second entity in response to the sixth message.

[0490] The seventh message can be used to indicate the model update result.

[0491] The model update result may include that the model update is completed.

[0492] The seventh message may include a second model identifier and the model update result.

[0493] In Figure 7 In the illustrated embodiment, the communication system constructs a common model update process through the interaction between various entities, enabling the communication system to intelligently provide common model update services for users, networks, or third parties based on common model update requirements during communication.

[0494] The above-mentioned multiple embodiments and various methods can be combined arbitrarily.

[0495] Exemplarily, Figure 4 the illustrated embodiment is combined with Figure 5 the illustrated embodiment, Figure 4 the illustrated embodiment is combined with Figure 5 Method 1 below the illustrated embodiment, Figure 4 the illustrated embodiment is combined with Figure 5 Method 2 below the illustrated embodiment, Figure 4 the illustrated embodiment is combined with Figure 5 Method 3 below the illustrated embodiment, Figure 4 the illustrated embodiment is combined withFigure 5 Combination of Method 4 below the illustrated embodiment.

[0496] Another exemplary Figure 4 the illustrated embodiment, Figure 5 the illustrated embodiment and Figure 6 the illustrated embodiment are combined, Figure 4 the illustrated embodiment, Figure 5 Method 1 below the illustrated embodiment and Figure 6 the illustrated embodiment are combined, Figure 4 the illustrated embodiment, Figure 5 Method 2 below the illustrated embodiment and Figure 6 the illustrated embodiment are combined, Figure 4 the illustrated embodiment, Figure 5 Method 3 below the illustrated embodiment and Figure 6 the illustrated embodiment are combined, Figure 4 the illustrated embodiment, Figure 5 Method 4 below the illustrated embodiment and Figure 6 the illustrated embodiment are combined, Figure 4 the illustrated embodiment, Figure 5 the illustrated embodiment and Figure 6 Method 1 below the illustrated embodiment are combined, Figure 4 the illustrated embodiment, Figure 5 Method 1 below the illustrated embodiment and Figure 6 Method 1 below the illustrated embodiment are combined, Figure 4 the illustrated embodiment, Figure 5 Method 2 below the illustrated embodiment and Figure 6 Method 1 below the illustrated embodiment are combined, Figure 4 the illustrated embodiment, Figure 5 Method 3 below the illustrated embodiment and Figure 6 Method 1 below the illustrated embodiment are combined, Figure 4 the illustrated embodiment, Figure 5 Method 4 below the illustrated embodiment and Figure 6 Method 1 below the illustrated embodiment are combined, Figure 4 the illustrated embodiment, Figure 5 the illustrated embodiment and Figure 6 Method 2 below the illustrated embodiment are combined, Figure 4 the illustrated embodiment, Figure 5 Method 1 below the illustrated embodiment and Figure 6 Method 2 below the illustrated embodiment are combined, Figure 4 the illustrated embodiment, Figure 5 Method 2 below the illustrated embodiment and Figure 6 Method 2 below the illustrated embodiment are combined, Figure 4 the illustrated embodiment, Figure 5 Method 3 below the illustrated embodiment and Figure 6Combination of Method 2 below the illustrated embodiment Figure 4 the illustrated embodiment Figure 5 Combination of Method 4 below the illustrated embodiment and Figure 6 Combination of Method 2 below the illustrated embodiment Figure 4 the illustrated embodiment Figure 5 the illustrated embodiment and Figure 6 Combination of Method 3 below the illustrated embodiment Figure 4 the illustrated embodiment Figure 5 Combination of Method 1 below the illustrated embodiment and Figure 6 Combination of Method 3 below the illustrated embodiment Figure 4 the illustrated embodiment Figure 5 Combination of Method 2 below the illustrated embodiment and Figure 6 Combination of Method 3 below the illustrated embodiment Figure 4 the illustrated embodiment Figure 5 Combination of Method 3 below the illustrated embodiment and Figure 6 Combination of Method 3 below the illustrated embodiment Figure 4 the illustrated embodiment Figure 5 Combination of Method 4 below the illustrated embodiment and Figure 6 Combination of Method 3 below the illustrated embodiment

[0497] Another exemplary Figure 4 the illustrated embodiment Figure 5 the illustrated embodiment Figure 6 the illustrated embodiment and Figure 7 Combination with the illustrated embodiment Figure 4 the illustrated embodiment Figure 5 the illustrated embodiment Figure 6 Combination of Method 1 below the illustrated embodiment and Figure 7 Combination with the illustrated embodiment Figure 4 the illustrated embodiment Figure 5 the illustrated embodiment Figure 6 Combination of Method 2 below the illustrated embodiment and Figure 7 Combination with the illustrated embodiment Figure 4 the illustrated embodiment Figure 5 the illustrated embodiment Figure 6 Combination of Method 3 below the illustrated embodiment and Figure 7 Combination with the illustrated embodiment Figure 4 the illustrated embodiment Figure 5 Method 1 below the illustrated embodiment Figure 6 the illustrated embodiment and Figure 7 Combination with the illustrated embodiment Figure 4 the illustrated embodiment Figure 5 Method 1 below the illustrated embodiment Figure 6 Combination of Method 1 below the illustrated embodiment and Figure 7 Combination with the illustrated embodiment Figure 4 the illustrated embodiment Figure 5Method 1 below the illustrated embodiment Figure 6 Method 2 below the illustrated embodiment and Figure 7 the illustrated embodiment are combined, Figure 4 the illustrated embodiment, Figure 5 Method 1 below the illustrated embodiment, Figure 6 Method 3 below the illustrated embodiment and Figure 7 the illustrated embodiment are combined, Figure 4 the illustrated embodiment, Figure 5 Method 2 below the illustrated embodiment, Figure 6 the illustrated embodiment and Figure 7 the illustrated embodiment are combined, Figure 4 the illustrated embodiment, Figure 5 Method 2 below the illustrated embodiment, Figure 6 Method 1 below the illustrated embodiment and Figure 7 the illustrated embodiment are combined, Figure 4 the illustrated embodiment, Figure 5 Method 2 below the illustrated embodiment, Figure 6 Method 2 below the illustrated embodiment and Figure 7 the illustrated embodiment are combined, Figure 4 the illustrated embodiment, Figure 5 Method 2 below the illustrated embodiment, Figure 6 Method 3 below the illustrated embodiment and Figure 7 the illustrated embodiment are combined, Figure 4 the illustrated embodiment, Figure 5 Method 3 below the illustrated embodiment, Figure 6 the illustrated embodiment and Figure 7 the illustrated embodiment are combined, Figure 4 the illustrated embodiment, Figure 5 Method 3 below the illustrated embodiment, Figure 6 Method 1 below the illustrated embodiment and Figure 7 the illustrated embodiment are combined, Figure 4 the illustrated embodiment, Figure 5 Method 3 below the illustrated embodiment, Figure 6 Method 2 below the illustrated embodiment and Figure 7 the illustrated embodiment are combined, Figure 4 the illustrated embodiment, Figure 5 Method 3 below the illustrated embodiment, Figure 6 Method 3 below the illustrated embodiment and Figure 7 the illustrated embodiment are combined, Figure 4 the illustrated embodiment, Figure 5 Method 4 below the illustrated embodiment, Figure 6 the illustrated embodiment and Figure 7 the illustrated embodiment are combined, Figure 4 the illustrated embodiment, Figure 5 Method 4 below the illustrated embodiment, Figure 6The first method below the illustrated embodiment is combined with Figure 7 the illustrated embodiment, Figure 4 the illustrated embodiment, Figure 5 the fourth method below the illustrated embodiment, Figure 6 the second method below the illustrated embodiment is combined with Figure 7 the illustrated embodiment, Figure 4 the illustrated embodiment, Figure 5 the fourth method below the illustrated embodiment, Figure 6 the third method below the illustrated embodiment is combined with Figure 7 the illustrated embodiment.

[0498] Based on the above-mentioned multiple embodiments, several combined embodiments obtained by combining at least two of the above-mentioned multiple embodiments are shown below.

[0499] Embodiment 1, as Figure 8 shown, the method includes:

[0500] S801. A first entity sends a first message to a second entity, and the first message is used to request to register a model.

[0501] It should be noted that for the execution process of S801, reference can be made to the execution process of S401. The only difference is that the model information in the first message may include the necessary information of the model, and the necessary information may include the model type, model application scenario [optional], model modality, model algorithm, model accuracy, model description information, and model deployment requirements; alternatively, the model information in the first message may include some of the above necessary information; or, the model information in the first message carries all the information in the model registration information.

[0502] S802. Model query.

[0503] For the model query process, reference can be made to the relevant description in S401, which will not be elaborated here.

[0504] S803. Model verification.

[0505] For the model verification process, reference can be made to the relevant description in Figure 5 the illustrated embodiment, which will not be elaborated here.

[0506] S804. In response to the first message, the second entity sends a second message to the first entity, and the second message includes a first model identifier, a second model identifier, and registration decision-related information.

[0507] S805. Based on the registration decision-related information, the first entity sends a third message to the second entity, and the third message includes the second model identifier and the registration decision.

[0508] The execution process from S804 to S805 can refer to the execution process of S402 to S403, which will not be elaborated here.

[0509] S806. The first entity sends a fourth message to the third entity, and the fourth message is used to request to store a model.

[0510] The fourth message may include a second model identifier, a model transmission method, a model security certificate, a model address [optional], and a model [optional].

[0511] If the model is not carried in the fourth message, S807 can be executed; if the model is carried in the fourth message, S808 can be executed.

[0512] S807. Model transmission.

[0513] S808. In response to the fourth message, the third entity sends a fifth message to the first entity, and the fifth message includes a second model identifier and a model storage result.

[0514] It should be noted that the execution process from S806 to S808 can refer to the execution process of S601 to S602, which will not be elaborated here.

[0515] S809. The first entity sends a sixth message to the second entity, and the sixth message includes a second model identifier and model update information.

[0516] S810. In response to the sixth message, the second entity sends a seventh message to the first entity, and the seventh message includes a second model identifier and a model update result.

[0517] It should be noted that the execution process from S809 to S810 can refer to the execution process of S701 to S702, which will not be elaborated here.

[0518] Embodiment 2. As Figure 9 shown, the method includes:

[0519] S901. Model verification.

[0520] The model verification process can refer to the relevant description in the Figure 5 shown embodiment, which will not be elaborated here.

[0521] S902. The first entity sends a first message to the second entity, and the first message is used to request to register a model.

[0522] S903. Model query.

[0523] The execution process from S902 to S903 can refer to the execution process of S801 to S802, which will not be elaborated here.

[0524] S904. The second entity sends a second message to the first entity in response to the first message. The second message includes the first model identifier, the second model identifier, and registration decision-related information.

[0525] S905. The first entity sends a third message to the second entity based on the registration decision-related information. The third message includes the second model identifier and the registration decision.

[0526] S906. The first entity sends a fourth message to the third entity. The fourth message is used to request storing the model.

[0527] S907. Model transmission.

[0528] S908. The third entity sends a fifth message to the first entity in response to the fourth message. The fifth message includes the second model identifier and the model storage result.

[0529] S909. The first entity sends a sixth message to the second entity. The sixth message includes the second model identifier and the model update information.

[0530] S910. The second entity sends a seventh message to the first entity in response to the sixth message. The seventh message includes the second model identifier and the model update result.

[0531] It should be noted that the execution processes of S904 to S910 can refer to the execution processes of S804 to S810, which will not be elaborated here.

[0532] The difference between Embodiment 2 and Embodiment 1 is that model verification is completed before model registration.

[0533] Embodiment 3 is as follows Figure 10 As shown, the method includes:

[0534] S1001. The first entity sends a first message to the second entity. The first message is used to request registering the model.

[0535] S1002. Model query.

[0536] S1003. Model verification.

[0537] S1004. The second entity sends a second message to the first entity in response to the first message. The second message includes the first model identifier, the second model identifier, and registration decision-related information.

[0538] S1005. The first entity sends a third message to the second entity based on the registration decision-related information. The third message includes the second model identifier and the registration decision.

[0539] It should be noted that the execution processes of S1001 to S1005 can refer to the execution processes of S801 to S805, which will not be elaborated here.

[0540] S1006. The second entity sends a tenth message to the fourth entity. The tenth message is used to request to store a model, and the tenth message includes a second model identifier.

[0541] S1007. The fourth entity sends a twelfth message to the third entity. The twelfth message includes a second model identifier, a model transmission method, a model security certificate, and a model [optional].

[0542] If the model is not carried in the fourth message, S1008 can be executed. If the model is carried in the fourth message, S1009 can be executed.

[0543] S1008. Model transmission.

[0544] S1009. In response to the twelfth message, the third entity sends a thirteenth message to the fourth entity. The thirteenth message includes a second model identifier and a model storage result.

[0545] S1010. The fourth entity sends an eleventh message to the second entity. The eleventh message includes a second model identifier.

[0546] It should be noted that for the execution processes of S1006 to S1010, reference can be made to Figure 6 the relevant description of Model Verification Method 3 below the illustrated embodiment, which will not be elaborated here.

[0547] S1011. The first entity sends a sixth message to the second entity. The sixth message includes a second model identifier and model update information.

[0548] S1012. In response to the sixth message, the second entity sends a seventh message to the first entity. The seventh message includes a second model identifier and a model update result.

[0549] It should be noted that for the execution processes of S1011 to S1012, reference can be made to the execution processes of S701 to S702, which will not be elaborated here.

[0550] Embodiment 4. As Figure 11 shown, the method includes:

[0551] S1101. Model verification.

[0552] For the model verification process, reference can be made to Figure 5 the relevant description in the illustrated embodiment, which will not be elaborated here.

[0553] S1102. The first entity sends a first message to the second entity. The first message is used to request to register a model.

[0554] S1103. Model query.

[0555] S1104. The second entity sends a second message to the first entity in response to the first message. The second message includes the first model identifier, the second model identifier, and registration decision-related information.

[0556] S1105. The first entity sends a third message to the second entity based on the registration decision-related information. The third message includes the second model identifier and the registration decision.

[0557] S1106. The second entity sends a tenth message to the fourth entity. The tenth message is used to request storing the model. The tenth message includes the second model identifier.

[0558] S1107. The fourth entity sends a twelfth message to the third entity. The twelfth message includes the second model identifier, the model transmission method, the model security certificate, and the model [optional].

[0559] S1108. Model transmission.

[0560] S1109. The third entity sends a thirteenth message to the fourth entity in response to the twelfth message. The thirteenth message includes the second model identifier and the model storage result.

[0561] S1110. The fourth entity sends an eleventh message to the second entity. The eleventh message includes the second model identifier.

[0562] S1111. The first entity sends a sixth message to the second entity. The sixth message includes the second model identifier and model update information.

[0563] S1112. The second entity sends a seventh message to the first entity in response to the sixth message. The seventh message includes the second model identifier and the model update result.

[0564] It should be noted that for the execution processes of S1104 to S1112, reference can be made to the execution processes of S1004 to S1012, which will not be elaborated here.

[0565] The difference between Embodiment 4 and Embodiment 3 is that model verification is completed before model registration.

[0566] Embodiment 5, as Figure 12 shown, the method includes:

[0567] S1201. The first entity sends a first message to the second entity. The first message is used to request registering a model.

[0568] S1202. Model query.

[0569] S1203. Model verification.

[0570] S1204. The second entity sends a second message to the first entity in response to the first message. The second message includes the first model identifier, the second model identifier, and registration decision-related information.

[0571] S1205. The first entity sends a third message to the second entity based on the registration decision-related information. The third message includes the second model identifier and the registration decision.

[0572] S1206. The first entity sends a fourth message to the second entity. The fourth message is used to request storing the model.

[0573] S1207. Model transmission.

[0574] S1208. The second entity sends a fifth message to the first entity in response to the fourth message. The fifth message includes the second model identifier and the model storage result.

[0575] S1209. The first entity sends a sixth message to the second entity. The sixth message includes the second model identifier and the model update information.

[0576] S1210. The second entity sends a seventh message to the first entity in response to the sixth message. The seventh message includes the second model identifier and the model update result.

[0577] It should be noted that for the execution processes of S1201 to S1210, reference can be made to the execution processes of S801 to S810, which will not be elaborated here.

[0578] The difference between Embodiment 5 and Embodiment 1 is that the second entity has the model registration function and the model storage function.

[0579] When the second entity has the model registration function, the model storage function, and the model verification function, the model verification in S1203 is completed through the interaction between the first entity and the second entity.

[0580] When the third entity has the model storage function and the model verification function, the model verification in S1203 is completed through the interaction between the first entity and the third entity, and the model storage in S1206 to S1208 is completed through the interaction between the first entity and the third entity.

[0581] Embodiment 6. As Figure 13 shown, the method includes:

[0582] S1301. The first entity sends a first message to the second entity. The first message is used to request registering the model. The first message includes the first model identifier.

[0583] S1302. The second entity sends second indication information to the first entity in response to the first message. The second indication information includes a first model identifier, a second model identifier, and a model information template.

[0584] S1303. The first entity sends the first message to the second entity based on the model information template. The first message is used to request model registration and includes the second model identifier and model information.

[0585] The model information is determined based on the model information template.

[0586] S1304. Model query.

[0587] S1305. Model verification.

[0588] S1306. The second entity sends a second message to the first entity in response to the first message. The second message includes the second model identifier and registration decision-related information.

[0589] S1307. The first entity sends a third message to the second entity based on the registration decision-related information. The third message includes the second model identifier and the registration decision.

[0590] S1308. The first entity sends a fourth message to the third entity. The fourth message is used to request storing the model.

[0591] S1309. Model transmission.

[0592] S1310. The third entity sends a fifth message to the first entity in response to the fourth message. The fifth message includes the second model identifier and the model storage result.

[0593] S1311. The first entity sends a sixth message to the second entity. The sixth message includes the second model identifier and model update information.

[0594] S1312. The second entity sends a seventh message to the first entity in response to the sixth message. The seventh message includes the second model identifier and the model update result.

[0595] It should be noted that for the execution processes of S1304 to S1312, reference can be made to the execution processes of S802 to S810, which will not be elaborated here.

[0596] It should be noted that the above embodiments are only examples, and model registration, model verification, model storage, and model update can also be combined in other ways.

[0597] Figure 14 This is the structural schematic diagram of the model registration device 1400 provided by the embodiments of the present application. As Figure 14As shown, the device 1400 includes: a memory 1410, a transceiver 1420, and a processor 1430.

[0598] The memory 1410 is used to store computer programs; the transceiver 1420 is used to send and receive data under the control of the processor 1430; the processor 1430 is used to read the computer programs stored in the memory 1410 and perform the following operations:

[0599] Send a first message to a second entity, where the first message is used to request model registration, and the first message includes a first model identifier and / or model information, and the first model identifier is the identifier of the model in the first entity;

[0600] Receive a second message sent by the second entity in response to the first message, where the second message includes a second model identifier and first indication information, the second model identifier is the network identifier assigned by the second entity to the model, and the first indication information indicates a registration decision or registration decision-related information;

[0601] Based on the registration decision-related information, send a third message to the second entity, where the third message includes the second model identifier and the registration decision.

[0602] In one implementation, the model is a common model.

[0603] In one implementation, the model information includes at least one of the following: model type, model modality, model algorithm, model accuracy, model security, model privacy, model description information, model deployment requirements, model inference performance, model open range, model version, model owner information, or automated deployment script.

[0604] In one implementation, the model description information includes at least one of the following: model accuracy rate, variance of the model accuracy rate, data input format, data output format, model size, full model identifier corresponding to the compressed model, number of model parameters, model recall rate, or model F1 value;

[0605] The model deployment requirements include at least one of the following: model dependencies, minimum resource requirements, or recommended resource configurations, where the resources include computing power resources and storage resources.

[0606] In one implementation, the model information further includes at least one of the following: model application scenario, model segmentation information, model compression information, or model training information.

[0607] In one implementation, the model training information includes at least one of the following: training data set, metadata corresponding to the training data set, data preprocessing method, model features, model hyperparameters, or model structure.

[0608] In one implementation, the processor 1430 is further used to perform the following operations:

[0609] Receive second indication information sent by a second entity, where the second indication information includes a first model identifier, a second model identifier, and a model information template.

[0610] In one implementation, the processor 1430 is further configured to perform the following operations:

[0611] Send a fourth message to the second entity;

[0612] Receive a fifth message sent by the second entity in response to the fourth message;

[0613] Or,

[0614] Send a fourth message to a third entity;

[0615] Receive a fifth message sent by the third entity in response to the fourth message;

[0616] Wherein, the fourth message is used to request storing a model, and the fourth message includes at least one of the following: a second model identifier, a model transmission method, a model security certificate, a model address, or a model; the fifth message is used to indicate a model storage result.

[0617] In one implementation, the processor 1430 is further configured to perform the following operations:

[0618] Send a model to the second entity or the third entity.

[0619] In one implementation, the processor 1430 is further configured to perform the following operations:

[0620] Send a sixth message to the second entity, where the sixth message includes a second model identifier and model update information;

[0621] Receive a seventh message sent by the second entity in response to the sixth message, where the seventh message is used to indicate a model update result.

[0622] In one implementation, the processor 1430 is further configured to perform the following operations:

[0623] Send an eighth message to the second entity;

[0624] Receive a ninth message sent by the second entity in response to the eighth message;

[0625] Or,

[0626] Send an eighth message to the third entity;

[0627] Receive a ninth message sent by the third entity in response to the eighth message;

[0628] Or,

[0629] Send an eighth message to a fourth entity;

[0630] Receive a ninth message sent by the fourth entity in response to the eighth message;

[0631] The eighth message is used to request verification of the model, and the eighth message includes a second model identifier and the model; the ninth message is used to indicate the model verification result.

[0632] It should be noted here that the above-mentioned model registration device 1400 provided by this application can implement all the method steps implemented by the first entity in the above method embodiment, and can achieve the same technical effect. The same parts and beneficial effects as those in the method embodiment will not be specifically described herein.

[0633] Figure 15 This is a schematic structural diagram of a model registration device 1500 provided by an embodiment of this application. As Figure 15 shown, the device 1500 includes: a memory 1510, a transceiver 1520, and a processor 1530.

[0634] The memory 1510 is used to store computer programs; the transceiver 1520 is used to transmit and receive data under the control of the processor 1530; the processor 1530 is used to read the computer programs stored in the memory 1510 and perform the following operations:

[0635] Receive a first message sent by a first entity, the first message is used to request model registration, the first message includes a first model identifier and / or model information, and the first model identifier is the identifier of the model in the first entity;

[0636] In response to the first message, send a second message to the first entity, the second message includes a second model identifier and a first indication information, the second model identifier is the network identifier assigned by the second entity to the model, and the first indication information indicates a registration decision or registration decision-related information;

[0637] Receive a third message sent by the first entity, the third message is a message determined based on the registration decision-related information, and the third message includes a second model identifier and a registration decision.

[0638] In one implementation, the model is a public model.

[0639] In one implementation, the model information includes at least one of the following: model type, model modality, model algorithm, model accuracy, model security, model privacy, model description information, model deployment requirements, model inference performance, model open range, model version, model owner information, or automated deployment script.

[0640] In one embodiment, the model description information includes at least one of the following: model accuracy, variance of model accuracy, data input format, data output format, model size, full model identifier corresponding to the compressed model, number of model parameters, model recall rate, or model F1 value;

[0641] The model deployment requirements include at least one of the following: model dependencies, minimum resource requirements, or recommended resource configurations, where the resources include computing power resources and storage resources.

[0642] In one embodiment, the model information further includes at least one of the following: model application scenario, model segmentation information, model compression information, or model training information.

[0643] In one embodiment, the model training information includes at least one of the following: training data set, metadata corresponding to the training data set, data preprocessing method, model features, model hyperparameters, or model structure.

[0644] In one embodiment, the processor 1530 is further configured to perform the following operations:

[0645] Send second indication information to the first entity, where the second indication information includes a first model identifier, a second model identifier, and a model information template.

[0646] In one embodiment, the processor 1530 is further configured to perform the following operations:

[0647] Receive a fourth message sent by the first entity, where the fourth message is used to request storing the model, and the fourth message includes at least one of the following: second model identifier, model transmission method, model security certificate, model address, or model;

[0648] Send a fifth message in response to the fourth message sent by the first entity, where the fifth message is used to indicate the model storage result.

[0649] In one embodiment, the processor 1530 is further configured to perform the following operations:

[0650] Receive the model.

[0651] In one embodiment, the processor 1530 is further configured to perform the following operations:

[0652] Send a tenth message to the third entity;

[0653] Receive an eleventh message sent by the third entity in response to the tenth message;

[0654] Or,

[0655] Send a tenth message to the fourth entity;

[0656] Receive an eleventh message sent by the fourth entity in response to the tenth message;

[0657] The tenth message is used to request storing a model. The tenth message includes at least one of the following: a second model identifier, a model transmission method, a model security certificate, or a model. The eleventh message is used to indicate the model storage result.

[0658] In one implementation, the processor 1530 is further configured to perform the following operations:

[0659] Send the model to a third entity or a fourth entity.

[0660] In one implementation, the processor 1530 is further configured to perform the following operations:

[0661] Receive a sixth message sent by a first entity. The sixth message includes a second model identifier and model update information;

[0662] In response to the sixth message, send a seventh message to the first entity. The seventh message is used to indicate the model update result.

[0663] In one implementation, the processor 1530 is further configured to perform the following operations:

[0664] Receive an eighth message sent by a first entity. The eighth message is used to request model verification. The eighth message includes a second model identifier and a model;

[0665] In response to the eighth message, send a ninth message to the first entity. The ninth message is used to indicate the model verification result.

[0666] It should be noted here that the above-mentioned model registration device 1500 provided in this application can implement all the method steps implemented by the second entity in the above method embodiments, and can achieve the same technical effects. The same parts and beneficial effects as those in the method embodiments will not be specifically described herein.

[0667] Figure 16 This is a schematic structural diagram of a model registration device 1600 provided in an embodiment of this application. As Figure 16 shown, the device 1600 includes: a memory 1610, a transceiver 1620, and a processor 1630.

[0668] The memory 1610 is used to store a computer program. The transceiver 1620 is used to transmit and receive data under the control of the processor 1630. The processor 1630 is used to read the computer program stored in the memory 1610 and perform the following operations:

[0669] Receive a model storage request message, which includes at least one of the following: a second model identifier, a model transmission method, a model security certificate, a model address, or a model. The second model identifier is a network identifier assigned by the second entity to the model. The model storage request message is the fourth message sent by the first entity, the tenth message sent by the second entity, or the twelfth message sent by the fourth entity;

[0670] Send a model storage response message, which is used to indicate the model storage result. The storage response message is the fifth message sent to the first entity, the eleventh message sent to the second entity, or the thirteenth message sent to the fourth entity.

[0671] In one embodiment, the processor 1630 is further configured to perform the following operations:

[0672] Receive a model.

[0673] In one embodiment, the processor 1630 is further configured to perform the following operations:

[0674] Receive the eighth message sent by the first entity. The eighth message is used to request model verification and includes a second model identifier and a model;

[0675] In response to the eighth message, send the ninth message to the first entity. The ninth message is used to indicate the model verification result.

[0676] It should be noted here that the above-mentioned model registration device 1600 provided in this application can implement all the method steps implemented by the third entity in the above method embodiments and can achieve the same technical effects. Therefore, the same parts and beneficial effects as those in the method embodiments will not be specifically described in this embodiment.

[0677] Figure 17 This is a schematic structural diagram of the model registration device 1700 provided in an embodiment of this application. As Figure 17 shown, the device 1700 includes: a memory 1710, a transceiver 1720, and a processor 1730.

[0678] The memory 1710 is used to store computer programs; the transceiver 1720 is used to send and receive data under the control of the processor 1730; the processor 1730 is used to read the computer programs stored in the memory 1710 and perform the following operations:

[0679] Receive the eighth message sent by the first entity. The eighth message is used to request verification of the model and includes a second model identifier and a model. The second model identifier is a network identifier assigned by the second entity to the model;

[0680] In response to the eighth message, send the ninth message to the first entity. The ninth message is used to indicate the model verification result.

[0681] In one embodiment, the processor 1730 is further configured to perform the following operations:

[0682] Receive a tenth message sent by a second entity, where the tenth message is used to request storing a model, and the tenth message includes a second model identifier;

[0683] In response to the tenth message, send an eleventh message to the second entity, where the eleventh message is used to indicate the model storage result.

[0684] In one embodiment, the processor 1730 is further configured to perform the following operations:

[0685] Send a twelfth message to a third entity, where the twelfth message is used to request storing a model, and the twelfth message includes at least one of the following: a second model identifier, a model transmission method, a model security certificate, or a model;

[0686] Receive a thirteenth message sent by the third entity, where the thirteenth message is used to indicate the model storage result.

[0687] It should be noted here that the above model registration device 1700 provided in this application can implement all the method steps implemented by the fourth entity in the above method embodiments, and can achieve the same technical effects. The same parts and beneficial effects as those in the method embodiments will not be specifically described in this embodiment.

[0688] Among them, in Figures 14 to 17 , when the model registration device is a terminal, the device may further include a user interface. For different terminals, the user interface may also be an interface capable of externally or internally connecting to required devices, and the connected devices include but are not limited to a keypad, a display, a speaker, a microphone, a joystick, etc.

[0689] The bus architecture may include any number of interconnected buses and bridges. Specifically, various circuits of one or more processors represented by the processor 1430 or the processor 1530 or the processor 1630 or the processor 1730 and memories represented by the memory 1410 or the memory 1510 or the memory 1610 or the memory 1710 are linked together. The bus architecture may also link together various other circuits such as peripheral devices, voltage regulators, and power management circuits, which are well known in the art. Therefore, they will not be further described herein. The bus interface provides an interface. The transceiver may be multiple components, that is, including a transmitter and a receiver, and provides a unit for communicating with various other devices on a transmission medium, and these transmission mediums include wireless channels, wired channels, optical fiber cables, and other transmission mediums. The processor is responsible for managing the bus architecture and general processing, and the memory may store data used by the processor when performing operations.

[0690] Optionally, the processor may be a Central Processing Unit (CPU), an Application Specific Integrated Circuit (ASIC), a Field-Programmable Gate Array (FPGA), or a Complex Programmable Logic Device (CPLD). The processor may also adopt a multi-core architecture.

[0691] Figure 18 FIG. 1800 is a schematic structural diagram of the model registration device provided by an embodiment of the present application. As Figure 18 shown, the device 1800 includes:

[0692] A first sending unit 1810, configured to send a first message to a second entity, where the first message is used to request model registration, and the first message includes a first model identifier and / or model information, and the first model identifier is an identifier of the model in the first entity;

[0693] A first receiving unit 1820, configured to receive a second message sent by the second entity in response to the first message, where the second message includes a second model identifier and first indication information, the second model identifier is a network identifier assigned by the second entity to the model, and the first indication information indicates a registration decision or registration decision-related information;

[0694] A second sending unit 1830, configured to send a third message to the second entity based on the registration decision-related information, where the third message includes the second model identifier and the registration decision.

[0695] In one implementation manner, the model is a public model.

[0696] In one implementation manner, the model information includes at least one of the following: model type, model modality, model algorithm, model accuracy, model security, model privacy, model description information, model deployment requirements, model inference performance, model open range, model version, model owner information, or automated deployment script.

[0697] In one implementation manner, the model description information includes at least one of the following: model accuracy rate, variance of the model accuracy rate, data input format, data output format, model size, full model identifier corresponding to the compressed model, number of model parameters, model recall rate, or model F1 value;

[0698] The model deployment requirements include at least one of the following: model dependencies, minimum resource requirements, or recommended resource configurations, where the resources include computing power resources and storage resources.

[0699] In one embodiment, the model information further includes at least one of the following: model application scenario, model segmentation information, model compression information, or model training information.

[0700] In one embodiment, the model training information includes at least one of the following: training data set, metadata corresponding to the training data set, data preprocessing method, model features, model hyperparameters, or model structure.

[0701] In one embodiment, the apparatus 1800 further includes:

[0702] A second receiving unit, configured to receive second indication information sent by a second entity, where the second indication information includes a first model identifier, a second model identifier, and a model information template.

[0703] In one embodiment, the apparatus 1800 further includes:

[0704] A third sending unit, configured to send a fourth message to the second entity;

[0705] A third receiving unit, configured to receive a fifth message sent by the second entity in response to the fourth message;

[0706] Or,

[0707] A third sending unit, configured to send a fourth message to a third entity;

[0708] A third receiving unit, configured to receive a fifth message sent by the third entity in response to the fourth message;

[0709] Wherein, the fourth message is used to request storing a model, and the fourth message includes at least one of the following: a second model identifier, a model transmission method, a model security certificate, a model address, or a model; the fifth message is used to indicate a model storage result.

[0710] In one embodiment, the apparatus 1800 further includes:

[0711] A fourth sending unit, configured to send a model to the second entity or the third entity.

[0712] In one embodiment, the apparatus 1800 further includes:

[0713] A fifth sending unit, configured to send a sixth message to the second entity, where the sixth message includes a second model identifier and model update information;

[0714] A fourth receiving unit, configured to receive a seventh message sent by the second entity in response to the sixth message, where the seventh message is used to indicate a model update result.

[0715] In one embodiment, the apparatus 1800 further includes:

[0716] The sixth sending unit is configured to send an eighth message to a second entity;

[0717] The fifth receiving unit is configured to receive a ninth message sent by the second entity in response to the eighth message;

[0718] Or,

[0719] The sixth sending unit is configured to send an eighth message to a third entity;

[0720] The fifth receiving unit is configured to receive a ninth message sent by the third entity in response to the eighth message;

[0721] Or,

[0722] The sixth sending unit is configured to send an eighth message to a fourth entity;

[0723] The fifth receiving unit is configured to receive a ninth message sent by the fourth entity in response to the eighth message;

[0724] Wherein, the eighth message is used to request model verification, and the eighth message includes a second model identifier and a model; the ninth message is used to indicate the model verification result.

[0725] In one implementation, the first entity is a first terminal, a first access network device, or a first core network device;

[0726] The second entity is deployed on a second terminal, a second access network device, or a second core network device;

[0727] The third entity is deployed on a third terminal, a third access network device, or a third core network device;

[0728] The fourth entity is deployed on a fourth access network device or a fourth core network device;

[0729] The first terminal, the second terminal, and the third terminal are the same or different from each other, the first access network device, the second access network device, the third access network device, and the fourth access network device are the same or different from each other, and the first core network device, the second core network device, the third core network device, and the fourth core network device are the same or different from each other.

[0730] It should be noted here that the above-mentioned model registration device 1800 provided in this application can implement all the method steps implemented by the first entity in the above method embodiments, and can achieve the same technical effects. The same parts and beneficial effects as those in the method embodiments will not be specifically described in this embodiment.

[0731] Figure 19 It is a schematic structural diagram of a model registration device 1900 provided in an embodiment of this application. As Figure 19 shown, the device 1900 includes:

[0732] A first receiving unit 1910, configured to receive a first message sent by a first entity, where the first message is used to request model registration, and the first message includes a first model identifier and / or model information, and the first model identifier is an identifier of the model in the first entity;

[0733] A first sending unit 1920, configured to send a second message to the first entity in response to the first message, where the second message includes a second model identifier and first indication information, the second model identifier is a network identifier assigned by a second entity to the model, and the first indication information indicates a registration decision or registration decision-related information;

[0734] A second receiving unit 1930, configured to receive a third message sent by the first entity, where the third message is a message determined based on the registration decision-related information, and the third message includes the second model identifier and the registration decision.

[0735] In one embodiment, the model is a common model.

[0736] In one embodiment, the model information includes at least one of the following: model type, model modality, model algorithm, model accuracy, model security, model privacy, model description information, model deployment requirements, model inference performance, model open range, model version, model owner information, or automated deployment script.

[0737] In one embodiment, the model description information includes at least one of the following: model accuracy rate, variance of the model accuracy rate, data input format, data output format, model size, full model identifier corresponding to the compressed model, number of model parameters, model recall rate, or model F1 value;

[0738] The model deployment requirements include at least one of the following: model dependencies, minimum resource requirements, or recommended resource configurations, where the resources include computing power resources and storage resources.

[0739] In one embodiment, the first model information further includes at least one of the following: model application scenario, model segmentation information, model compression information, or model training information.

[0740] In one embodiment, the model training information includes at least one of the following: training data set, metadata corresponding to the training data set, data preprocessing method, model features, model hyperparameters, or model structure.

[0741] In one embodiment, the apparatus 1900 further includes:

[0742] A second sending unit, configured to send second indication information to the first entity, where the second indication information includes the first model identifier, the second model identifier, and a model information template.

[0743] In one embodiment, the apparatus 1900 further includes:

[0744] A third receiving unit, configured to receive a fourth message sent by a first entity, where the fourth message is used to request storing a model, and the fourth message includes at least one of the following: a second model identifier, a model transmission method, a model security certificate, a model address, or a model;

[0745] A third sending unit, configured to send a fifth message to the first entity in response to the fourth message, where the fifth message is used to indicate a model storage result.

[0746] In one embodiment, the apparatus 1900 further includes:

[0747] A fourth receiving unit, configured to receive a model.

[0748] In one embodiment, the apparatus 1900 further includes:

[0749] A fourth sending unit, configured to send a tenth message to a third entity;

[0750] A fifth receiving unit, configured to receive an eleventh message sent by the third entity in response to the tenth message;

[0751] Or,

[0752] A fourth sending unit, configured to send a tenth message to a fourth entity;

[0753] A fifth receiving unit, configured to receive an eleventh message sent by the fourth entity in response to the tenth message;

[0754] The tenth message is used to request storing a model, and the tenth message includes at least one of the following: a second model identifier, a model transmission method, a model security certificate, or a model; the eleventh message is used to indicate a model storage result.

[0755] In one embodiment, the apparatus 1900 further includes:

[0756] A fifth sending unit, configured to send a model to the third entity or the fourth entity.

[0757] In one embodiment, the apparatus 1900 further includes:

[0758] A sixth receiving unit, configured to receive a sixth message sent by a first entity, where the sixth message includes a second model identifier and model update information;

[0759] A sixth sending unit, configured to send a seventh message to the first entity in response to the sixth message, where the seventh message is used to indicate a model update result.

[0760] In one embodiment, the apparatus 1900 further includes:

[0761] A seventh receiving unit, configured to receive an eighth message sent by a first entity, where the eighth message is used to request model verification, and the eighth message includes a second model identifier and a model;

[0762] A seventh sending unit, configured to send a ninth message to the first entity in response to the eighth message, where the ninth message is used to indicate a model verification result.

[0763] It should be noted here that the above-mentioned model registration device 1900 provided in this application can implement all the method steps implemented by the second entity in the above method embodiments, and can achieve the same technical effects. Therefore, the same parts and beneficial effects as those in the method embodiments will not be specifically described in this embodiment.

[0764] Figure 20 FIG. is a schematic structural diagram of a model registration device 2000 provided in an embodiment of this application. As Figure 20 shown, the device 2000 includes:

[0765] A first receiving unit 2010, configured to receive a model storage request message, where the model storage request message includes at least one of the following: a second model identifier, a model transmission method, a model security certificate, a model address, or a model. The second model identifier is a network identifier assigned by the second entity to the model, and the model storage request message is a fourth message sent by the first entity, a tenth message sent by the second entity, or a twelfth message sent by the fourth entity;

[0766] A first sending unit 2020, configured to send a model storage response message, where the model storage response message is used to indicate a model storage result, and the storage response message is a fifth message sent to the first entity, an eleventh message sent to the second entity, or a thirteenth message sent to the fourth entity.

[0767] In an implementation manner, the device 2000 further includes:

[0768] A second receiving unit, configured to receive a model.

[0769] In an implementation manner, the device 2000 further includes:

[0770] A third receiving unit, configured to receive an eighth message sent by the first entity, where the eighth message is used to request model verification, and the eighth message includes a second model identifier and a model;

[0771] A second sending unit, configured to send a ninth message to the first entity in response to the eighth message, where the ninth message is used to indicate a model verification result.

[0772] It should be noted here that the above-mentioned model registration device 2000 provided by this application can implement all the method steps implemented by the third entity in the above method embodiments, and can achieve the same technical effects. Therefore, the same parts and beneficial effects as those in the method embodiments will not be specifically described herein again.

[0773] Figure 21 FIG. 4 is a schematic structural diagram of a model registration device 2100 provided by an embodiment of this application. As Figure 21 shown, the device 2100 includes:

[0774] A first receiving unit 2110, configured to receive an eighth message sent by a first entity, where the eighth message is used to request model verification, and the eighth message includes a second model identifier and a model, and the second model identifier is a network identifier assigned by a second entity to the model;

[0775] A first sending unit 2120, configured to send a ninth message to the first entity in response to the eighth message, where the ninth message is used to indicate the model verification result.

[0776] In one implementation, the device 2100 further includes:

[0777] A second receiving unit, configured to receive a tenth message sent by a second entity, where the tenth message is used to request model storage, and the tenth message includes a second model identifier;

[0778] A second sending unit, configured to send an eleventh message to the second entity in response to the tenth message, where the eleventh message is used to indicate the model storage result.

[0779] In one implementation, the device 2100 further includes:

[0780] A third sending unit, configured to send a twelfth message to a third entity, where the twelfth message is used to request model storage, and the twelfth message includes at least one of the following: a second model identifier, a model transmission method, a model security certificate, or a model;

[0781] A third receiving unit, configured to receive a thirteenth message sent by the third entity, where the thirteenth message is used to indicate the model storage result.

[0782] It should be noted here that the above-mentioned model registration device 2100 provided by this application can implement all the method steps implemented by the fourth entity in the above method embodiments, and can achieve the same technical effects. Therefore, the same parts and beneficial effects as those in the method embodiments will not be specifically described herein again.

[0783] It should be noted that the division of units in the embodiments of the present application is illustrative. It is only a logical function division, and there may be other division methods in actual implementation. In addition, in each embodiment of the present application, the functional units can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit. The above-mentioned integrated units can be implemented in the form of hardware or in the form of software functional units.

[0784] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a processor-readable storage medium. Based on this understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, or all or part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) or a processor to execute all or part of the steps of each method embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes such as USB flash drives, mobile hard disks, read-only memories (ROM), random access memories (RAM), magnetic disks, or optical discs.

[0785] The embodiments of the present application also provide a non-transitory readable storage medium. The non-transitory readable storage medium stores a computer program, and the computer program is used to cause a processor to execute all the method steps of the first entity, or all the method steps of the second entity, or all the method steps of the third entity, or all the method steps of the fourth entity in the above method embodiments.

[0786] The non-transitory readable storage medium can be any available medium or data storage device accessible by a computer, including but not limited to magnetic memories (such as floppy disks, hard disks, magnetic tapes, magneto-optical discs (MO), etc.), optical memories (such as CDs, DVDs, BDs, HVDs, etc.), and semiconductor memories (such as ROM, EPROM, EEPROM, non-volatile memories (NAND FLASH), solid-state drives (SSD)).

[0787] The embodiments of the present application also provide a computer program product, including a computer program, and when the computer program is executed by a processor, it implements all or part of the steps of the above method embodiments.

[0788] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the present application can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can take the form of a computer program product implemented on at least one computer-usable storage medium (including but not limited to disk memory and optical memory, etc.) that contains computer-usable program code.

[0789] The present application is described with reference to the flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each flow and / or block in the flowchart and / or block diagram, as well as the combination of flows and / or blocks in the flowchart and / or block diagram, can be implemented by computer-executable instructions. These computer-executable instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, such that the instructions executed by the processor of the computer or other programmable data processing devices generate means for implementing the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0790] These processor-executable instructions can also be stored in a processor-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, such that the instructions stored in the processor-readable memory generate a manufactured article including instruction means that implement the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0791] These processor-executable instructions can also be loaded onto a computer or other programmable data processing device, such that a series of operation steps are executed on the computer or other programmable device to generate a computer-implemented process, and thus the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0792] Obviously, those skilled in the art can make various modifications and variations to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalent technologies, the present application is also intended to include these modifications and variations.

Claims

1. A model registration method, characterized in that, Applied to a first entity, the method includes: Sending a first message to a second entity, the first message being used to request model registration, the first message including a first model identifier and / or model information, the first model identifier being the identifier of the model in the first entity; Receiving a second message sent by the second entity in response to the first message, the second message including a second model identifier and first indication information, the second model identifier being the network identifier assigned by the second entity to the model, the first indication information indicating a registration decision or registration decision-related information; Based on the registration decision-related information, sending a third message to the second entity, the third message including the second model identifier and a registration decision.

2. The method according to claim 1, wherein The model is a common model.

3. The method according to claim 1 or 2, characterized in that, The model information includes at least one of the following: model type, model modality, model algorithm, model accuracy, model security, model privacy, model description information, model deployment requirements, model inference performance, model open range, model version, model owner information, or an automated deployment script.

4. The method according to claim 3, wherein The model description information includes at least one of the following: model accuracy rate, variance of the model accuracy rate, data input format, data output format, model size, full model identifier corresponding to the compressed model, number of model parameters, model recall rate, or model F1 value; The model deployment requirements include at least one of the following: model dependencies, minimum resource requirements, or recommended resource configurations, where the resources include computing power resources and storage resources.

5. The method according to claim 3, characterized in that, The model information further includes at least one of the following: model application scenario, model segmentation information, model compression information, or model training information.

6. The method according to claim 5, wherein The model training information includes at least one of the following: training data set, metadata corresponding to the training data set, data preprocessing method, model features, model hyperparameters, or model structure.

7. The method according to any one of claims 1-6, characterized in that, The method further includes: Receiving second indication information sent by the second entity, the second indication information including the first model identifier, the second model identifier, and a model information template.

8. The method according to any one of claims 1 to 7, characterized in that, The method further includes: Sending a fourth message to the second entity; Receiving a fifth message sent by the second entity in response to the fourth message; Or, Sending a fourth message to a third entity; Receiving a fifth message sent by the third entity in response to the fourth message; Wherein, the fourth message is used to request storing the model, the fourth message including at least one of the following: the second model identifier, model transmission method, model security certificate, model address, or the model; the fifth message is used to indicate a model storage result.

9. The method according to claim 8, wherein The method further includes: Sending the model to the second entity or the third entity.

10. The method according to any one of claims 1-9, characterized in that, The method further includes: Sending a sixth message to the second entity, the sixth message including the second model identifier and model update information; Receiving a seventh message sent by the second entity in response to the sixth message, the seventh message being used to indicate a model update result.

11. The method according to any one of claims 1-10, characterized in that, The method further includes: Sending an eighth message to the second entity; Receiving a ninth message sent by the second entity in response to the eighth message; Or, Sending an eighth message to a third entity; Receive a ninth message sent by the third entity in response to the eighth message; Or, Send an eighth message to a fourth entity; Receive a ninth message sent by the fourth entity in response to the eighth message; Wherein, the eighth message is used to request verification of the model, and the eighth message includes the second model identifier and the model; the ninth message is used to indicate the model verification result.

12. The method according to claim 11, wherein The first entity is a first terminal, a first access network device, or a first core network device; The second entity is deployed in a second terminal, a second access network device, or a second core network device; The third entity is deployed in a third terminal, a third access network device, or a third core network device; The fourth entity is deployed in a fourth access network device or a fourth core network device; The first terminal, the second terminal, and the third terminal are the same or different from each other, the first access network device, the second access network device, the third access network device, and the fourth access network device are the same or different from each other, and the first core network device, the second core network device, the third core network device, and the fourth core network device are the same or different from each other.

13. A model registration method, characterized in that, Applied to the second entity, the method includes: Receive a first message sent by the first entity, the first message being used to request registration of a model, the first message including a first model identifier and / or model information, and the first model identifier being the identifier of the model in the first entity; In response to the first message, send a second message to the first entity, the second message including a second model identifier and first indication information, the second model identifier being the network identifier assigned by the second entity to the model, and the first indication information indicating a registration decision or registration decision-related information; Receive a third message sent by the first entity, the third message being a message determined based on the registration decision-related information, and the third message including the second model identifier and the registration decision.

14. The method according to claim 13, characterized in that, The model is a common model.

15. The method according to claim 13 or 14, characterized in that, The model information includes at least one of the following: model type, model modality, model algorithm, model accuracy, model security, model privacy, model description information, model deployment requirements, model inference performance, model open range, model version, model owner information, or automated deployment script.

16. The method according to claim 15, characterized in that, The model description information includes at least one of the following: model accuracy, variance of model accuracy, data input format, data output format, model size, full model identifier corresponding to the compressed model, number of model parameters, model recall rate, or model F1 value; The model deployment requirements include at least one of the following: model dependencies, minimum resource requirements, or recommended resource configuration, and the resources include computing power resources and storage resources.

17. The method according to claim 15, characterized in that, The first model information further includes at least one of the following: model application scenario, model segmentation information, model compression information, or model training information.

18. The method according to claim 17, characterized in that, The model training information includes at least one of the following: training data set, metadata corresponding to the training data set, data preprocessing method, model features, model hyperparameters, or model structure.

19. The method according to any one of claims 13-18, characterized in that, The method further includes: Send second indication information to the first entity, where the second indication information includes the first model identifier, the second model identifier, and a model information template.

20. The method according to any one of claims 13-19, characterized in that, The method further includes: Receive a fourth message sent by the first entity, where the fourth message is used to request storing the model, and the fourth message includes at least one of the following: the second model identifier, a model transmission method, a model security certificate, a model address, or the model; In response to the fourth message, send a fifth message to the first entity, where the fifth message is used to indicate a model storage result.

21. The method according to claim 20, wherein The method further includes: Receive the model.

22. The method according to any one of claims 13-19, characterized in that, The method further includes: Send a tenth message to a third entity; Receive an eleventh message sent by the third entity in response to the tenth message; Or, Send a tenth message to a fourth entity; Receive an eleventh message sent by the fourth entity in response to the tenth message; The tenth message is used to request storing the model, and the tenth message includes at least one of the following: the second model identifier, a model transmission method, a model security certificate, or the model; the eleventh message is used to indicate a model storage result.

23. The method according to claim 22, wherein The method further includes: Send the model to the third entity or the fourth entity.

24. The method according to any one of claims 13-23, characterized in that, The method further includes: Receive a sixth message sent by the first entity, where the sixth message includes the second model identifier and model update information; In response to the sixth message, send a seventh message to the first entity, where the seventh message is used to indicate a model update result.

25. The method according to any one of claims 13 - 24, characterized in that, The method further includes: Receive an eighth message sent by the first entity, where the eighth message is used to request verifying the model, and the eighth message includes the second model identifier and the model; In response to the eighth message, send a ninth message to the first entity, where the ninth message is used to indicate a model verification result.

26. A model registration method, characterized in that, Applied to a third entity, the method includes: Receive a model storage request message, where the model storage request message includes at least one of the following: a second model identifier, a model transmission method, a model security certificate, a model address, or a model, the second model identifier is a network identifier assigned by a second entity to the model, and the model storage request message is a fourth message sent by a first entity, or a tenth message sent by the second entity, or a twelfth message sent by the fourth entity; Send a model storage response message, where the model storage response message is used to indicate a model storage result, and the storage response message is a fifth message sent to the first entity, or an eleventh message sent to the second entity, or a thirteenth message sent to the fourth entity.

27. The method according to claim 26, wherein The method further includes: Receive the model.

28. The method according to claim 26 or 27, characterized in that, The method further includes: Receive an eighth message sent by a first entity, where the eighth message is used to request verifying the model, and the eighth message includes the second model identifier and the model; In response to the eighth message, send a ninth message to the first entity, where the ninth message is used to indicate a model verification result.

29. A model registration method, characterized in that, Applied to a fourth entity, the method includes: Receive an eighth message sent by a first entity, where the eighth message is used to request verification of a model, and the eighth message includes a second model identifier and the model, and the second model identifier is a network identifier assigned by a second entity to the model; In response to the eighth message, send a ninth message to the first entity, where the ninth message is used to indicate the model verification result.

30. The method according to claim 29, wherein The method further includes: Receive a tenth message sent by the second entity, where the tenth message is used to request storage of the model, and the tenth message includes the second model identifier; In response to the tenth message, send an eleventh message to the second entity, where the eleventh message is used to indicate the model storage result.

31. The method according to claim 29 or 30, characterized in that, The method further includes: Send a twelfth message to a third entity, where the twelfth message is used to request storage of the model, and the twelfth message includes at least one of the following: the second model identifier, the model transmission method, the model security certificate, or the model; Receive a thirteenth message sent by the third entity, where the thirteenth message is used to indicate the model storage result.

32. A model registration device, characterized in that, Applied to a first entity, the apparatus includes: A first sending unit, configured to send a first message to a second entity, where the first message is used to request registration of a model, and the first message includes a first model identifier and / or model information, and the first model identifier is an identifier of the model in the first entity; A receiving unit, configured to receive a second message sent by the second entity in response to the first message, where the second message includes a second model identifier and first indication information, the second model identifier is a network identifier assigned by the second entity to the model, and the first indication information indicates a registration decision or registration decision-related information; A second sending unit, configured to send a third message to the second entity based on the registration decision-related information, where the third message includes the second model identifier and the registration decision.

33. A model registration device, characterized in that, Applied to a second entity, the apparatus includes: A first receiving unit, configured to receive a first message sent by a first entity, where the first message is used to request registration of a model, and the first message includes a first model identifier and / or model information, and the first model identifier is an identifier of the model in the first entity; A sending unit, configured to send a second message to the first entity in response to the first message, where the second message includes a second model identifier and first indication information, the second model identifier is a network identifier assigned by the second entity to the model, and the first indication information indicates a registration decision or registration decision-related information; A second receiving unit, configured to receive a third message sent by the first entity, where the third message is a message determined based on the registration decision-related information, and the third message includes the second model identifier and the registration decision.

34. A model registration device, characterized in that, Applied to a third entity, the apparatus includes: A receiving unit, configured to receive a model storage request message, where the model storage request message includes at least one of the following: a second model identifier, a model transmission method, a model security certificate, a model address, or a model. The second model identifier is a network identifier assigned by a second entity to the model. The model storage request message is a fourth message sent by a first entity, a tenth message sent by the second entity, or a twelfth message sent by a fourth entity. A sending unit, configured to send a model storage response message, where the model storage response message is used to indicate a model storage result. The storage response message is a fifth message sent to the first entity, an eleventh message sent to the second entity, or a thirteenth message sent to the fourth entity.

35. A model registration device, characterized in that, Applied to a fourth entity, the apparatus includes: A receiving unit, configured to receive an eighth message sent by a first entity, where the eighth message is used to request model verification. The eighth message includes a second model identifier and the model. The second model identifier is a network identifier assigned by a second entity to the model. A sending unit, configured to send a ninth message to the first entity in response to the eighth message, where the ninth message is used to indicate a model verification result.

36. A model registration device, characterized in that, Applied to a first entity, the apparatus includes a memory, a transceiver, and a processor: The memory is configured to store a computer program; the transceiver is configured to transmit and receive data under the control of the processor; the processor is configured to read the computer program in the memory and perform the following operations: Send a first message to a second entity, where the first message is used to request model registration. The first message includes a first model identifier and / or model information. The first model identifier is an identifier of the model in the first entity. Receive a second message sent by the second entity in response to the first message, where the second message includes a second model identifier and a first indication information. The second model identifier is a network identifier assigned by the second entity to the model. The first indication information indicates a registration decision or registration decision-related information. Based on the registration decision-related information, send a third message to the second entity, where the third message includes the second model identifier and a registration decision.

37. The device according to claim 36, characterized in that, The model is a public model.

38. The device according to claim 36 or 37, characterized in that, The model information includes at least one of the following: model type, model modality, model algorithm, model accuracy, model security, model privacy, model description information, model deployment requirements, model inference performance, model open range, model version, model owner information, or an automated deployment script.

39. The device according to claim 38, wherein, The model description information includes at least one of the following: model accuracy, variance of model accuracy, data input format, data output format, model size, full model identifier corresponding to a compressed model, number of model parameters, model recall rate, or model F1 value. The model deployment requirements include at least one of the following: model dependencies, minimum resource requirements, or recommended resource configurations. The resources include computing power resources and storage resources.

40. The device according to claim 38, wherein, The model information further includes at least one of the following: model application scenario, model segmentation information, model compression information, or model training information.

41. The device according to claim 40, wherein, The model training information includes at least one of the following: training data set, metadata corresponding to the training data set, data preprocessing method, model features, model hyperparameters, or model structure.

42. The device according to any one of claims 36 - 41, characterized in that, The processor is further configured to perform the following operations: Receive second indication information sent by the second entity, where the second indication information includes the first model identifier, the second model identifier, and a model information template.

43. The device according to any one of claims 36 - 42, characterized in that, The processor is further configured to perform the following operations: Send a fourth message to the second entity; Receive a fifth message sent by the second entity in response to the fourth message; Or, Send a fourth message to a third entity; Receive a fifth message sent by the third entity in response to the fourth message; Wherein, the fourth message is used to request storing the model, and the fourth message includes at least one of the following: the second model identifier, model transmission method, model security certificate, model address, or the model; the fifth message is used to indicate the model storage result.

44. The device according to claim 43, wherein, The processor is further configured to perform the following operations: Send the model to the second entity or the third entity.

45. The device according to any one of claims 36 - 44, characterized in that, The processor is further configured to perform the following operations: Send a sixth message to the second entity, where the sixth message includes the second model identifier and model update information; Receive a seventh message sent by the second entity in response to the sixth message, where the seventh message is used to indicate the model update result.

46. The device according to any one of claims 36 - 45, characterized in that, The processor is further configured to perform the following operations: Send an eighth message to the second entity; Receive a ninth message sent by the second entity in response to the eighth message; Or, Send an eighth message to a third entity; Receive a ninth message sent by the third entity in response to the eighth message; Or, Send an eighth message to a fourth entity; Receive a ninth message sent by the fourth entity in response to the eighth message; Wherein, the eighth message is used to request verifying the model, and the eighth message includes the second model identifier and the model; the ninth message is used to indicate the model verification result.

47. A model registration device, characterized in that, Applied to a second entity, the device includes a memory, a transceiver, and a processor: The memory is used to store a computer program; the transceiver is used to send and receive data under the control of the processor; the processor is used to read the computer program in the memory and perform the following operations: Receive a first message sent by a first entity, where the first message is used to request registering a model, and the first message includes a first model identifier and / or model information, and the first model identifier is the identifier of the model in the first entity; Send a second message to the first entity in response to the first message, where the second message includes a second model identifier and first indication information, the second model identifier is the network identifier assigned by the second entity to the model, and the first indication information indicates a registration decision or information related to the registration decision; Receive a third message sent by the first entity, where the third message is a message determined based on the information related to the registration decision, and the third message includes the second model identifier and the registration decision.

48. The device according to claim 47, characterized in that, The model is a public model.

49. The device according to claim 47 or 48, characterized in that, The model information includes at least one of the following: model type, model modality, model algorithm, model accuracy, model security, model privacy, model description information, model deployment requirements, model inference performance, model open range, model version, model owner information, or automated deployment script.

50. The device according to claim 49, characterized in that, The model description information includes at least one of the following: model accuracy, variance of model accuracy, data input format, data output format, model size, full model identifier corresponding to the compressed model, number of model parameters, model recall rate, or model F1 value; The model deployment requirements include at least one of the following: model dependencies, minimum resource requirements, or recommended resource configuration, where the resources include computing resources and storage resources.

51. The device according to claim 49, characterized in that, The model information further includes at least one of the following: model application scenario, model segmentation information, model compression information, or model training information.

52. The device according to claim 51, characterized in that, The model training information includes at least one of the following: training data set, metadata corresponding to the training data set, data preprocessing method, model features, model hyperparameters, or model structure.

53. The device according to any one of claims 47 to 52, characterized in that, The processor is further configured to perform the following operations: Send second indication information to the first entity, where the second indication information includes the first model identifier, the second model identifier, and a model information template.

54. The device according to any one of claims 47-53, characterized in that, The processor is further configured to perform the following operations: Receive a fourth message sent by the first entity, where the fourth message is used to request storing the model, and the fourth message includes at least one of the following: the second model identifier, model transmission method, model security certificate, model address, or the model; Send a fifth message in response to the fourth message sent by the first entity, where the fifth message is used to indicate the model storage result.

55. The device according to claim 54, characterized in that, The processor is further configured to perform the following operations: Receive the model.

56. The device according to any one of claims 47 - 53, characterized in that, The processor is further configured to perform the following operations: Send a tenth message to a third entity; Receive an eleventh message sent by the third entity in response to the tenth message; Or, Send a tenth message to a fourth entity; Receive an eleventh message sent by the fourth entity in response to the tenth message; The tenth message is used to request storing the model, and the tenth message includes at least one of the following: the second model identifier, model transmission method, model security certificate, or the model; the eleventh message is used to indicate the model storage result.

57. The device according to claim 56, characterized in that, The processor is further configured to perform the following operations: Send the model to the third entity or the fourth entity.

58. The device according to any one of claims 47-57, characterized in that, The processor is further configured to perform the following operations: Receive a sixth message sent by the first entity, where the sixth message includes the second model identifier and model update information; Send a seventh message in response to the sixth message to the first entity, where the seventh message is used to indicate the model update result.

59. The device according to any one of claims 47 - 58, characterized in that, The processor is further configured to perform the following operations: Receive an eighth message sent by the first entity, where the eighth message is used to request verifying the model, and the eighth message includes the second model identifier and the model; Send a ninth message in response to the eighth message to the first entity, where the ninth message is used to indicate the model verification result.

60. A model registration device, characterized in that, Applied to a third entity, the device includes a memory, a transceiver, and a processor: The memory is configured to store computer programs; the transceiver is configured to transmit and receive data under the control of the processor; the processor is configured to read the computer programs in the memory and perform the following operations: Receive a model storage request message, where the model storage request message includes at least one of the following: a second model identifier, a model transmission method, a model security certificate, a model address, or a model. The second model identifier is a network identifier assigned by a second entity to the model. The model storage request message is a fourth message sent by a first entity, a tenth message sent by the second entity, or a twelfth message sent by a fourth entity; Send a model storage response message, where the model storage response message is used to indicate the model storage result. The storage response message is a fifth message sent to the first entity, an eleventh message sent to the second entity, or a thirteenth message sent to the fourth entity.

61. The device according to claim 60, characterized in that: The processor is further configured to perform the following operations: Receive the model.

62. The device according to claim 60 or 61, characterized in that, The processor is further configured to perform the following operations: Receive an eighth message sent by the first entity, where the eighth message is used to request verification of the model, and the eighth message includes the second model identifier and the model; In response to the eighth message, send a ninth message to the first entity, where the ninth message is used to indicate the model verification result.

63. A model registration device, characterized in that, Applied to a fourth entity, the device includes a memory, a transceiver, and a processor: The memory is configured to store computer programs; the transceiver is configured to transmit and receive data under the control of the processor; the processor is configured to read the computer programs in the memory and perform the following operations: Receive an eighth message sent by the first entity, where the eighth message is used to request verification of a model, and the eighth message includes a second model identifier and the model. The second model identifier is a network identifier assigned by a second entity to the model; In response to the eighth message, send a ninth message to the first entity, where the ninth message is used to indicate the model verification result.

64. The device according to claim 63, characterized in that, The processor is further configured to perform the following operations: Receive a tenth message sent by the second entity, where the tenth message is used to request storage of the model, and the tenth message includes the second model identifier; In response to the tenth message, send an eleventh message to the second entity, where the eleventh message is used to indicate the model storage result.

65. The device according to claim 63 or 64, characterized in that, The processor is further configured to perform the following operations: Send a twelfth message to the third entity, where the twelfth message is used to request storage of the model, and the twelfth message includes at least one of the following: the second model identifier, a model transmission method, a model security certificate, or the model; Receive a thirteenth message sent by the third entity, where the thirteenth message is used to indicate the model storage result.

66. A non-transitory readable storage medium, characterized in that, The non-transitory readable storage medium stores a computer program, and the computer program is used to cause a processor to execute the method according to any one of claims 1-11, or the method according to any one of claims 13-25, or the method according to any one of claims 26-28, or the method according to any one of claims 29-31.

Images