Information transmission method and apparatus, and device

Abstract

The present disclosure provides an information transmission method and apparatus, and a device. The information transmission method comprises: receiving an artificial intelligence (AI) model request message sent by a terminal; sending an AI model strategy query request for the terminal to a second core network device on the basis of the AI model request message; receiving an AI model strategy query response for the terminal fed back by the second core network device; and feeding back an AI model response message to the terminal on the basis of the AI model strategy query response, wherein the AI model response message carries AI model information.

Description

Information transmission method, device and equipment

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This disclosure claims priority to the Chinese patent application filed with the China Patent Office on November 21, 2023, with application number 202311557290.5 and application name “A method, device and apparatus for information transmission”, the entire contents of which are incorporated by reference into this disclosure. Technical Field

[0003] The present disclosure relates to the field of communication technologies, and in particular to an information transmission method, apparatus, and device. Background Art

[0004] In related technologies, although communication systems have added a Network Data Analytics Function (NWDAF) to provide artificial intelligence (AI) capabilities, model training only occurs within the NWDAF, which has logical functions, and the NWDAF, which has analytical requirements, is the sole consumer of AI models. AI models can only be used for internal network performance, congestion, and other data analysis. There is a lack of network element functionality that allows mobile communication users to discover and select AI models, and the AI ​​models involved are limited to data analysis types.

[0005] From the above, it can be seen that the relevant technologies have defects such as being unable to support the provision of AI models based on user needs.

[0006] Summary of the Invention

[0007] The purpose of the present disclosure is to provide an information transmission method, device and equipment to solve the problem in related technologies that cannot support the provision of AI models based on user needs.

[0008] In order to solve the above technical problems, an embodiment of the present disclosure provides an information transmission method, which is applied to a first core network device, and the method includes:

[0009] Receive AI model request messages sent by terminals;

[0010] Sending an AI model policy query request for the terminal to the second core network device according to the AI ​​model request message;

[0011] receiving an AI model policy query response for the terminal fed back by the second core network device;

[0012] According to the AI ​​model strategy query response, an AI model response message is fed back to the terminal; the AI ​​model response message carries AI model information.

[0013] Optionally, before receiving the artificial intelligence AI model request message sent by the terminal, the method further includes:

[0014] Receive an AI model discovery message sent by the terminal; the AI ​​model discovery message carries artificial intelligence service requirement description AIRD information;

[0015] According to the AIRD information, the AI ​​service type information is determined, and an AI model discovery response is fed back to the terminal.

[0016] Optionally, the AI ​​model request message carries identification information of the AI ​​service model applied for by the terminal;

[0017] Feedback of an AI model response message to the terminal according to the AI ​​model strategy query response includes:

[0018] Determining, according to the AI ​​model policy query response and the identification information, whether the AI ​​service model applied for by the terminal is within a subscription model range corresponding to the terminal, to obtain a first determination result;

[0019] Acquire AI model information according to the first determination result;

[0020] Feedback an AI model response message to the terminal based on the AI ​​model information.

[0021] Optionally, obtaining AI model information according to the first determination result includes:

[0022] When the first determination result indicates that the AI ​​business model applied for by the terminal is not within the subscription model range corresponding to the terminal, the AI ​​model information corresponding to the terminal is determined according to the AI ​​model request message, the stored AI model information and the model policy information carried by the AI ​​model policy query response.

[0023] Optionally, the AI ​​model request message further carries overhead related information; the overhead related information includes: at least one of: data type information, data size information, and data dimension information; the model strategy information carried by the AI ​​model strategy query response includes: overhead limit information;

[0024] The information transmission method further includes:

[0025] Determine, based on the overhead-related information, overhead information of the AI ​​service corresponding to the AI ​​model request message; the overhead information includes at least one of: computing time information, computing resource overhead information, and storage resource overhead information;

[0026] The determining of the AI ​​model information according to the AI ​​model request message, the locally stored AI model information, and the model policy information carried in the AI ​​model policy query response, when the first determination result indicates that the AI ​​service model applied for by the terminal is not within the subscription model range corresponding to the terminal, includes:

[0027] When the first determination result indicates a first situation, or when the first determination result indicates the first situation and the overhead information does not satisfy the overhead limit information, determining the AI ​​model information according to the overhead information, the AI ​​model request message, the locally stored AI model information, and the model policy information carried in the AI ​​model policy query response;

[0028] Among them, the first situation refers to the situation where the AI ​​business model applied for by the terminal is not within the scope of the subscription model corresponding to the terminal.

[0029] Optionally, the AI ​​model request message carries artificial intelligence reasoning result requirement AIRR information; and the AI ​​model strategy query request carries the AIRR information and AI business type information.

[0030] Optionally, the feeding back an AI model response message to the terminal according to the AI ​​model policy query response includes:

[0031] Determine the AI ​​model information based on the model strategy information and candidate model information carried in the AI ​​model strategy query response;

[0032] Feedback an AI model response message to the terminal based on the AI ​​model information.

[0033] Optionally, the AI ​​model request message further carries overhead related information; the overhead related information includes: at least one of: data type information, data size information, and data dimension information; the model strategy information carried by the AI ​​model strategy query response includes: overhead limit information;

[0034] The information transmission method further includes:

[0035] Determine, based on the overhead-related information, overhead information of the AI ​​service corresponding to the AI ​​model request message; the overhead information includes at least one of: computing time information, computing resource overhead information, and storage resource overhead information;

[0036] The determining of AI model information according to the model strategy information and candidate model information carried in the AI ​​model strategy query response includes:

[0037] Determine the AI ​​model information based on the overhead information, the model strategy information carried by the AI ​​model strategy query response, and the candidate model information.

[0038] Optionally, the feeding back an AI model response message to the terminal according to the AI ​​model policy query response includes:

[0039] If the AI ​​model policy query response indicates that there is no model policy information corresponding to the terminal, sending an AI model training request to the third core network device; the AI ​​model training request carries the AI ​​service type information and the candidate AI model information;

[0040] Receiving an AI model training response fed back by the third core network device;

[0041] Determining AI model information based on the AI ​​model training response;

[0042] Feedback an AI model response message to the terminal based on the AI ​​model information.

[0043] Optionally, the AI ​​model request message further carries overhead related information; the overhead related information includes: at least one of: data type information, data size information, and data dimension information; the model strategy information carried by the AI ​​model strategy query response includes: overhead limit information;

[0044] The information transmission method further includes:

[0045] Determine, based on the overhead-related information, overhead information of the AI ​​service corresponding to the AI ​​model request message; the overhead information includes at least one of: computing time information, computing resource overhead information, and storage resource overhead information;

[0046] The determining of AI model information according to the AI ​​model training response includes:

[0047] Determine AI model information based on the overhead information and the AI ​​model training response.

[0048] The present disclosure also provides an information transmission method, which is applied to a second core network device and includes:

[0049] Receive an AI model policy query request for the terminal sent by the first core network device;

[0050] According to the AI ​​model policy query request, an AI model policy query response for the terminal is fed back to the first core network device.

[0051] Optionally, the AI ​​model strategy query request carries a terminal identifier of the terminal;

[0052] Feedback of an AI model policy query response for the terminal to the first core network device according to the AI ​​model policy query request includes:

[0053] According to the terminal identifier, an AI model policy query response for the terminal is fed back to the first core network device.

[0054] Optionally, the AI ​​model strategy query request carries AIRR information and AI service type information;

[0055] Feedback of an AI model policy query response for the terminal to the first core network device according to the AI ​​model policy query request includes:

[0056] Determining, based on the AIRR information and the AI ​​business type information, whether there is an AI historical policy corresponding to the AI ​​model policy query request, to obtain a second determination result;

[0057] Based on the second determination result, an AI model policy query response for the terminal is fed back to the first core network device.

[0058] Optionally, the feeding back an AI model policy query response for the terminal to the first core network device based on the second determination result includes:

[0059] If the second determination result indicates that there is an AI historical policy corresponding to the AI ​​model policy query request, feeding back an AI model policy query response for the terminal to the first core network device according to the AI ​​historical policy; the AI ​​historical policy includes: model policy information and candidate model information;

[0060] If the second determination result indicates that there is no AI historical policy corresponding to the AI ​​model policy query request, an AI model policy query response indicating that there is no model policy information corresponding to the terminal is fed back to the first core network device.

[0061] The present disclosure also provides an information transmission method, which is applied to a terminal and includes:

[0062] Sending an AI model request message to the first core network device;

[0063] Receive an AI model response message fed back by the first core network device; the AI ​​model response message carries AI model information.

[0064] Optionally, before sending the AI ​​model request message to the first core network device, the method further includes:

[0065] Sending an AI model discovery message to the first core network device; the AI ​​model discovery message carries AIRD information;

[0066] Receive the AI ​​model discovery response fed back by the first core network device.

[0067] Optionally, the AI ​​model request message carries identification information of the AI ​​service model applied for by the terminal;

[0068] And / or, the AI ​​model request message carries overhead related information; the overhead related information includes: at least one of data type information, data size information, and data dimension information;

[0069] And / or, the AI ​​model request message carries AIRR information.

[0070] The present disclosure also provides an information transmission method, which is applied to a third core network device. The method includes:

[0071] Receive an AI model training request sent by the first core network device; the AI ​​model training request carries AI service type information and candidate AI model information;

[0072] According to the AI ​​model training request, an AI model training response is fed back to the first core network device, and AI model training information corresponding to the AI ​​model training request is sent to the second core network device.

[0073] Optionally, feeding back an AI model training response to the first core network device according to the AI ​​model training request includes:

[0074] Perform candidate AI model training based on the AI ​​business type information and candidate AI model information, and obtain evaluation results;

[0075] Based on the evaluation result, an AI model training response is fed back to the first core network device.

[0076] Optionally, the AI ​​model training request also carries AIRR information;

[0077] The candidate AI model training is performed based on the AI ​​business type information and the candidate AI model information, and an evaluation result is obtained, including:

[0078] Perform candidate AI model training based on the AI ​​business type information and the candidate AI model information to obtain a training result;

[0079] Determining the weights of evaluation indicators based on the AIRR information;

[0080] An evaluation result is obtained according to the weights and the training result.

[0081] The embodiment of the present disclosure further provides an information transmission device, which is a first core network device and includes a memory, a transceiver, and a processor:

[0082] A memory for storing a computer program; a transceiver for transmitting and receiving data under the control of the processor; and a processor for reading the computer program in the memory and performing the following operations:

[0083] Receiving, via the transceiver, an artificial intelligence (AI) model request message sent by a terminal;

[0084] According to the AI ​​model request message, sending an AI model policy query request for the terminal to the second core network device through the transceiver;

[0085] Receiving, through the transceiver, an AI model policy query response for the terminal fed back by the second core network device;

[0086] According to the AI ​​model strategy query response, an AI model response message is fed back to the terminal; the AI ​​model response message carries AI model information.

[0087] Optionally, the operation further includes:

[0088] Before receiving the artificial intelligence AI model request message sent by the terminal, receiving the AI ​​model discovery message sent by the terminal through the transceiver; the AI ​​model discovery message carries artificial intelligence service requirement description AIRD information;

[0089] According to the AIRD information, AI service type information is determined, and an AI model discovery response is fed back to the terminal through the transceiver.

[0090] Optionally, the AI ​​model request message carries identification information of the AI ​​service model applied for by the terminal;

[0091] Feedback of an AI model response message to the terminal according to the AI ​​model strategy query response includes:

[0092] Determining, according to the AI ​​model policy query response and the identification information, whether the AI ​​service model applied for by the terminal is within a subscription model range corresponding to the terminal, to obtain a first determination result;

[0093] Acquire AI model information according to the first determination result;

[0094] Feedback an AI model response message to the terminal based on the AI ​​model information.

[0095] Optionally, obtaining AI model information according to the first determination result includes:

[0096] When the first determination result indicates that the AI ​​business model applied for by the terminal is not within the subscription model range corresponding to the terminal, the AI ​​model information corresponding to the terminal is determined according to the AI ​​model request message, the stored AI model information and the model policy information carried by the AI ​​model policy query response.

[0097] Optionally, the AI ​​model request message further carries overhead related information; the overhead related information includes: at least one of: data type information, data size information, and data dimension information; the model strategy information carried by the AI ​​model strategy query response includes: overhead limit information;

[0098] The operations further include:

[0099] Determine, based on the overhead-related information, overhead information of the AI ​​service corresponding to the AI ​​model request message; the overhead information includes at least one of: computing time information, computing resource overhead information, and storage resource overhead information;

[0100] The determining of the AI ​​model information according to the AI ​​model request message, the locally stored AI model information, and the model policy information carried in the AI ​​model policy query response, when the first determination result indicates that the AI ​​service model applied for by the terminal is not within the subscription model range corresponding to the terminal, includes:

[0101] When the first determination result indicates a first situation, or when the first determination result indicates the first situation and the overhead information does not satisfy the overhead limit information, determining the AI ​​model information according to the overhead information, the AI ​​model request message, the locally stored AI model information, and the model policy information carried in the AI ​​model policy query response;

[0102] Among them, the first situation refers to the situation where the AI ​​business model applied for by the terminal is not within the scope of the subscription model corresponding to the terminal.

[0103] Optionally, the AI ​​model request message carries artificial intelligence reasoning result requirement AIRR information; and the AI ​​model strategy query request carries the AIRR information and AI business type information.

[0104] Optionally, the feeding back an AI model response message to the terminal according to the AI ​​model policy query response includes:

[0105] Determine the AI ​​model information based on the model strategy information and candidate model information carried in the AI ​​model strategy query response;

[0106] Feedback an AI model response message to the terminal based on the AI ​​model information.

[0107] Optionally, the AI ​​model request message further carries overhead related information; the overhead related information includes: at least one of: data type information, data size information, and data dimension information; the model strategy information carried by the AI ​​model strategy query response includes: overhead limit information;

[0108] The operations further include:

[0109] Determine, based on the overhead-related information, overhead information of the AI ​​service corresponding to the AI ​​model request message; the overhead information includes at least one of: computing time information, computing resource overhead information, and storage resource overhead information;

[0110] The determining of AI model information according to the model strategy information and candidate model information carried in the AI ​​model strategy query response includes:

[0111] Determine the AI ​​model information based on the overhead information, the model strategy information carried by the AI ​​model strategy query response, and the candidate model information.

[0112] Optionally, the feeding back an AI model response message to the terminal according to the AI ​​model policy query response includes:

[0113] When the AI ​​model policy query response indicates that there is no model policy information corresponding to the terminal, sending an AI model training request to a third core network device through the transceiver; the AI ​​model training request carries the AI ​​service type information and the candidate AI model information;

[0114] Receiving, through the transceiver, an AI model training response fed back by the third core network device;

[0115] Determining AI model information based on the AI ​​model training response;

[0116] Feedback an AI model response message to the terminal based on the AI ​​model information.

[0117] Optionally, the AI ​​model request message further carries overhead related information; the overhead related information includes: at least one of: data type information, data size information, and data dimension information; the model strategy information carried by the AI ​​model strategy query response includes: overhead limit information;

[0118] The operations further include:

[0119] Determine, based on the overhead-related information, overhead information of the AI ​​service corresponding to the AI ​​model request message; the overhead information includes at least one of: computing time information, computing resource overhead information, and storage resource overhead information;

[0120] The determining of AI model information according to the AI ​​model training response includes:

[0121] Determine AI model information based on the overhead information and the AI ​​model training response.

[0122] The embodiment of the present disclosure further provides an information transmission device, which is a second core network device and includes a memory, a transceiver, and a processor:

[0123] A memory for storing a computer program; a transceiver for transmitting and receiving data under the control of the processor; and a processor for reading the computer program in the memory and performing the following operations:

[0124] Receiving, through the transceiver, an AI model policy query request for the terminal sent by the first core network device;

[0125] According to the AI ​​model policy query request, an AI model policy query response for the terminal is fed back to the first core network device.

[0126] Optionally, the AI ​​model strategy query request carries a terminal identifier of the terminal;

[0127] Feedback of an AI model policy query response for the terminal to the first core network device according to the AI ​​model policy query request includes:

[0128] According to the terminal identifier, an AI model policy query response for the terminal is fed back to the first core network device.

[0129] Optionally, the AI ​​model strategy query request carries AIRR information and AI service type information;

[0130] Feedback of an AI model policy query response for the terminal to the first core network device according to the AI ​​model policy query request includes:

[0131] Determining, based on the AIRR information and the AI ​​business type information, whether there is an AI historical policy corresponding to the AI ​​model policy query request, to obtain a second determination result;

[0132] Based on the second determination result, an AI model policy query response for the terminal is fed back to the first core network device.

[0133] Optionally, the feeding back an AI model policy query response for the terminal to the first core network device based on the second determination result includes:

[0134] If the second determination result indicates that there is an AI historical policy corresponding to the AI ​​model policy query request, feeding back an AI model policy query response for the terminal to the first core network device according to the AI ​​historical policy; the AI ​​historical policy includes: model policy information and candidate model information;

[0135] If the second determination result indicates that there is no AI historical policy corresponding to the AI ​​model policy query request, an AI model policy query response indicating that there is no model policy information corresponding to the terminal is fed back to the first core network device.

[0136] The present disclosure also provides an information transmission device, which is a terminal and includes a memory, a transceiver, and a processor.

[0137] A memory for storing a computer program; a transceiver for transmitting and receiving data under the control of the processor; and a processor for reading the computer program in the memory and performing the following operations:

[0138] Sending an AI model request message to the first core network device through the transceiver;

[0139] The transceiver receives an AI model response message fed back by the first core network device; the AI ​​model response message carries AI model information.

[0140] Optionally, the operation further includes:

[0141] Before sending the AI ​​model request message to the first core network device, sending an AI model discovery message to the first core network device through the transceiver; the AI ​​model discovery message carries AIRD information;

[0142] Receive the AI ​​model discovery response fed back by the first core network device through the transceiver.

[0143] Optionally, the AI ​​model request message carries identification information of the AI ​​service model applied for by the terminal;

[0144] And / or, the AI ​​model request message carries overhead related information; the overhead related information includes: at least one of data type information, data size information, and data dimension information;

[0145] And / or, the AI ​​model request message carries AIRR information.

[0146] The embodiment of the present disclosure further provides an information transmission device, which is a third core network device and includes a memory, a transceiver, and a processor:

[0147] A memory for storing a computer program; a transceiver for transmitting and receiving data under the control of the processor; and a processor for reading the computer program in the memory and performing the following operations:

[0148] Receiving, through the transceiver, an AI model training request sent by the first core network device; the AI ​​model training request carries AI service type information and candidate AI model information;

[0149] According to the AI ​​model training request, an AI model training response is fed back to the first core network device, and AI model training information corresponding to the AI ​​model training request is sent to the second core network device through the transceiver.

[0150] Optionally, feeding back an AI model training response to the first core network device according to the AI ​​model training request includes:

[0151] Perform candidate AI model training based on the AI ​​business type information and candidate AI model information, and obtain evaluation results;

[0152] Based on the evaluation result, an AI model training response is fed back to the first core network device.

[0153] Optionally, the AI ​​model training request also carries AIRR information;

[0154] The candidate AI model training is performed based on the AI ​​business type information and the candidate AI model information, and an evaluation result is obtained, including:

[0155] Perform candidate AI model training based on the AI ​​business type information and the candidate AI model information to obtain a training result;

[0156] Determining the weights of evaluation indicators based on the AIRR information;

[0157] An evaluation result is obtained according to the weights and the training result.

[0158] The present disclosure also provides an information transmission device, which is applied to a first core network device. The device includes:

[0159] A first receiving unit is configured to receive an artificial intelligence (AI) model request message sent by a terminal;

[0160] A first sending unit, configured to send an AI model policy query request for the terminal to the second core network device according to the AI ​​model request message;

[0161] A second receiving unit is configured to receive an AI model policy query response for the terminal fed back by the second core network device;

[0162] The first feedback unit is configured to feed back an AI model response message to the terminal according to the AI ​​model policy query response; the AI ​​model response message carries AI model information.

[0163] Optionally, the device further comprises:

[0164] The third receiving unit is configured to receive an AI model discovery message sent by the terminal before receiving the AI ​​model request message sent by the terminal; the AI ​​model discovery message carries AIRD information;

[0165] The first processing unit is configured to determine AI service type information according to the AIRD information, and to feed back an AI model discovery response to the terminal.

[0166] Optionally, the AI ​​model request message carries identification information of the AI ​​service model applied for by the terminal;

[0167] Feedback of an AI model response message to the terminal according to the AI ​​model strategy query response includes:

[0168] Determining, according to the AI ​​model policy query response and the identification information, whether the AI ​​service model applied for by the terminal is within a subscription model range corresponding to the terminal, to obtain a first determination result;

[0169] Acquire AI model information according to the first determination result;

[0170] Feedback an AI model response message to the terminal based on the AI ​​model information.

[0171] Optionally, obtaining AI model information according to the first determination result includes:

[0172] When the first determination result indicates that the AI ​​business model applied for by the terminal is not within the subscription model range corresponding to the terminal, the AI ​​model information corresponding to the terminal is determined according to the AI ​​model request message, the stored AI model information and the model policy information carried by the AI ​​model policy query response.

[0173] Optionally, the AI ​​model request message further carries overhead related information; the overhead related information includes: at least one of: data type information, data size information, and data dimension information; the model strategy information carried by the AI ​​model strategy query response includes: overhead limit information;

[0174] The information transmission device further includes:

[0175] A first determining unit is configured to determine, based on the overhead-related information, overhead information of the AI ​​service corresponding to the AI ​​model request message; the overhead information includes at least one of: computing time information, computing resource overhead information, and storage resource overhead information;

[0176] The determining of the AI ​​model information according to the AI ​​model request message, the locally stored AI model information, and the model policy information carried in the AI ​​model policy query response, when the first determination result indicates that the AI ​​service model applied for by the terminal is not within the subscription model range corresponding to the terminal, includes:

[0177] When the first determination result indicates a first situation, or when the first determination result indicates the first situation and the overhead information does not satisfy the overhead limit information, determining the AI ​​model information according to the overhead information, the AI ​​model request message, the locally stored AI model information, and the model policy information carried in the AI ​​model policy query response;

[0178] Among them, the first situation refers to the situation where the AI ​​business model applied for by the terminal is not within the scope of the subscription model corresponding to the terminal.

[0179] Optionally, the AI ​​model request message carries artificial intelligence reasoning result requirement AIRR information; and the AI ​​model strategy query request carries the AIRR information and AI business type information.

[0180] Optionally, the feeding back an AI model response message to the terminal according to the AI ​​model policy query response includes:

[0181] Determine the AI ​​model information based on the model strategy information and candidate model information carried in the AI ​​model strategy query response;

[0182] Feedback an AI model response message to the terminal based on the AI ​​model information.

[0183] Optionally, the AI ​​model request message further carries overhead related information; the overhead related information includes: at least one of: data type information, data size information, and data dimension information; the model strategy information carried by the AI ​​model strategy query response includes: overhead limit information;

[0184] The information transmission device further includes:

[0185] A second determining unit is configured to determine, based on the overhead related information, overhead information of the AI ​​service corresponding to the AI ​​model request message; the overhead information includes at least one of: computing time information, computing resource overhead information, and storage resource overhead information;

[0186] The determining of AI model information according to the model strategy information and candidate model information carried in the AI ​​model strategy query response includes:

[0187] Determine the AI ​​model information based on the overhead information, the model strategy information carried by the AI ​​model strategy query response, and the candidate model information.

[0188] Optionally, the feeding back an AI model response message to the terminal according to the AI ​​model policy query response includes:

[0189] If the AI ​​model policy query response indicates that there is no model policy information corresponding to the terminal, sending an AI model training request to the third core network device; the AI ​​model training request carries the AI ​​service type information and the candidate AI model information;

[0190] Receiving an AI model training response fed back by the third core network device;

[0191] Determining AI model information based on the AI ​​model training response;

[0192] Feedback an AI model response message to the terminal based on the AI ​​model information.

[0193] Optionally, the AI ​​model request message further carries overhead related information; the overhead related information includes: at least one of: data type information, data size information, and data dimension information; the model strategy information carried by the AI ​​model strategy query response includes: overhead limit information;

[0194] The information transmission device further includes:

[0195] A third determining unit is configured to determine, based on the overhead-related information, overhead information of the AI ​​service corresponding to the AI ​​model request message; the overhead information includes at least one of: computing time information, computing resource overhead information, and storage resource overhead information;

[0196] The determining of AI model information according to the AI ​​model training response includes:

[0197] Determine AI model information based on the overhead information and the AI ​​model training response.

[0198] The present disclosure also provides an information transmission device, which is applied to a second core network device and includes:

[0199] a fourth receiving unit, configured to receive an AI model policy query request for the terminal sent by the first core network device;

[0200] The second feedback unit is configured to feed back an AI model policy query response for the terminal to the first core network device based on the AI ​​model policy query request.

[0201] Optionally, the AI ​​model strategy query request carries a terminal identifier of the terminal;

[0202] Feedback of an AI model policy query response for the terminal to the first core network device according to the AI ​​model policy query request includes:

[0203] According to the terminal identifier, an AI model policy query response for the terminal is fed back to the first core network device.

[0204] Optionally, the AI ​​model strategy query request carries AIRR information and AI business type information;

[0205] Feedback of an AI model policy query response for the terminal to the first core network device according to the AI ​​model policy query request includes:

[0206] Determining, based on the AIRR information and the AI ​​business type information, whether there is an AI historical policy corresponding to the AI ​​model policy query request, to obtain a second determination result;

[0207] Based on the second determination result, an AI model policy query response for the terminal is fed back to the first core network device.

[0208] Optionally, the feeding back an AI model policy query response for the terminal to the first core network device based on the second determination result includes:

[0209] If the second determination result indicates that there is an AI historical policy corresponding to the AI ​​model policy query request, feeding back an AI model policy query response for the terminal to the first core network device according to the AI ​​historical policy; the AI ​​historical policy includes: model policy information and candidate model information;

[0210] If the second determination result indicates that there is no AI historical policy corresponding to the AI ​​model policy query request, an AI model policy query response indicating that there is no model policy information corresponding to the terminal is fed back to the first core network device.

[0211] The present disclosure also provides an information transmission device, which is applied to a terminal and includes:

[0212] A second sending unit is configured to send an AI model request message to the first core network device;

[0213] The fifth receiving unit is used to receive the AI ​​model response message fed back by the first core network device; the AI ​​model response message carries AI model information.

[0214] Optionally, the device further comprises:

[0215] A third sending unit is configured to send an AI model discovery message to the first core network device before sending the AI ​​model request message to the first core network device; the AI ​​model discovery message carries AIRD information;

[0216] The sixth receiving unit is used to receive the AI ​​model discovery response fed back by the first core network device.

[0217] Optionally, the AI ​​model request message carries identification information of the AI ​​service model applied for by the terminal;

[0218] And / or, the AI ​​model request message carries overhead related information; the overhead related information includes: at least one of data type information, data size information, and data dimension information;

[0219] And / or, the AI ​​model request message carries AIRR information.

[0220] The present disclosure also provides an information transmission device, which is applied to a third core network device. The device includes:

[0221] a seventh receiving unit, configured to receive an AI model training request sent by the first core network device; the AI ​​model training request carries AI service type information and candidate AI model information;

[0222] The third feedback unit is used to feedback an AI model training response to the first core network device according to the AI ​​model training request, and to send AI model training information corresponding to the AI ​​model training request to the second core network device.

[0223] Optionally, feeding back an AI model training response to the first core network device according to the AI ​​model training request includes:

[0224] Perform candidate AI model training based on the AI ​​business type information and candidate AI model information, and obtain evaluation results;

[0225] Based on the evaluation result, an AI model training response is fed back to the first core network device.

[0226] Optionally, the AI ​​model training request also carries AIRR information;

[0227] The candidate AI model training is performed based on the AI ​​business type information and the candidate AI model information, and an evaluation result is obtained, including:

[0228] Perform candidate AI model training based on the AI ​​business type information and the candidate AI model information to obtain a training result;

[0229] Determining the weights of evaluation indicators based on the AIRR information;

[0230] An evaluation result is obtained according to the weights and the training result.

[0231] An embodiment of the present disclosure also provides a non-transitory readable storage medium, which stores a computer program, and the computer program is used to enable the processor to execute the above-mentioned method on the first core network device side, the second core network device side, the terminal side or the third core network device side.

[0232] The beneficial effects of the above technical solutions disclosed herein are as follows:

[0233] In the above scheme, the information transmission method receives an artificial intelligence AI model request message sent by the terminal; sends an AI model policy query request for the terminal to the second core network device according to the AI ​​model request message; receives an AI model policy query response for the terminal fed back by the second core network device; and feeds back an AI model response message to the terminal according to the AI ​​model policy query response; the AI ​​model response message carries AI model information; it can support the provision of corresponding AI model information to the terminal according to the AI ​​model request message, and then support the provision of AI models based on user needs; it is a good solution to the problem that related technologies cannot support the provision of AI models based on user needs. BRIEF DESCRIPTION OF THE DRAWINGS

[0234] FIG1 is a schematic diagram of a wireless communication system architecture according to an embodiment of the present disclosure;

[0235] FIG2 is a schematic diagram of the architecture of a machine learning model according to an embodiment of the present disclosure;

[0236] FIG3 is a flowchart of an information transmission method according to an embodiment of the present disclosure;

[0237] FIG4 is a second flow chart of the information transmission method according to an embodiment of the present disclosure;

[0238] FIG5 is a third flow chart of the information transmission method according to an embodiment of the present disclosure;

[0239] FIG6 is a fourth flow chart of the information transmission method according to an embodiment of the present disclosure;

[0240] FIG7 is a schematic diagram of a network element architecture according to an embodiment of the present disclosure;

[0241] FIG8 is a schematic diagram of a first specific implementation architecture of the information transmission method according to an embodiment of the present disclosure;

[0242] FIG9 is a schematic diagram of a first embodiment of the information transmission method according to the present disclosure;

[0243] FIG10 is a second schematic diagram of a specific implementation architecture of the information transmission method according to an embodiment of the present disclosure;

[0244] FIG11 is a second schematic diagram of a specific implementation flow of the information transmission method according to an embodiment of the present disclosure;

[0245] FIG12 is a third schematic diagram of a specific implementation architecture of the information transmission method according to an embodiment of the present disclosure;

[0246] FIG13 is a third schematic diagram of a specific implementation flow of the information transmission method according to an embodiment of the present disclosure;

[0247] FIG14 is a first structural diagram of an information transmission device according to an embodiment of the present disclosure;

[0248] FIG15 is a second structural diagram of an information transmission device according to an embodiment of the present disclosure;

[0249] FIG16 is a third structural diagram of an information transmission device according to an embodiment of the present disclosure;

[0250] FIG17 is a fourth structural diagram of an information transmission device according to an embodiment of the present disclosure;

[0251] FIG18 is a first structural diagram of an information transmission device according to an embodiment of the present disclosure;

[0252] FIG19 is a second structural diagram of the information transmission device according to an embodiment of the present disclosure;

[0253] FIG20 is a third structural diagram of the information transmission device according to an embodiment of the present disclosure;

[0254] FIG21 is a fourth structural diagram of the information transmission device according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0255] The following will be combined with the accompanying drawings in the embodiments of the present disclosure to clearly and completely describe the technical solutions in the embodiments of the present disclosure. Obviously, the embodiments described are only part of the embodiments of the present disclosure and not all of the embodiments. Based on the embodiments of the present disclosure, all other embodiments obtained by ordinary technicians in this field without making any creative efforts shall fall within the scope of protection of the present disclosure.

[0256] In the embodiments of the present disclosure, the term "and / or" describes the association relationship between associated objects, indicating that three relationships can exist. For example, A and / or B can represent three situations: A exists alone, A and B exist simultaneously, and B exists alone. The character " / " generally indicates that the associated objects are in an "or" relationship.

[0257] In the embodiments of the present disclosure, the term "plurality" refers to two or more than two, and other quantifiers are similar thereto.

[0258] It is noted that the technical solution provided by the embodiments of the present disclosure can be applied to a variety of systems, especially the fifth generation (the 5 thThe 5G Generation (5G) system can be, for example, a global system of mobile communication (GSM) system, a code division multiple access (CDMA) system, a wideband code division multiple access (WCDMA) general packet radio service (GPRS) system, a long term evolution (LTE) system, a LTE frequency division duplex (FDD) system, a LTE time division duplex (TDD) system, an advanced long term evolution (LTE-A) system, a universal mobile telecommunication system (UMTS), a world-wide interoperability for microwave access (WiMAX) system, a 5G new air interface (NR) system, and the like. These various systems include terminal equipment and network equipment. The system can also include a core network part, such as an evolved packet system (EPS), a 5G system (5G system, 5GS), and the like.

[0259] Figure 1 shows a block diagram of a wireless communication system to which embodiments of the present disclosure may be applied. The wireless communication system includes a terminal device (referred to as a terminal for short) and a network device.

[0260] The terminal device involved in the embodiments of the present disclosure may be a device that provides voice and / or data connectivity to a user, a handheld device with wireless connection function, or other processing device connected to a wireless modem. 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 User Equipment (UE). A wireless terminal device can communicate with one or more core networks (CN) via a radio access network (RAN). The wireless terminal device may be a mobile terminal device, such as a mobile phone (or "cellular" phone) and a computer with a mobile terminal device. For example, it may be a portable, pocket-sized, handheld, computer-built-in or vehicle-mounted mobile device that exchanges voice and / or data with a radio 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), and other devices. The wireless terminal device may also be referred to as a system, a subscriber unit, a subscriber station, a mobile station, a mobile station, a remote station, an access point, a remote terminal device, an access terminal device, a user terminal device, a user agent, or a user device, but is not limited in the embodiments of the present disclosure.

[0261] The network device involved in the embodiments of the present disclosure may be a base station, which may include multiple cells providing services to terminals. Depending on the specific application scenario, the base station may also be called an access point, or may be a device in an access network that communicates with a wireless terminal device through one or more sectors on an air interface, or may be named by another name. The network device may be used to interchange received air frames with Internet Protocol (IP) packets, acting as a router between the wireless terminal device and the rest of the access network, wherein the rest of the access network may include an Internet Protocol (IP) communication network. The network device may also coordinate the attribute management of the air interface. For example, the network device involved in the embodiments of the present disclosure may be a base transceiver station (BTS) in the Global System for Mobile communications (GSM) or code division multiple access (CDMA), a network device (NodeB) in wide-band code division multiple access (WCDMA), an evolutionary Node B (eNB or e-NodeB) in the long term evolution (LTE) system, a 5G base station (gNB) in the next generation system, a home evolved Node B (HeNB), a relay node, a femto, a pico, etc., and is not limited in the embodiments of the present disclosure. In some network structures, 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.

[0262] Network devices and terminal devices can each use one or more antennas for Multiple Input Multiple Output (MIMO) transmission. MIMO transmission can be single-user MIMO (SU-MIMO) or multi-user MIMO (MU-MIMO). Depending on the form and number of antenna combinations, MIMO transmission can be two-dimensional MIMO (2D-MIMO), three-dimensional MIMO (3D-MIMO), full-dimensional MIMO (FD-MIMO), or massive MIMO. It can also use diversity transmission, precoding transmission, or beamforming transmission.

[0263] The following first introduces the contents involved in the solution provided by the embodiment of the present disclosure.

[0264] The sixth generation th The organic integration of 6G (6th Generation) networks and artificial intelligence (AI) is a future development trend. To realize the vision of 6G, AI support is indispensable. Therefore, 6G mobile communication networks need to consider deep coupling with AI during the design phase. 6G's inherent intelligence requires the network to provide intelligent and inclusive AI capabilities. The provided AI models should not only be used for the network itself, but also provide AI model discovery capabilities to provide AI services to mobile communication users. At the same time, on-demand selection of AI models is extremely important, as it determines the resource consumption and performance of AI models in solving AI services. Currently, AI services in 5G communication systems are limited to the network itself, and AI models cannot be selected according to demand.

[0265] The 5G system AI capabilities and models are described as follows:

[0266] The current 5G mobile communication system network architecture is designed around connectivity and data transmission. The 5G communication system has added a Network Data Analytics Function (NWDAF). NWDAF collects data generated by 5G core network functions and provides AI-powered data analysis capabilities for network performance, including network service experience, network performance, slice load, network function load, and terminal mobility.

[0267] In terms of architecture, NWDAF can be decomposed into NWDAFs that include the Model Training Logical Function (MTLF) and the Analytics Logical Function (AnLF). Multiple NWDAFs can share, synthesize, and transfer analytical data.

[0268] Specifically, as shown in Figure 2 (Trained Machine Learning Model Provisioning Architecture), the 5G system architecture allows a NWDAF containing the analysis logic function (AnLF) to use an AI model from another NWDAF containing the model training logic function (MTLF) to provide AI services. The NWDAF containing the AnLF can use the Nnwdaf interface to request and select an AI model to provide services.

[0269] Furthermore, 5G communication systems lack specific methods and processes for selecting AI models based on different AI service requirements and types. Specifically, the existing 5G architecture lacks integration with AI and cannot provide flexible AI model selection for diverse AI services. Furthermore, the existing 6G intelligent endogenous architecture still lacks the ability to discover AI models and make on-demand AI model selection decisions based on user-provided data and requirements.

[0270] Based on the above, the embodiments of the present disclosure provide an information transmission method, apparatus, and device to address the problem in related technologies that cannot support the provision of AI models based on user needs. The method, apparatus, and device are based on the same patent application concept. Since the principles of the method, apparatus, and device for solving the problem are similar, the implementation of the method, apparatus, and device can refer to each other, and the repeated parts will not be repeated.

[0271] The information transmission method provided in the embodiment of the present disclosure is applied to a first core network device, as shown in FIG3 , and includes:

[0272] Step 31: Receive an artificial intelligence (AI) model request message sent by the terminal;

[0273] Step 32: Send an AI model policy query request for the terminal to the second core network device according to the AI ​​model request message;

[0274] Step 33: Receive an AI model policy query response for the terminal fed back by the second core network device;

[0275] Step 34: Feedback an AI model response message to the terminal based on the AI ​​model policy query response; the AI ​​model response message carries AI model information.

[0276] Among them, the first core network device can be implemented as an artificial intelligence evaluation and selection function (AI Evaluation and Selection Function, AIESF) device, and / or, the AI ​​model request message can carry the terminal identification (UE ID) of the terminal, and / or, the second core network device can be implemented as a policy control function (Policy Control Function, PCF) device, and / or, the AI ​​model policy query request can carry the terminal identification (UE ID) of the terminal, and / or, the AI ​​model information may include: AI Model ID (AI model identification), AI model accuracy, estimated training time and other information at least one item, but is not limited to this.

[0277] The information transmission method provided by the embodiment of the present disclosure receives an artificial intelligence (AI) model request message sent by a terminal; sends an AI model policy query request for the terminal to a second core network device based on the AI ​​model request message; receives an AI model policy query response for the terminal fed back by the second core network device; and feeds back an AI model response message to the terminal based on the AI ​​model policy query response; the AI ​​model response message carries AI model information; and can support the provision of corresponding AI model information to the terminal based on the AI ​​model request message, thereby supporting the provision of AI models based on user needs; and well solves the problem in related technologies that cannot support the provision of AI models based on user needs.

[0278] Furthermore, before receiving the artificial intelligence AI model request message sent by the terminal, it also includes: receiving the AI ​​model discovery message sent by the terminal; the AI ​​model discovery message carries the artificial intelligence service requirement description AIRD information; according to the AIRD information, determining the AI ​​service type information, and feeding back the AI ​​model discovery response to the terminal.

[0279] This allows the AI ​​service type information to be clearly identified for subsequent use. The AI ​​model discovery response may carry the AI ​​service type information, but is not limited thereto.

[0280] This solution specifically includes three scenarios: Scenario 1: The terminal specifies an AI model; Scenario 2: The terminal does not specify an AI model, but the second core network device stores the corresponding AI policy (i.e., the model policy information corresponding to the terminal); and Scenario 3: The terminal does not specify an AI model, and the second core network device does not store the corresponding AI policy. Each scenario is described below:

[0281] For situation one, the AI ​​model request message carries the identification information of the AI ​​business model applied for by the terminal; the AI ​​model response message is fed back to the terminal based on the AI ​​model policy query response, including: determining whether the AI ​​business model applied for by the terminal is within the subscription model range corresponding to the terminal based on the AI ​​model policy query response and the identification information, and obtaining a first determination result; obtaining AI model information based on the first determination result; and feeding back an AI model response message to the terminal based on the AI ​​model information.

[0282] In this way, the AI ​​model response message can be accurately fed back to the terminal; wherein, the identification information can correspond to the AI ​​business type information, and / or, the obtaining of AI model information according to the first determination result can include: when the first determination result indicates that the AI ​​business model applied for by the terminal is within the subscription model range corresponding to the terminal, directly obtaining the corresponding AI model information according to the identification information of the AI ​​business model applied for by the terminal; and / or, the AI ​​model request message carries artificial intelligence reasoning result requirement AIRR information (AIRR can be used as the model performance expected by the terminal, such as the expected model accuracy rate of more than 95%. Even if the terminal specifies the AI ​​type, there can be performance requirements), wherein, "according to the AI ​​model policy query response and the identification information, determine Determine whether the AI ​​business model applied for by the terminal is within the scope of the subscription model corresponding to the terminal, and obtain a first determination result” may include: when it is determined according to the AI ​​model policy query response that the AI ​​business model applied for by the terminal meets the AIRR information, determine whether the AI ​​business model applied for by the terminal is within the scope of the subscription model corresponding to the terminal according to the AI ​​model policy query response and the identification information, and obtain a first determination result; further, this solution may also include: when it is determined according to the AI ​​model policy query response that the AI ​​business model applied for by the terminal meets the AIRR information, the specific operation of “feeding back an AI model response message to the terminal according to the AI ​​model policy query response” corresponding to the following situation two or three may be performed, but it is not limited to this.

[0283] Among them, obtaining AI model information based on the first determination result includes: when the first determination result indicates that the AI ​​business model applied for by the terminal is not within the subscription model range corresponding to the terminal, determining the AI ​​model information corresponding to the terminal based on the AI ​​model request message, the stored AI model information and the model policy information carried by the AI ​​model policy query response.

[0284] This can support accurate acquisition of AI model information in the above-mentioned situations. The "stored AI model information" can be stored locally or stored in a third core network device, which is not limited here.

[0285] In an embodiment of the present disclosure, the AI ​​model request message further carries overhead-related information; the overhead-related information includes: at least one of data type information, data size information, and data dimension information; the model policy information carried by the AI ​​model policy query response includes: overhead limit information; the information transmission method further includes: determining, based on the overhead-related information, overhead information of the AI ​​service corresponding to the AI ​​model request message; the overhead information includes: at least one of computing time information, computing resource overhead information, and storage resource overhead information; when the first determination result indicates that the AI ​​service model applied for by the terminal is not within the scope of the subscription model corresponding to the terminal, determining the AI ​​model information based on the AI ​​model request message, locally stored AI model information, and the model policy information carried by the AI ​​model policy query response, includes: when the first determination result indicates a first situation, or when the first determination result indicates the first situation and the overhead information does not meet the overhead limit information, determining the AI ​​model information based on the overhead information, the AI ​​model request message, locally stored AI model information, and the model policy information carried by the AI ​​model policy query response; wherein the first situation refers to a situation where the AI ​​service model applied for by the terminal is not within the scope of the subscription model corresponding to the terminal.

[0286] In this way, AI model information of an AI model that better meets the needs can be obtained.

[0287] For situations two and three, the AI ​​model request message carries artificial intelligence reasoning result requirement AIRR information; and the AI ​​model strategy query request carries the AIRR information and AI business type information.

[0288] This makes it easier to support the acquisition of AI models that better meet terminal needs.

[0289] For situation two, the feeding back an AI model response message to the terminal based on the AI ​​model policy query response includes: determining AI model information based on the model strategy information and candidate model information carried by the AI ​​model policy query response; and feeding back an AI model response message to the terminal based on the AI ​​model information.

[0290] This allows for accurate feedback of AI model response messages.

[0291] Furthermore, the AI ​​model request message also carries overhead-related information; the overhead-related information includes: at least one of: data type information, data size information, and data dimension information; the model policy information carried by the AI ​​model policy query response includes: overhead limit information; the information transmission method also includes: determining the overhead information of the AI ​​service corresponding to the AI ​​model request message based on the overhead-related information; the overhead information includes: at least one of: computing time information, computing resource overhead information, and storage resource overhead information; determining the AI ​​model information based on the model policy information and candidate model information carried by the AI ​​model policy query response includes: determining the AI ​​model information based on the overhead information, the model policy information and candidate model information carried by the AI ​​model policy query response.

[0292] In this way, AI model information of an AI model that better meets the requirements can be obtained. The method may further include: extracting data features based on the overhead-related information; correspondingly, sending an AI model policy query request for the terminal to the second core network device based on the AI ​​model request message, including: sending an AI model policy query request for the terminal to the second core network device based on the AI ​​model request message and the data features; but is not limited to this.

[0293] For situation three, the AI ​​model response message is fed back to the terminal based on the AI ​​model policy query response, including: when the AI ​​model policy query response indicates that there is no model policy information corresponding to the terminal, an AI model training request is sent to a third core network device; the AI ​​model training request carries the AI ​​service type information and candidate AI model information; receiving the AI ​​model training response fed back by the third core network device; determining the AI ​​model information based on the AI ​​model training response; and feeding back an AI model response message to the terminal based on the AI ​​model information.

[0294] This can also support accurate feedback of AI model response messages. Among them, "the AI ​​model policy query response indicates that there is no model policy information corresponding to the terminal", which can be understood as: no AI model matching the AI ​​model request message is retrieved; and / or, the third core network device can be implemented as an artificial intelligence model storage function AIMSF device, and / or, the AI ​​model training request can also carry AIRR information, and the third core network device operates accordingly; and / or, the candidate AI model information can be obtained based on the correspondence between "AI business type-AI business model-evaluation index" (such as a relationship table), but is not limited to this.

[0295] Furthermore, the AI ​​model request message also carries overhead-related information; the overhead-related information includes: at least one of: data type information, data size information, and data dimension information; the model strategy information carried by the AI ​​model strategy query response includes: overhead limit information; the information transmission method also includes: determining the overhead information of the AI ​​service corresponding to the AI ​​model request message based on the overhead-related information; the overhead information includes: at least one of: computing time information, computing resource overhead information, and storage resource overhead information; determining the AI ​​model information based on the AI ​​model training response includes: determining the AI ​​model information based on the overhead information and the AI ​​model training response.

[0296] In this way, AI model information of an AI model that better meets the requirements can be obtained. Wherein, determining the AI ​​model information based on the overhead information and the AI ​​model training response may include: determining the AI ​​model information based on the overhead information, the AI ​​model training response and AIRR, but is not limited thereto.

[0297] The present disclosure also provides an information transmission method, which is applied to a second core network device, as shown in FIG4 , including:

[0298] Step 41: Receive an AI model policy query request for the terminal sent by the first core network device;

[0299] Step 42: Based on the AI ​​model policy query request, an AI model policy query response for the terminal is fed back to the first core network device.

[0300] Among them, the first core network device can be implemented as an artificial intelligence evaluation and selection function AIESF device, and / or, the second core network device can be implemented as a policy control function PCF device, and / or, the AI ​​model policy query request can carry the terminal identification (UE ID) of the terminal, but is not limited to this.

[0301] The information transmission method provided by the embodiment of the present disclosure receives an AI model policy query request for a terminal sent by a first core network device; based on the AI ​​model policy query request, an AI model policy query response for the terminal is fed back to the first core network device; it can support the provision of AI model information corresponding to the AI ​​model request message to the terminal, and further support the provision of AI models based on user needs; it effectively solves the problem in related technologies that cannot support the provision of AI models based on user needs.

[0302] This solution specifically includes three scenarios: Scenario 1: The terminal specifies an AI model; Scenario 2: The terminal does not specify an AI model, but the second core network device stores the corresponding AI policy (i.e., the model policy information corresponding to the terminal); and Scenario 3: The terminal does not specify an AI model, and the second core network device does not store the corresponding AI policy. Each scenario is described below:

[0303] For case one, case two and / or case three, the AI ​​model policy query request carries the terminal identifier of the terminal; the feedback of the AI ​​model policy query response for the terminal to the first core network device based on the AI ​​model policy query request includes: feedback of the AI ​​model policy query response for the terminal to the first core network device based on the terminal identifier.

[0304] This can accurately feedback the AI ​​model policy query response for the terminal.

[0305] For situations two and three, the AI ​​model policy query request carries AIRR information and AI service type information; based on the AI ​​model policy query request, the AI ​​model policy query response for the terminal is fed back to the first core network device, including: determining whether there is an AI historical policy corresponding to the AI ​​model policy query request based on the AIRR information and the AI ​​service type information, and obtaining a second determination result; based on the second determination result, the AI ​​model policy query response for the terminal is fed back to the first core network device.

[0306] In this way, even if the user does not specify an AI model, an AI model that meets the terminal requirements can be obtained, and accurate AI model strategy query response feedback can be performed.

[0307] The method of feeding back an AI model policy query response for the terminal to the first core network device based on the second determination result includes: (1) when the second determination result indicates that there is an AI historical policy corresponding to the AI ​​model policy query request, feeding back an AI model policy query response for the terminal to the first core network device based on the AI ​​historical policy; the AI ​​historical policy includes: model policy information and candidate model information; (2) when the second determination result indicates that there is no AI historical policy corresponding to the AI ​​model policy query request, feeding back an AI model policy query response to the first core network device to indicate that there is no model policy information corresponding to the terminal.

[0308] In this way, for the above-mentioned situations 2 or 3, an accurate AI model policy query response for the terminal can be obtained. Among them, "indicating that there is no model policy information corresponding to the terminal" can be understood as: no AI model matching the AI ​​model request message initiated by the terminal was retrieved, but it is not limited to this. Among them, the model policy information may include the AI ​​model's overhead information for each AI service, such as computing resource overhead information, storage resource overhead information, etc., which is not limited here.

[0309] The present disclosure also provides an information transmission method, which is applied to a terminal, as shown in FIG5 , and includes:

[0310] Step 51: Send an AI model request message to the first core network device;

[0311] Step 52: Receive the AI ​​model response message fed back by the first core network device; the AI ​​model response message carries AI model information.

[0312] Among them, the first core network device can be implemented as an artificial intelligence evaluation and selection function AIESF device, and / or the AI ​​model request message can carry the terminal identifier (UE ID) of the terminal, and / or the AI ​​model information may include: at least one of the information such as AI Model ID (AI model identifier), AI model accuracy, and estimated training time, and / or step 51 may include: sending an AI model request message to the first core network device according to the AI ​​service type information; and / or, after step 52, it may also include: according to the AI ​​model information, using the corresponding AI model to execute the generated AI service, but is not limited to this.

[0313] The information transmission method provided by the embodiment of the present disclosure sends an AI model request message to the first core network device; receives an AI model response message fed back by the first core network device; the AI ​​model response message carries AI model information; it can support the acquisition of AI model information corresponding to the AI ​​model request message, and then support the provision of AI models based on user needs; it effectively solves the problem that related technologies cannot support the provision of AI models based on user needs.

[0314] Furthermore, before sending the AI ​​model request message to the first core network device, it also includes: sending an AI model discovery message to the first core network device; the AI ​​model discovery message carries AIRD information; and receiving an AI model discovery response fed back by the first core network device.

[0315] This allows the first core network device to first identify the AI ​​service type information for subsequent use. The AI ​​model discovery response may carry the AI ​​service type information, but is not limited thereto.

[0316] Among them, the AI ​​model request message carries the identification information of the AI ​​business model applied for by the terminal; and / or, the AI ​​model request message carries overhead-related information; the overhead-related information includes: at least one of: data type information, data size information and data dimension information; and / or, the AI ​​model request message carries AIRR information.

[0317] This can support the terminal to obtain accurate AI model response messages. Among them, the "identification information of the AI ​​business model applied for by the terminal" can correspond to the AI ​​business type information, but is not limited to this.

[0318] The present disclosure also provides an information transmission method, which is applied to a third core network device. As shown in FIG6 , the method includes:

[0319] Step 61: Receive an AI model training request sent by a first core network device; the AI ​​model training request carries AI service type information and candidate AI model information;

[0320] Step 62: Based on the AI ​​model training request, an AI model training response is fed back to the first core network device, and AI model training information corresponding to the AI ​​model training request is sent to the second core network device.

[0321] Among them, the first core network device can be implemented as an artificial intelligence evaluation and selection function AIESF device, and / or, the third core network device can be implemented as an artificial intelligence model storage function AIMSF device, and / or, the candidate AI model information can be obtained based on the correspondence between "AI business type-AI business model-evaluation index" (such as a relationship table), and / or, "AI model training information" can include: terminal identification, the optimal AI business model ID (corresponding to the AI ​​model request message) and at least one of the corresponding hyperparameter group IDs (AI business model ID), but is not limited to this.

[0322] The information transmission method provided by the embodiment of the present disclosure receives an AI model training request sent by a first core network device; the AI ​​model training request carries AI service type information and candidate AI model information; based on the AI ​​model training request, an AI model training response is fed back to the first core network device, and AI model training information corresponding to the AI ​​model training request is sent to the second core network device; it can support the provision of AI model information corresponding to the AI ​​model request message to the terminal, and further support the provision of AI models based on user needs; it well solves the problem that related technologies cannot support the provision of AI models based on user needs.

[0323] Among them, the feeding back of the AI ​​model training response to the first core network device according to the AI ​​model training request includes: training the candidate AI model according to the AI ​​service type information and the candidate AI model information, and obtaining an evaluation result; and feeding back the AI ​​model training response to the first core network device according to the evaluation result.

[0324] In this way, the AI ​​model training response can be obtained specifically and accurately.

[0325] In the embodiment of the present disclosure, the AI ​​model training request also carries AIRR information; the candidate AI model training is performed according to the AI ​​business type information and the candidate AI model information, and an evaluation result is obtained, including: the candidate AI model training is performed according to the AI ​​business type information and the candidate AI model information to obtain a training result; the weight of the evaluation index is determined according to the AIRR information; and the evaluation result is obtained according to the weight and the training result.

[0326] In this way, the evaluation results corresponding to the candidate AI models can be accurately obtained. Among them, "according to the AI ​​business type information and the candidate AI model information, the candidate AI model is trained to obtain the training results; according to the AIRR information, the weight of the evaluation index is determined; according to the weight and the training results, the evaluation results are obtained", which may specifically include: training multiple candidate AI models in parallel (such as starting multiple training processes to train different AI models at the same time), determining the evaluation index corresponding to each candidate AI model according to the correspondence between "AI business type-AI business model-evaluation index" (such as a relationship table), and using the evaluation index to evaluate the output results of each candidate AI model to obtain the training results; determining the importance ranking of the evaluation index according to the AIRR information, assigning corresponding weights to each evaluation index, and obtaining a comprehensive training score (i.e., evaluation result) according to the weights and the evaluation index results calculated by each candidate AI model (such as multiplying the evaluation index results calculated by each candidate AI model by the corresponding weights and adding them up); but it is not limited to this.

[0327] It is noted here that the relevant contents of the above-mentioned methods on each side (such as the first core network device side and the terminal side methods) can refer to each other, and the repeated contents will not be repeated.

[0328] The information transmission method provided in the embodiment of the present disclosure is illustrated below with examples. The first core network device takes the artificial intelligence evaluation and selection function AIESF device as an example, the second core network device takes the policy control function PCF device as an example, and the third core network device takes the artificial intelligence model storage function AIMSF device as an example.

[0329] In response to the above technical problems, and taking into account: in order to make the 6G network have the ability of intelligent endogenous generation, it should not only be able to provide AI model discovery and services to the network element functions within the network, but also should be able to provide multiple AI types of model discovery to mobile communication user UE, and should be able to perform reasonable and efficient AI model selection according to AI business needs; wherein, the above-mentioned network element functions and mobile communication user UE are users with AI needs; the user has registered with the network before performing AI model discovery and on-demand selection, and has generated AI services that need to be processed. Based on this, the embodiment of the present disclosure provides an information transmission method, which can be specifically implemented as a 6G intelligent endogenous AI model discovery and on-demand selection method, mainly involving: in order to realize AI model discovery and on-demand selection, as shown in Figure 7, two new network functions are added to the network structure, namely AI Evaluation and Selection Function (AIESF) and AI Model Storage Function (AIMSF). AIESF and AIMSF are introduced respectively below. In addition, PCF in Figure 7 represents Policy Control Function, UDR represents Unified Data Repository, UDSF represents Unstructured Data Storage Network Function, AMF represents Access and Mobility Management Function, SMF represents Session Management Function, NRF represents Network Repository Function, RAN represents Radio Access Network, UPF represents User Plane Function, DN represents Data Network, and N1, N2, N3, N4 and N6 represent interfaces between corresponding network elements.

[0330] 1. AI Evaluation and Selection Function (AIESF):

[0331] 1) It can be deployed on the core network side;

[0332] 2) It can evaluate the computing resource and storage resource overhead as well as the computing time;

[0333] 3) It can support AI model discovery, receive AI model discovery requests from the RAN side or other network element functions in the core network, and feedback the corresponding discovered AI models;

[0334] 4) Ability to maintain (including adding, removing, and updating) AI model information stored by AIMSF and synchronize AI model information with AIMSF; AI model information includes model name, identification ID, model description, etc.

[0335] 5) It can evaluate whether the submitted AI task has a matching training model (i.e., AI model), evaluate information such as data type and size, and weigh indicators such as computational time and model output accuracy to select the optimal AI model. Furthermore, it can combine the AI ​​strategy information provided by PCF (corresponding to the aforementioned model strategy information) to make intelligent AI model selection decisions.

[0336] 2. AI Model Storage Function (AIMSF):

[0337] 1) Can be deployed on the core network side;

[0338] 2) It can store multiple types of AI models, see Table 1-1 below. AIMSF can store pre-configured AI models and hyperparameters (corresponding to the AI ​​models); specifically, the search space of AIMSF can be composed of pre-configured AI models and hyperparameters (corresponding to the AI ​​models), but is not limited to this.

[0339] 3) It can support receiving AI model training requests and provide corresponding AI business model training and inference services based on the training requests;

[0340] 4) It can be responsible for maintaining AI models and corresponding hyperparameter data suitable for solving various problems (corresponding to service requests for various AI models). This can be understood as storing relevant information after training the AI ​​model.

[0341] 5) It can intelligently iterate and update stored AI models or obtain more appropriate models based on AI business types; it can also support adding and / or deleting AI models. In addition, operation and maintenance personnel can also add or delete AI models through the management platform.

[0342] Table 1-1 Comparison of AI business types, matching business models, and evaluation indicators

[0343] Among them, SVM stands for Support Vector Machines model, SGD stands for Stochastic Gradient Descent, KNN stands for K-Nearest Neighbor, RF stands for Random Forest, DT stands for Decision Tree, LR stands for Logistic Regression model, CNN stands for Convolutional Neural Network, LTSM stands for Long Short-Term Memory network, K-means stands for K-means clustering algorithm, and YOLO stands for You Only Look Once.

[0344] F1-Score stands for balanced F Score, which is the harmonic mean of precision and recall.

[0345] MSE stands for Mean Square Error, RMSE stands for Root Mean Square Error, MAE stands for Mean Absolute Error, R-squared stands for goodness of fit, SSE stands for Sum of Squares for Error, and SI stands for Silhouette Index.

[0346] In this solution, AI models can be pre-deployed in AIMSF, which stores various types of pre-trained models. AI model generation is related to AI model training and will not be elaborated on in detail here.

[0347] The following is a specific example to illustrate this solution.

[0348] Example 0: The user specifies the AI ​​model;

[0349] This embodiment can be implemented using the architecture shown in FIG8 , and specifically as shown in FIG9 , includes the following steps:

[0350] Step 91. The user sends an AI model discovery message to the AIESF (corresponding to the above-mentioned sending of an AI model discovery message to the first core network device), where the message content may include user information (UE Information) and AI service requirements description (AI Requirements Description, AIRD). When the user is a mobile communication user, the user information may include user ID (such as UE ID), application information that triggers the AI ​​service, manufacturer identification, and other information. When the user is a network element function NF within the network, the user information may include information such as NF Profile (network element function configuration). Among them, AIRD may include problem description, data source (whether data collection is requested), and other information.

[0351] Step 92: AIESF analyzes the AI ​​model discovery message and determines the AI ​​service type according to AIRD; corresponding to the above-mentioned determination of AI service type information according to the AIRD information.

[0352] AIESF responds to the user and sends an AI model discovery response to the user (corresponding to the above-mentioned feedback of the AI ​​model discovery response to the terminal), indicating that AIESF has received the AI ​​service demand (which can also be understood as AI business demand) and classified the AI ​​type according to the demand description. The response content may include the AI ​​business type (corresponding to the above-mentioned AI business type information).

[0353] Step 93. The user sends an AI model request message (corresponding to the above-mentioned sending of an AI model request message to the first core network device), where the message content may include user ID (such as UE ID), data type (Data Type), data size (Data Size), data dimension (Data Dimension), AI inference result requirements (AI Inference Result Requirements, AIRR), and relevant information of the applied AI business model (such as AI Model ID, which may correspond to the received AI business type information). Among them, the AI ​​business model can be provided based on whether the user has historical experience and knowledge of AI training; specifically, this embodiment considers the user specifying the AI ​​model, and the AI ​​model sent in step 93 can be specified by the user based on historical experience information.

[0354] Step 94: The AIESF queries the PCF (sending a user AI policy subscription query message) for the user's subscribed user AI model policy to determine whether the AI ​​service model applied for by the user is within the model range subscribed by the user. Corresponding to the aforementioned AI model request message, the AIESF sends an AI model policy query request for the terminal to the second core network device. The user AI policy subscription query message may carry the UE ID.

[0355] Step 95. The PCF responds to the user AI model policy query and returns a user AI model policy message (corresponding to the above-mentioned receiving the AI ​​model policy query request for the terminal sent by the first core network device; according to the AI ​​model policy query request, the AI ​​model policy query response for the terminal is fed back to the first core network device). The user AI model policy message may include at least one of the AI ​​model type (AI Type) subscribed by the user, AI service priority (Priority), historical AI model selection information and hyperparameters (corresponding to History in the figure), computing resource and storage resource consumption limits (corresponding to Limitation in the figure), model charges, transmission overhead, and other information; the user AI model policy message may also include UE ID.

[0356] The AIESF evaluates the computation time and overhead of computing resources, storage resources, etc. (and may also include extracting data features) based on information such as the data type and data size in the AI ​​model request message; corresponding to the above, the AIESF determines the overhead information of the AI ​​service corresponding to the AI ​​model request message based on the overhead related information; the overhead information includes at least one of computation time information, computing resource overhead information, and storage resource overhead information. The "AIESF evaluates the computation time and overhead of computing resources, storage resources, etc. based on information such as the data type and data size in the AI ​​model request message" may be performed when the AIESF determines that the AI ​​service model applied for by the terminal meets the AIRR based on the AI ​​model policy message; further, when the AIESF determines that the AI ​​service model applied for by the terminal does not meet the AIRR based on the AI ​​model policy message, the AIESF may proceed to the "AIESF evaluates the computation time and overhead of computing resources, storage resources, etc. based on information such as the data type and data size in the AI ​​model request message, and extracts data features" of the following embodiment 1 or 2 to complete the subsequent operation of feeding back the AI ​​model policy query response to the terminal (for example, continuing to execute steps 116-118 in embodiment 1), but is not limited thereto.

[0357] Then proceed to step 96a or 96b:

[0358] Step 96a. If the AI ​​business model applied for by the user is within the model range subscribed by the user and meets the Limitation provided by the PCF, the AIESF sends an AI model feedback message (also called an AI model response message) to the user. The message content may include AI Model ID (consistent with the AI ​​Model ID in step 93), AI model accuracy, estimated training time and other information; corresponding to the above-mentioned case where the first determination result indicates that the AI ​​business model applied for by the terminal is within the subscription model range corresponding to the terminal, the AI ​​model information is determined according to the identification information (this information may include: AI Model ID, AI model accuracy, estimated training time and other information).

[0359] Step 96b. If the AI ​​business model applied for by the user is not within the model range subscribed by the user, the AIESF can make the best model selection decision based on the AI ​​model information stored by the maintained AIMSF, and in combination with the received user AI model request message and the AI ​​model policy message provided by the PCF; corresponding to the above-mentioned case where the first determination result indicates that the AI ​​business model applied for by the terminal is not within the subscription model range corresponding to the terminal, the AI ​​model information corresponding to the terminal is determined based on the AI ​​model request message, the stored AI model information, and the model policy information carried by the AI ​​model policy query response. Then, the AIESF sends an AI model response message to the user (corresponding to the above-mentioned feedback of the AI ​​model response message to the terminal based on the AI ​​model information), indicating that the user failed to specify the AI ​​model (the content of the message may include the reason for the failure), and provides the user with recommended AI model information, which may include information such as AI Model ID, AI model accuracy, and estimated training time.

[0360] In this solution, the AI ​​model is stored in AIMSF. AIESF evaluates a series of factors and selects the most suitable one from AIMSF (AIESF is responsible for maintaining the AI ​​model information stored in AIMSF); but this is not limited to this.

[0361] In addition, the relevant content of the AI ​​model request message mentioned above is introduced as follows:

[0362] a) Data Type, which may include at least one of the following types: text TXT, image IMG, audio AUD, video VID, data DAT, etc.

[0363] b) AI service types (AI Types), which may include at least one of: Classification (Classification, Cla), Prediction (Pred), Regression (Regression, Reg), Clustering (Clustering, Clust), Computer Vision (Computer Vision, CV), etc.

[0364] c) AI business model (AI Model), which may include: support vector machine (SVM), gradient descent (SGD), K-nearest neighbor (KNN), neural network (Neural Network), logistic regression (LR), decision tree (DT), convolutional neural network (CNN), long short-term memory (LSTM), K-means clustering (K-means), random forest (RF), YOLO (You Only Look Once) and other models;

[0365] d) AI Inference Result Requirements (AIRR), which may include at least one of the following indicators: expected accuracy, mean square error, training time, generalization, consistency between loss function and optimization objective, and fairness.

[0366] Example 1: The user does not specify an AI model, but PCF has stored the corresponding AI strategy, historical experience and knowledge;

[0367] This embodiment can be implemented using the architecture shown in FIG10 , and specifically as shown in FIG11 , includes the following steps:

[0368] Step 111. The user sends an AI model discovery message to the AIESF (corresponding to the sending of the AI ​​model discovery message to the first core network device mentioned above), where the message content may include user information (UE Information) and AI service requirements description (AI Requirements Description, AIRD). When the user is a mobile communication user, the user information may include user ID (such as UE ID), application information that triggers the AI ​​service, manufacturer identification, and other information. When the user is a network element function NF within the network, the user information may include information such as NF Profile. Among them, AIRD may include problem description, data source (whether data collection is requested), and other information.

[0369] Step 112: AIESF analyzes the AI ​​model discovery message and determines the AI ​​service type according to the AIRD; corresponding to the above-mentioned determination of the AI ​​service type information according to the AIRD information.

[0370] AIESF responds to the user and sends an AI model discovery response to the user (corresponding to the above-mentioned feedback of the AI ​​model discovery response to the terminal), indicating that AIESF has received the AI ​​service demand (which can also be understood as AI business demand) and classified the AI ​​type according to the demand description. The response content may include the AI ​​business type (corresponding to the above-mentioned AI business type information).

[0371] Step 113. The user sends an AI model request message (corresponding to the above-mentioned sending of the AI ​​model request message to the first core network device), where the message content may include the user ID (such as UE ID), data type (Data Type), data size (Data Size), data dimension (Data Dimension), and AI inference result requirements (AI Inference Result Requirements, AIRR). The AI ​​business model may be provided based on whether the user has historical experience and knowledge of AI training.

[0372] The AI ​​model request message in step 113 does not carry: relevant information of the applied AI business model (such as AI Model ID, which may correspond to the received AI business type information); specifically, the difference between step 113 of this embodiment and step 93 of embodiment 0 is that: in this embodiment, the AI ​​model request message does not provide an AI Model ID, that is, the AI ​​model is not specified.

[0373] Step 114: The AIESF queries the PCF for the user's subscribed user AI model policy (sending a user AI policy subscription query message). Corresponding to the aforementioned AI model request message, the AIESF sends an AI model policy query request for the terminal to the second core network device. The user AI policy subscription query message may carry the UE ID.

[0374] Step 115. The PCF responds to the user AI model policy query and returns a user AI model policy message (corresponding to the above-mentioned receiving the AI ​​model policy query request for the terminal sent by the first core network device; according to the AI ​​model policy query request, the AI ​​model policy query response for the terminal is fed back to the first core network device). The user AI model policy message may include at least one of the AI ​​model type (AI Type) subscribed by the user, AI service priority (Priority), historical AI model selection information and hyperparameters (corresponding to History in the figure), computing resource and storage resource consumption limits (corresponding to Limitation in the figure), model charges, transmission overhead, and other information; the user AI model policy message may also include UE ID.

[0375] AIESF evaluates the computing time and the overhead of computing resources, storage resources, etc. according to the data type and data size in the AI ​​model request message (corresponding to the above-mentioned determination of the overhead information of the AI ​​service corresponding to the AI ​​model request message based on the overhead-related information; the overhead information includes: at least one of computing time information, computing resource overhead information and storage resource overhead information), and extracts data features; it can also be understood that AIESF evaluates the AI ​​model request information (corresponding to the AI ​​model request message) and generates information such as data features and overhead.

[0376] Step 116. The AIESF sends an AI policy query request to the PCF. The request may include at least one of the following information: user ID (i.e., UE ID), data features, AI inference result requirements (AIRR), and AI service type. The request may be used to trigger the PCF to execute: determine whether there is historical experience (AI model-related experience information) corresponding to the AI ​​service generated by the user based on the above information.

[0377] Based on the information in the provided AI policy query request, PCF retrieves historical experience and knowledge that matches AIRR and AI business types, and determines whether there is a matched AI historical policy; corresponding to the above, based on the AIRR information and the AI ​​business type information, it determines whether there is an AI historical policy corresponding to the AI ​​model policy query request, and obtains a second determination result.

[0378] It is noted that in this embodiment, the request sent by the AIESF to the PCF in step 114 and the request sent by the AIESF to the PCF in step 116 may be included in the above-mentioned AI model policy query request for the terminal, that is, two sub-requests belonging to the request; this embodiment is carried out in a manner of sending these two sub-requests separately, but of course they can also be sent together, which is not limited here.

[0379] Step 117. If the PCF matches a matching AI policy, it returns the AI ​​policy (AI business model and corresponding hyperparameters) to the AIESF; corresponding to the above-mentioned second determination result, the AI ​​model policy query response for the terminal is fed back to the first core network device; the AI ​​model response message carries AI model information; specifically, corresponding to the case where the second determination result indicates that there is an AI historical policy corresponding to the AI ​​model policy query request, the AI ​​model policy query response for the terminal is fed back to the first core network device according to the AI ​​historical policy; the AI ​​historical policy includes: model policy information and candidate model information. Specifically, the PCF can provide one or more matching AI policy Profile Lists (configuration lists) to the AIESF based on the matching results. The Profile List may include recorded computing resource overhead, storage resource overhead, model charges, model performance, training time and other information. Among them, the information contained in each AI strategy carried by the Profile List can assist the AIESF in selecting an AI model after receiving the Profile List. For example, after receiving the Profile List, the AIESF selects an AI model based on information such as the AIRR provided by the terminal. Specifically, if the AIRR requires a time consumption of less than 100 milliseconds, the AIESF can accordingly exclude the AI ​​models provided by the PCF (excluding some models) and finally select one of them. In addition, the information contained in each AI strategy carried by the Profile List can also assist the AIESF in providing feedback to the terminal, such as feedback on the estimated training time.

[0380] After receiving the AI ​​policy query response from the PCF, the AIESF integrates the user AI policy message and the AI ​​policy query response provided by the PCF, and combines the resource overhead information and other information evaluated by the AIESF to make an AI model selection decision among the multiple AI models provided by the PCF; corresponding to the above-mentioned determination of the AI ​​model information based on the model policy information and candidate model information carried by the AI ​​model policy query response. The AI ​​policy query response may carry at least one of the following information: the UE ID, the candidate AI Model ID, and the hyperparameters corresponding to the candidate AI Model ID.

[0381] Step 118. AIESF sends an AI model feedback message to the user, which may include information such as AI Model ID, AI model accuracy, and estimated training time; corresponding to the above-mentioned AI model response message fed back to the terminal based on the AI ​​model information.

[0382] Example 2: The user does not specify an AI model, PCF does not retrieve the corresponding AI strategy, and has no historical experience and knowledge;

[0383] This embodiment can be implemented using the architecture shown in FIG12 , and specifically as shown in FIG13 , includes the following steps:

[0384] Step 131. The user sends an AI model discovery message to the AIESF (corresponding to the above-mentioned sending of an AI model discovery message to the first core network device), where the message content may include user information (UE Information) and AI service requirements description (AI Requirements Description, AIRD). When the user is a mobile communication user, the user information may include user ID (such as UE ID), application information that triggers the AI ​​service, manufacturer identification, and other information. When the user is a network element function NF within the network, the user information may include information such as NF Profile. Among them, AIRD may include problem description, data source (whether data collection is requested), and other information.

[0385] Step 132: AIESF analyzes the AI ​​model discovery message and determines the AI ​​service type according to AIRD; corresponding to the above-mentioned determination of AI service type information according to the AIRD information.

[0386] AIESF responds to the user and sends an AI model discovery response to the user (corresponding to the above-mentioned feedback of the AI ​​model discovery response to the terminal), indicating that AIESF has received the AI ​​service demand (which can also be understood as AI business demand) and classified the AI ​​type according to the demand description. The response content may include the AI ​​business type (corresponding to the above-mentioned AI business type information).

[0387] Step 133. The user sends an AI model request message (corresponding to the above-mentioned sending of the AI ​​model request message to the first core network device). The message content may include the user ID (e.g., UE ID), data type (Data Type), data size (Data Size), data dimension (Data Dimension), and AI inference result requirements (AI Inference Result Requirements, AIRR). The AI ​​business model may be provided based on whether the user has historical experience and knowledge of AI training.

[0388] The AI ​​model request message in step 133 does not carry: relevant information of the applied AI business model (such as the AI ​​Model ID, which may correspond to the received AI business type information); specifically, the difference between step 133 of this embodiment and step 93 of embodiment 0 is that: in this embodiment, the AI ​​model request message does not provide the AI ​​Model ID, and no matching AI model is subsequently retrieved based on historical experience, and an AI model comparison is required. For details, see the following steps.

[0389] Step 134: The AIESF queries the PCF for the user AI model policy subscribed by the user (by sending a user AI policy subscription query message). Corresponding to the above-mentioned AI model request message, the AIESF sends an AI model policy query request for the terminal to the second core network device. The user AI policy subscription query message may carry the UE ID.

[0390] Step 135. The PCF responds to the user AI model policy query and returns a user AI model policy message (corresponding to the above-mentioned receiving the AI ​​model policy query request for the terminal sent by the first core network device; according to the AI ​​model policy query request, the AI ​​model policy query response for the terminal is fed back to the first core network device). The user AI model policy message may include at least one of the AI ​​model type (AI Type) subscribed by the user, AI service priority (Priority), historical AI model selection information and hyperparameters (corresponding to History in the figure), computing resource and storage resource consumption limits (corresponding to Limitation in the figure), model charges, transmission overhead, and other information; the user AI model policy message may also include UE ID.

[0391] AIESF evaluates the computing time and the overhead of computing resources, storage resources, etc. according to the data type and data size in the AI ​​model request message (corresponding to the above-mentioned determination of the overhead information of the AI ​​service corresponding to the AI ​​model request message based on the overhead-related information; the overhead information includes: computing time information and at least one of computing resource overhead information and storage resource overhead information), and extracts data features; it can also be understood that AIESF evaluates the AI ​​model request information (corresponding to the AI ​​model request message) and generates information such as data features and overhead.

[0392] Step 136. The AIESF sends an AI policy query request to the PCF. The request may include at least one of the following information: user ID (i.e., UE ID), data features, AI inference result requirements (AIRR), and AI service type. The request may be used to trigger the PCF to execute: determine whether there is historical experience (AI model-related experience information) corresponding to the AI ​​service generated by the user based on the above information.

[0393] Based on the information in the AI ​​policy query request provided in step 136, the PCF retrieves historical experience and knowledge that matches the AIRR and AI business type, and determines whether there is a matched AI historical policy; corresponding to the above, based on the AIRR information and the AI ​​business type information, it determines whether there is an AI historical policy corresponding to the AI ​​model policy query request, and obtains a second determination result.

[0394] It is noted that in this embodiment, the request sent by the AIESF to the PCF in step 134 and the request sent by the AIESF to the PCF in step 136 may be included in the above-mentioned AI model policy query request for the terminal, that is, two sub-requests belonging to the request; this embodiment is carried out in a manner of sending these two sub-requests separately, but of course they can also be sent together, which is not limited here.

[0395] Step 137: The PCF does not match a matching AI policy, and returns a null value (Void) to the AIESF, indicating that no AI model was retrieved (i.e., returns an AI policy query response carrying a null value). This corresponds to the above-mentioned situation where, when the second determination result indicates that no AI historical policy corresponding to the AI ​​model policy query request exists, the PCF returns an AI model policy query response to the first core network device, indicating that no model policy information corresponding to the terminal exists. The AI ​​policy query response may also carry the UE ID.

[0396] After AIESF receives the message that the AI ​​strategy is empty, it triggers the AI ​​model selection process.

[0397] Step 138. AIESF queries the corresponding "Table 1-1 AI business type and matching business model and evaluation index comparison table" according to the judged AI business type, and sends an AI model comparison request to AIMSF. The request may include the content of the AI ​​model request message in step 133, as well as the AI ​​business type and the corresponding multiple AI business model IDs; corresponding to the above-mentioned case where the AI ​​model policy query response indicates that there is no model policy information corresponding to the terminal, an AI model training request is sent to the third core network device; the AI ​​model training request carries the AI ​​business type information and candidate AI model information.

[0398] AIMSF trains multiple AI models in parallel, calculates weighted training scores, and generates a Profile List; specifically, it may include: trying multiple AI models in parallel, starting multiple training processes to train different AI models at the same time, and evaluating the output results of each AI model according to the evaluation indicators provided in Table 1-1; corresponding to the above-mentioned AI business type information and candidate AI model information, candidate AI models are trained to obtain training results. Furthermore, the importance ranking of evaluation indicators can be determined according to the requirements of AI reasoning results, and corresponding weights can be assigned to each evaluation indicator. The evaluation indicator results calculated by each model are multiplied by the corresponding weights, and they are summed up (that is, the indicators multiplied by the weights corresponding to each model are summed up) to obtain a comprehensive training score (for each model) and generate an AI model Profile List; corresponding to the above-mentioned determination of the weights of evaluation indicators based on the AIRR information; and the evaluation results are obtained based on the weights and training results.

[0399] Step 139. The AIMSF stores the AI ​​model and hyperparameter data for this training. The AIMSF also reports the AI ​​strategy information to the PCF (corresponding to the AI ​​model training information corresponding to the AI ​​model training request sent to the second core network device). The AI ​​strategy information may include the user ID (corresponding to the terminal identifier), the optimal AI business model ID (corresponding to the AI ​​model request message), and the corresponding hyperparameter group ID (AI business model ID) so as to be saved as historical experience and knowledge for subsequent rapid retrieval.

[0400] Step 1310. AIMSF selects the top three models with the highest comprehensive training scores and sends the AI ​​model Profile List to AIESF; corresponding to the above, based on the evaluation results, the AI ​​model training response is fed back to the first core network device.

[0401] After AIESF receives the AI ​​model Profile List sent by AIMSF, it makes an AI model selection decision based on the Profile List, the user AI policy message provided by PCF, the overhead information evaluated by AIESF, AIRR and other information; corresponding to the above-mentioned determination of AI model information based on the overhead information and the AI ​​model training response.

[0402] Step 1311. AIESF sends an AI model feedback message to the user, which may include information such as AI Model ID, AI model accuracy, and estimated training time; corresponding to the above-mentioned AI model response message fed back to the terminal based on the AI ​​model information.

[0403] From the above, Example 1 and Example 2 are two different situations: Example 1 is to retrieve one or more AI models based on the historical experience obtained by PCF, and AIESF performs model selection among them; Example 2 is that no matching historical experience is retrieved, and AIMSF is required to perform model comparison and selection; the processes after step 7 of the two are different.

[0404] It is to be noted that the relevant contents of the above embodiments can be referred to each other, and the repeated parts will not be repeated here.

[0405] From the above, the embodiment of the present disclosure: Aiming at the architecture of 6G network intelligence endogenous and the vision of intelligent inclusiveness, a method of AI model discovery and on-demand selection is proposed; specifically, by adding two network functions, AIESF and AIMSF, the proposed method can not only serve the network element functions within the network, but also provide AI services to mobile communication users UE, realize AI model discovery, and the proposed method can also realize on-demand selection of AI models in combination with information such as business needs. Based on this, the method provided by the embodiment of the present disclosure is conducive to the realization of 6G network intelligence endogenous, and can flexibly respond to different business needs and scenarios to make on-demand selection of various AI types and models.

[0406] In summary, the solution provided by the embodiments of the present disclosure has the following advantages:

[0407] (1) For the future 6G intelligent endogenous architecture, it can support AI model discovery and make on-demand AI model selection decisions based on user-provided data and AI business needs.

[0408] (2) The AI ​​capabilities of the network are expanded. The proposed AIESF and AIMSF with AI capabilities can not only serve the internal network but also provide AI services to the outside world.

[0409] (3) The flexibility and efficiency of AI model selection are improved. A search table for different AI types is established, which stores new AI training and inference strategies and corresponding hyperparameters. This allows for flexible and efficient on-demand selection of multiple AI types and models based on different business needs and scenarios.

[0410] The embodiment of the present disclosure further provides an information transmission device, which is a first core network device. As shown in FIG14 , the device includes a memory 141, a transceiver 142, and a processor 143.

[0411] The memory 141 is used to store computer programs; the transceiver 142 is used to send and receive data under the control of the processor 143; the processor 143 is used to read the computer program in the memory 141 and perform the following operations:

[0412] Receiving, via the transceiver 142, an artificial intelligence (AI) model request message sent by a terminal;

[0413] According to the AI ​​model request message, sending an AI model policy query request for the terminal to the second core network device through the transceiver 142;

[0414] Receiving, through the transceiver 142, an AI model policy query response for the terminal fed back by the second core network device;

[0415] According to the AI ​​model strategy query response, an AI model response message is fed back to the terminal; the AI ​​model response message carries AI model information.

[0416] The information transmission device provided by the embodiment of the present disclosure receives an artificial intelligence (AI) model request message sent by a terminal; sends an AI model policy query request for the terminal to a second core network device based on the AI ​​model request message; receives an AI model policy query response for the terminal fed back by the second core network device; and feeds back an AI model response message to the terminal based on the AI ​​model policy query response; the AI ​​model response message carries AI model information; and can support the provision of corresponding AI model information to the terminal based on the AI ​​model request message, thereby supporting the provision of AI models based on user needs; and effectively solves the problem in related technologies that cannot support the provision of AI models based on user needs.

[0417] Specifically, the transceiver 142 is configured to receive and send data under the control of the processor 143 .

[0418] In FIG14 , the bus architecture may include any number of interconnected buses and bridges, specifically various circuits linking together one or more processors represented by processor 143 and memory represented by memory 141. 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 and are therefore not further described herein. The bus interface provides an interface. The transceiver 142 may be a plurality of components, i.e., a transmitter and a receiver, providing a unit for communicating with various other devices on a transmission medium, such as a wireless channel, a wired channel, an optical cable, and the like. The processor 143 is responsible for managing the bus architecture and general processing, and the memory 141 may store data used by the processor 143 when performing operations.

[0419] The processor 143 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.

[0420] Furthermore, the operation also includes: before receiving the artificial intelligence AI model request message sent by the terminal, receiving the AI ​​model discovery message sent by the terminal through the transceiver; the AI ​​model discovery message carries artificial intelligence service requirement description AIRD information; according to the AIRD information, determining the AI ​​service type information, and feeding back the AI ​​model discovery response to the terminal through the transceiver.

[0421] Among them, the AI ​​model request message carries the identification information of the AI ​​business model applied for by the terminal; the AI ​​model policy query response is fed back to the terminal. It includes: determining whether the AI ​​business model applied for by the terminal is within the subscription model range corresponding to the terminal according to the AI ​​model policy query response and the identification information, and obtaining a first determination result; obtaining AI model information according to the first determination result; and feeding back an AI model response message to the terminal according to the AI ​​model information.

[0422] In an embodiment of the present disclosure, obtaining AI model information based on the first determination result includes: when the first determination result indicates that the AI ​​business model applied for by the terminal is not within the subscription model range corresponding to the terminal, determining the AI ​​model information corresponding to the terminal based on the AI ​​model request message, the stored AI model information and the model policy information carried by the AI ​​model policy query response.

[0423] The AI ​​model request message further carries overhead-related information; the overhead-related information includes: at least one of data type information, data size information, and data dimension information; the model policy information carried by the AI ​​model policy query response includes: overhead limit information; the operation further includes: determining, based on the overhead-related information, overhead information of the AI ​​service corresponding to the AI ​​model request message; the overhead information includes: at least one of calculation time information, calculation resource overhead information, and storage resource overhead information; when the first determination result indicates that the AI ​​service model applied for by the terminal is not within the scope of the subscription model corresponding to the terminal, determining the AI ​​model information according to the AI ​​model request message, the locally stored AI model information, and the model policy information carried by the AI ​​model policy query response, includes: when the first determination result indicates a first situation, or when the first determination result indicates the first situation and the overhead information does not meet the overhead limit information, determining the AI ​​model information according to the overhead information, the AI ​​model request message, the locally stored AI model information, and the model policy information carried by the AI ​​model policy query response; wherein the first situation refers to a situation where the AI ​​service model applied for by the terminal is not within the scope of the subscription model corresponding to the terminal.

[0424] In an embodiment of the present disclosure, the AI ​​model request message carries AIRR information of artificial intelligence reasoning result requirements; and the AI ​​model strategy query request carries the AIRR information and AI business type information.

[0425] The feeding back an AI model response message to the terminal according to the AI ​​model policy query response includes: determining AI model information according to the model policy information and candidate model information carried in the AI ​​model policy query response; and feeding back an AI model response message to the terminal according to the AI ​​model information.

[0426] In an embodiment of the present disclosure, the AI ​​model request message also carries overhead-related information; the overhead-related information includes: at least one of data type information, data size information and data dimension information; the model policy information carried by the AI ​​model policy query response includes: overhead limit information; the operation also includes: determining the overhead information of the AI ​​service corresponding to the AI ​​model request message based on the overhead-related information; the overhead information includes: at least one of computing time information, computing resource overhead information and storage resource overhead information; determining the AI ​​model information based on the model policy information and candidate model information carried by the AI ​​model policy query response includes: determining the AI ​​model information based on the overhead information, the model policy information and candidate model information carried by the AI ​​model policy query response.

[0427] Among them, the feeding back an AI model response message to the terminal based on the AI ​​model policy query response includes: when the AI ​​model policy query response indicates that there is no model policy information corresponding to the terminal, sending an AI model training request to the third core network device through the transceiver; the AI ​​model training request carries the AI ​​service type information and candidate AI model information; receiving the AI ​​model training response fed back by the third core network device through the transceiver; determining the AI ​​model information based on the AI ​​model training response; and feeding back an AI model response message to the terminal based on the AI ​​model information.

[0428] In an embodiment of the present disclosure, the AI ​​model request message also carries overhead-related information; the overhead-related information includes: at least one of data type information, data size information, and data dimension information; the model strategy information carried by the AI ​​model strategy query response includes: overhead limit information; the operation also includes: determining the overhead information of the AI ​​service corresponding to the AI ​​model request message based on the overhead-related information; the overhead information includes: at least one of computing time information, computing resource overhead information, and storage resource overhead information; determining the AI ​​model information based on the AI ​​model training response includes: determining the AI ​​model information based on the overhead information and the AI ​​model training response.

[0429] It should be noted here that the above-mentioned device provided in the embodiment of the present disclosure can implement all the method steps implemented in the above-mentioned first core network device side method embodiment, and can achieve the same technical effect. The parts and beneficial effects of this embodiment that are the same as the method embodiment will not be described in detail here.

[0430] The embodiment of the present disclosure further provides an information transmission device, which is a second core network device, as shown in FIG15 , including a memory 151, a transceiver 152, and a processor 153:

[0431] The memory 151 is used to store computer programs; the transceiver 152 is used to send and receive data under the control of the processor 153; the processor 153 is used to read the computer program in the memory 151 and perform the following operations:

[0432] Receiving, through the transceiver 152, an AI model policy query request for the terminal sent by the first core network device;

[0433] According to the AI ​​model policy query request, an AI model policy query response for the terminal is fed back to the first core network device.

[0434] The information transmission device provided in the embodiment of the present disclosure receives an AI model policy query request for a terminal sent by a first core network device; based on the AI ​​model policy query request, it feeds back an AI model policy query response for the terminal to the first core network device; it can support the provision of AI model information corresponding to the AI ​​model request message to the terminal, and further support the provision of AI models based on user needs; it effectively solves the problem in related technologies that cannot support the provision of AI models based on user needs.

[0435] Specifically, the transceiver 152 is configured to receive and send data under the control of the processor 153 .

[0436] In FIG15 , the bus architecture may include any number of interconnected buses and bridges, specifically various circuits linking together one or more processors represented by processor 153 and memory represented by memory 151. 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 and are therefore not further described herein. The bus interface provides an interface. The transceiver 152 may be a plurality of components, i.e., a transmitter and a receiver, providing a unit for communicating with various other devices over a transmission medium, such as a wireless channel, a wired channel, an optical cable, or the like. The processor 153 is responsible for managing the bus architecture and general processing, and the memory 151 may store data used by the processor 153 when performing operations.

[0437] The processor 153 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.

[0438] Among them, the AI ​​model policy query request carries the terminal identifier of the terminal; and the feeding back an AI model policy query response for the terminal to the first core network device based on the AI ​​model policy query request includes: feeding back an AI model policy query response for the terminal to the first core network device based on the terminal identifier.

[0439] In an embodiment of the present disclosure, the AI ​​model policy query request carries AIRR information and AI service type information; the AI ​​model policy query response for the terminal is fed back to the first core network device based on the AI ​​model policy query request, including: determining whether there is an AI historical policy corresponding to the AI ​​model policy query request based on the AIRR information and the AI ​​service type information, and obtaining a second determination result; and based on the second determination result, feeding back the AI ​​model policy query response for the terminal to the first core network device.

[0440] The method of feeding back an AI model policy query response for the terminal to the first core network device based on the second determination result includes: (1) when the second determination result indicates that there is an AI historical policy corresponding to the AI ​​model policy query request, feeding back an AI model policy query response for the terminal to the first core network device based on the AI ​​historical policy; the AI ​​historical policy includes: model policy information and candidate model information; (2) when the second determination result indicates that there is no AI historical policy corresponding to the AI ​​model policy query request, feeding back an AI model policy query response to the first core network device to indicate that there is no model policy information corresponding to the terminal.

[0441] It should be noted here that the above-mentioned device provided in the embodiment of the present disclosure can implement all the method steps implemented in the above-mentioned second core network device side method embodiment, and can achieve the same technical effect. The parts and beneficial effects of this embodiment that are the same as the method embodiment will not be described in detail here.

[0442] The present disclosure also provides an information transmission device, which is a terminal, as shown in FIG16 , including a memory 161 , a transceiver 162 , and a processor 163 :

[0443] The memory 161 is used to store computer programs; the transceiver 162 is used to send and receive data under the control of the processor 163; the processor 163 is used to read the computer program in the memory 161 and perform the following operations:

[0444] Sending an AI model request message to the first core network device through the transceiver 162;

[0445] The transceiver 162 receives the AI ​​model response message fed back by the first core network device; the AI ​​model response message carries AI model information.

[0446] The information transmission device provided in the embodiment of the present disclosure sends an AI model request message to the first core network device; receives an AI model response message fed back by the first core network device; the AI ​​model response message carries AI model information; it can support the acquisition of AI model information corresponding to the AI ​​model request message, and then support the provision of AI models based on user needs; it effectively solves the problem in related technologies that cannot support the provision of AI models based on user needs.

[0447] Specifically, the transceiver 162 is configured to receive and send data under the control of the processor 163 .

[0448] In FIG16 , the bus architecture may include any number of interconnected buses and bridges, specifically various circuits of one or more processors represented by processor 163 and memory represented by memory 161, 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 and are therefore not further described herein. The bus interface provides an interface. The transceiver 162 may be a plurality of components, i.e., a transmitter and a receiver, providing a unit for communicating with various other devices on a transmission medium, such as a wireless channel, a wired channel, an optical cable, and the like. For different user devices, the user interface 164 may also be an interface capable of connecting external or internal devices as required, and the connected devices include but are not limited to a keypad, a display, a speaker, a microphone, a joystick, and the like.

[0449] The processor 163 is responsible for managing the bus architecture and general processing, and the memory 161 can store data used by the processor 163 when performing operations.

[0450] Optionally, the processor 163 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), and the processor may also adopt a multi-core architecture.

[0451] The processor calls the computer program stored in the memory to execute any of the methods provided by the embodiments of the present disclosure according to the obtained executable instructions. The processor and the memory can also be arranged physically separately.

[0452] Furthermore, the operation also includes: before sending the AI ​​model request message to the first core network device, sending an AI model discovery message to the first core network device through the transceiver; the AI ​​model discovery message carries AIRD information; and receiving the AI ​​model discovery response fed back by the first core network device through the transceiver.

[0453] Among them, the AI ​​model request message carries the identification information of the AI ​​business model applied for by the terminal; and / or, the AI ​​model request message carries overhead-related information; the overhead-related information includes: at least one of: data type information, data size information and data dimension information; and / or, the AI ​​model request message carries AIRR information.

[0454] It should be noted here that the above-mentioned device provided in the embodiment of the present disclosure can implement all the method steps implemented in the above-mentioned terminal-side method embodiment, and can achieve the same technical effect. The parts and beneficial effects of this embodiment that are the same as the method embodiment will not be described in detail here.

[0455] The embodiment of the present disclosure further provides an information transmission device, which is a third core network device. As shown in FIG17 , the device includes a memory 171, a transceiver 172, and a processor 173.

[0456] The memory 171 is used to store computer programs; the transceiver 172 is used to send and receive data under the control of the processor 173; the processor 173 is used to read the computer program in the memory 171 and perform the following operations:

[0457] Receiving, through the transceiver 172, an AI model training request sent by the first core network device; the AI ​​model training request carries AI service type information and candidate AI model information;

[0458] According to the AI ​​model training request, an AI model training response is fed back to the first core network device, and AI model training information corresponding to the AI ​​model training request is sent to the second core network device through the transceiver 172.

[0459] The information transmission device provided in the embodiment of the present disclosure receives an AI model training request sent by a first core network device; the AI ​​model training request carries AI service type information and candidate AI model information; based on the AI ​​model training request, an AI model training response is fed back to the first core network device, and AI model training information corresponding to the AI ​​model training request is sent to the second core network device; it can support the provision of AI model information corresponding to the AI ​​model request message to the terminal, and further support the provision of AI models based on user needs; it well solves the problem that related technologies cannot support the provision of AI models based on user needs.

[0460] Specifically, the transceiver 172 is configured to receive and send data under the control of the processor 173 .

[0461] In FIG17 , the bus architecture may include any number of interconnected buses and bridges, specifically one or more processors represented by processor 173 and various circuits of memory represented by memory 171. 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 and are therefore not further described herein. The bus interface provides an interface. The transceiver 172 may be a plurality of components, i.e., a transmitter and a receiver, providing a unit for communicating with various other devices over a transmission medium, such as a wireless channel, a wired channel, an optical cable, and the like. The processor 173 is responsible for managing the bus architecture and general processing, and the memory 171 may store data used by the processor 173 when performing operations.

[0462] The processor 173 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.

[0463] Among them, the feeding back of the AI ​​model training response to the first core network device according to the AI ​​model training request includes: training the candidate AI model according to the AI ​​service type information and the candidate AI model information, and obtaining an evaluation result; and feeding back the AI ​​model training response to the first core network device according to the evaluation result.

[0464] Furthermore, the AI ​​model training request also carries AIRR information; the candidate AI model training is performed according to the AI ​​business type information and the candidate AI model information, and an evaluation result is obtained, including: the candidate AI model training is performed according to the AI ​​business type information and the candidate AI model information, and a training result is obtained; the weight of the evaluation index is determined according to the AIRR information; and the evaluation result is obtained according to the weight and the training result.

[0465] It should be noted here that the above-mentioned device provided in the embodiment of the present disclosure can implement all the method steps implemented in the above-mentioned third core network device side method embodiment, and can achieve the same technical effect. The parts and beneficial effects of this embodiment that are the same as the method embodiment will not be described in detail here.

[0466] The present disclosure also provides an information transmission device, which is applied to a first core network device. As shown in FIG18 , the device includes:

[0467] The first receiving unit 181 is configured to receive an artificial intelligence AI model request message sent by a terminal;

[0468] A first sending unit 182 is configured to send an AI model policy query request for the terminal to the second core network device according to the AI ​​model request message;

[0469] The second receiving unit 183 is configured to receive an AI model policy query response for the terminal fed back by the second core network device;

[0470] The first feedback unit 184 is configured to feed back an AI model response message to the terminal according to the AI ​​model policy query response; the AI ​​model response message carries AI model information.

[0471] The information transmission device provided by the embodiment of the present disclosure receives an artificial intelligence (AI) model request message sent by a terminal; sends an AI model policy query request for the terminal to a second core network device based on the AI ​​model request message; receives an AI model policy query response for the terminal fed back by the second core network device; and feeds back an AI model response message to the terminal based on the AI ​​model policy query response; the AI ​​model response message carries AI model information; and can support the provision of corresponding AI model information to the terminal based on the AI ​​model request message, thereby supporting the provision of AI models based on user needs; and well solves the problem in related technologies that cannot support the provision of AI models based on user needs.

[0472] Furthermore, the information transmission device also includes: a third receiving unit, used to receive an AI model discovery message sent by the terminal before receiving the artificial intelligence AI model request message sent by the terminal; the AI ​​model discovery message carries artificial intelligence service requirement description AIRD information; a first processing unit, used to determine the AI ​​service type information based on the AIRD information, and feedback the AI ​​model discovery response to the terminal.

[0473] Among them, the AI ​​model request message carries the identification information of the AI ​​business model applied for by the terminal; the AI ​​model policy query response is fed back to the terminal. It includes: determining whether the AI ​​business model applied for by the terminal is within the subscription model range corresponding to the terminal according to the AI ​​model policy query response and the identification information, and obtaining a first determination result; obtaining AI model information according to the first determination result; and feeding back an AI model response message to the terminal according to the AI ​​model information.

[0474] In an embodiment of the present disclosure, obtaining AI model information based on the first determination result includes: when the first determination result indicates that the AI ​​business model applied for by the terminal is not within the subscription model range corresponding to the terminal, determining the AI ​​model information corresponding to the terminal based on the AI ​​model request message, the stored AI model information and the model policy information carried by the AI ​​model policy query response.

[0475] The AI ​​model request message also carries overhead-related information; the overhead-related information includes: at least one of data type information, data size information, and data dimension information; the model policy information carried by the AI ​​model policy query response includes: overhead limit information; the information transmission device further includes: a first determination unit, configured to determine, based on the overhead-related information, overhead information of the AI ​​service corresponding to the AI ​​model request message; the overhead information includes: at least one of calculation time information, calculation resource overhead information, and storage resource overhead information; when the first determination result indicates that the AI ​​service model applied for by the terminal is not within the scope of the subscription model corresponding to the terminal, determining the AI ​​model information based on the AI ​​model request message, the locally stored AI model information, and the model policy information carried by the AI ​​model policy query response, includes: when the first determination result indicates a first situation, or when the first determination result indicates the first situation and the overhead information does not meet the overhead limit information, determining the AI ​​model information based on the overhead information, the AI ​​model request message, the locally stored AI model information, and the model policy information carried by the AI ​​model policy query response; wherein the first situation refers to a situation where the AI ​​service model applied for by the terminal is not within the scope of the subscription model corresponding to the terminal.

[0476] In an embodiment of the present disclosure, the AI ​​model request message carries AIRR information of artificial intelligence reasoning result requirements; and the AI ​​model strategy query request carries the AIRR information and AI business type information.

[0477] The feeding back an AI model response message to the terminal according to the AI ​​model policy query response includes: determining AI model information according to the model policy information and candidate model information carried in the AI ​​model policy query response; and feeding back an AI model response message to the terminal according to the AI ​​model information.

[0478] In an embodiment of the present disclosure, the AI ​​model request message also carries overhead-related information; the overhead-related information includes: at least one of data type information, data size information and data dimension information; the model policy information carried by the AI ​​model policy query response includes: overhead limit information; the information transmission device also includes: a second determination unit, used to determine the overhead information of the AI ​​service corresponding to the AI ​​model request message based on the overhead-related information; the overhead information includes: at least one of computing time information, computing resource overhead information and storage resource overhead information; determining the AI ​​model information based on the model policy information and candidate model information carried by the AI ​​model policy query response includes: determining the AI ​​model information based on the overhead information, the model policy information and candidate model information carried by the AI ​​model policy query response.

[0479] Among them, the feeding back an AI model response message to the terminal based on the AI ​​model policy query response includes: when the AI ​​model policy query response indicates that there is no model policy information corresponding to the terminal, sending an AI model training request to a third core network device; the AI ​​model training request carries the AI ​​service type information and candidate AI model information; receiving the AI ​​model training response fed back by the third core network device; determining the AI ​​model information based on the AI ​​model training response; and feeding back an AI model response message to the terminal based on the AI ​​model information.

[0480] In an embodiment of the present disclosure, the AI ​​model request message also carries overhead-related information; the overhead-related information includes: at least one of data type information, data size information, and data dimension information; the model strategy information carried by the AI ​​model strategy query response includes: overhead limit information; the information transmission device also includes: a third determination unit, which is used to determine the overhead information of the AI ​​service corresponding to the AI ​​model request message based on the overhead-related information; the overhead information includes: at least one of computing time information, computing resource overhead information, and storage resource overhead information; determining the AI ​​model information based on the AI ​​model training response includes: determining the AI ​​model information based on the overhead information and the AI ​​model training response.

[0481] It should be noted here that the above-mentioned device provided in the embodiment of the present disclosure can implement all the method steps implemented in the above-mentioned first core network device side method embodiment, and can achieve the same technical effect. The parts and beneficial effects of this embodiment that are the same as the method embodiment will not be described in detail here.

[0482] The present disclosure also provides an information transmission apparatus, which is applied to a second core network device, as shown in FIG19 , and includes:

[0483] The fourth receiving unit 191 is configured to receive an AI model policy query request for a terminal sent by the first core network device;

[0484] The second feedback unit 192 is configured to feed back an AI model policy query response for the terminal to the first core network device based on the AI ​​model policy query request.

[0485] The information transmission device provided in the embodiment of the present disclosure receives an AI model policy query request for a terminal sent by a first core network device; based on the AI ​​model policy query request, it feeds back an AI model policy query response for the terminal to the first core network device; it can support the provision of AI model information corresponding to the AI ​​model request message to the terminal, and further support the provision of AI models based on user needs; it effectively solves the problem in related technologies that cannot support the provision of AI models based on user needs.

[0486] Among them, the AI ​​model policy query request carries the terminal identifier of the terminal; and the feeding back an AI model policy query response for the terminal to the first core network device based on the AI ​​model policy query request includes: feeding back an AI model policy query response for the terminal to the first core network device based on the terminal identifier.

[0487] In an embodiment of the present disclosure, the AI ​​model policy query request carries AIRR information and AI service type information; the AI ​​model policy query response for the terminal is fed back to the first core network device based on the AI ​​model policy query request, including: determining whether there is an AI historical policy corresponding to the AI ​​model policy query request based on the AIRR information and the AI ​​service type information, and obtaining a second determination result; based on the second determination result, the AI ​​model policy query response for the terminal is fed back to the first core network device.

[0488] The method of feeding back an AI model policy query response for the terminal to the first core network device based on the second determination result includes: (1) when the second determination result indicates that there is an AI historical policy corresponding to the AI ​​model policy query request, feeding back an AI model policy query response for the terminal to the first core network device based on the AI ​​historical policy; the AI ​​historical policy includes: model policy information and candidate model information; (2) when the second determination result indicates that there is no AI historical policy corresponding to the AI ​​model policy query request, feeding back an AI model policy query response to the first core network device to indicate that there is no model policy information corresponding to the terminal.

[0489] It should be noted here that the above-mentioned device provided in the embodiment of the present disclosure can implement all the method steps implemented in the above-mentioned second core network device side method embodiment, and can achieve the same technical effect. The parts and beneficial effects of this embodiment that are the same as the method embodiment will not be described in detail here.

[0490] The present disclosure also provides an information transmission device, which is applied to a terminal, as shown in FIG20 , and includes:

[0491] The second sending unit 201 is configured to send an AI model request message to the first core network device;

[0492] The fifth receiving unit 202 is used to receive the AI ​​model response message fed back by the first core network device; the AI ​​model response message carries AI model information.

[0493] The information transmission device provided in the embodiment of the present disclosure sends an AI model request message to the first core network device; receives an AI model response message fed back by the first core network device; the AI ​​model response message carries AI model information; it can support the acquisition of AI model information corresponding to the AI ​​model request message, and then support the provision of AI models based on user needs; it effectively solves the problem in related technologies that cannot support the provision of AI models based on user needs.

[0494] Furthermore, the information transmission device also includes: a third sending unit, used to send an AI model discovery message to the first core network device before sending an AI model request message to the first core network device; the AI ​​model discovery message carries AIRD information; and a sixth receiving unit, used to receive an AI model discovery response fed back by the first core network device.

[0495] Among them, the AI ​​model request message carries the identification information of the AI ​​business model applied for by the terminal; and / or, the AI ​​model request message carries overhead-related information; the overhead-related information includes: at least one of: data type information, data size information and data dimension information; and / or, the AI ​​model request message carries AIRR information.

[0496] It should be noted here that the above-mentioned device provided by the embodiment of the present disclosure can implement all the method steps implemented by the above-mentioned terminal-side method embodiment, and can achieve the same technical effect. The parts and beneficial effects of this embodiment that are the same as the method embodiment will not be described in detail here.

[0497] The present disclosure also provides an information transmission device, which is applied to a third core network device. As shown in FIG21 , the device includes:

[0498] The seventh receiving unit 211 is configured to receive an AI model training request sent by the first core network device; the AI ​​model training request carries AI service type information and candidate AI model information;

[0499] The third feedback unit 212 is used to feedback an AI model training response to the first core network device according to the AI ​​model training request, and send AI model training information corresponding to the AI ​​model training request to the second core network device.

[0500] The information transmission device provided by the embodiment of the present disclosure receives an AI model training request sent by a first core network device; the AI ​​model training request carries AI service type information and candidate AI model information; based on the AI ​​model training request, an AI model training response is fed back to the first core network device, and AI model training information corresponding to the AI ​​model training request is sent to the second core network device; it can support the provision of AI model information corresponding to the AI ​​model request message to the terminal, and further support the provision of AI models based on user needs; it well solves the problem that related technologies cannot support the provision of AI models based on user needs.

[0501] Among them, the feeding back of the AI ​​model training response to the first core network device according to the AI ​​model training request includes: training the candidate AI model according to the AI ​​service type information and the candidate AI model information, and obtaining an evaluation result; and feeding back the AI ​​model training response to the first core network device according to the evaluation result.

[0502] In the embodiment of the present disclosure, the AI ​​model training request also carries AIRR information; the candidate AI model training is performed according to the AI ​​business type information and the candidate AI model information, and an evaluation result is obtained, including: the candidate AI model training is performed according to the AI ​​business type information and the candidate AI model information to obtain a training result; the weight of the evaluation index is determined according to the AIRR information; and the evaluation result is obtained according to the weight and the training result.

[0503] It should be noted here that the above-mentioned device provided in the embodiment of the present disclosure can implement all the method steps implemented in the above-mentioned third core network device side method embodiment, and can achieve the same technical effect. The parts and beneficial effects of this embodiment that are the same as the method embodiment will not be described in detail here.

[0504] It should be noted that the division of units in the embodiments of the present disclosure is schematic and is merely a logical functional division. In actual implementation, other division methods may be used. Furthermore, the functional units in the various embodiments of the present disclosure may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0505] 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 disclosure is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for enabling 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 the method described in each embodiment of the present disclosure. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0506] An embodiment of the present disclosure also provides a non-transitory readable storage medium, which stores a computer program, and the computer program is used to enable the processor to execute the above-mentioned method on the first core network device side, the second core network device side, the terminal side or the third core network device side.

[0507] The non-transitory readable storage medium can be any available medium or data storage device that can be accessed by the processor, including but not limited to magnetic storage (such as floppy disks, hard disks, magnetic tapes, magneto-optical disks (MO)), optical storage (such as compact discs (CD), digital video discs (DVD), Blu-ray discs (BD), high-definition versatile discs (HVD), etc.), and semiconductor storage (such as ROM, erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), non-volatile memory (NAND (Non-volatile Memory Device) FLASH), solid-state drives (SSD)), etc.

[0508] Among them, the implementation embodiments of the methods on the first core network device side, the second core network device side, the terminal side or the third core network device side are all applicable to the embodiments of the non-transitory readable storage medium, and can also achieve the same technical effects.

[0509] Those skilled in the art will appreciate that the embodiments of the present disclosure may be provided as methods, systems, or computer program products. Therefore, the present disclosure may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present disclosure may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage and optical storage, etc.) containing computer-usable program code.

[0510] The present disclosure is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present disclosure. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer-executable instructions. These computer-executable instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device produce a device for implementing the functions specified in one or more processes in the flowchart and / or one or more boxes in the block diagram.

[0511] These processor-executable instructions may also be stored in a processor-readable memory that can direct a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the processor-readable memory produce a product including an instruction device that implements the functions specified in one or more processes in the flowchart and / or one or more boxes in the block diagram.

[0512] These processor-executable instructions may also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, whereby the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in one or more processes in the flowchart and / or one or more boxes in the block diagram.

[0513] Obviously, those skilled in the art may make various changes and modifications to the present disclosure without departing from the spirit and scope of the present disclosure. Thus, if these modifications and variations of the present disclosure fall within the scope of the claims of the present disclosure and their equivalents, the present disclosure is intended to include these modifications and variations.

Claims

1. An information transmission method, applied to a first core network device, the method comprising: Receive the artificial intelligence AI model request message sent by the terminal; Sending an AI model policy query request for the terminal to the second core network device according to the AI ​​model request message; Receiving an AI model policy query response for the terminal fed back by the second core network device; According to the AI ​​model strategy query response, an AI model response message is fed back to the terminal; the AI ​​model response message carries AI model information.

2. The information transmission method according to claim 1, wherein: Before receiving the AI ​​model request message sent by the terminal, it also includes: Receiving an AI model discovery message sent by the terminal; the AI ​​model discovery message carries AIRD information of an artificial intelligence service requirement description; According to the AIRD information, the AI ​​service type information is determined, and an AI model discovery response is fed back to the terminal.

3. The information transmission method according to claim 1, wherein: The AI ​​model request message carries identification information of the AI ​​service model applied for by the terminal; Feedback of an AI model response message to the terminal according to the AI ​​model strategy query response includes: Determine, according to the AI ​​model policy query response and the identification information, whether the AI ​​service model applied for by the terminal is within the subscription model range corresponding to the terminal, to obtain a first determination result; Acquire AI model information according to the first determination result; According to the AI ​​model information, an AI model response message is fed back to the terminal.

4. The information transmission method according to claim 3, wherein: The obtaining AI model information according to the first determination result includes: When the first determination result indicates that the AI ​​service model applied for by the terminal is not within the scope of the subscription model corresponding to the terminal, the AI ​​model information corresponding to the terminal is determined according to the AI ​​model request message, the stored AI model information and the model policy information carried by the AI ​​model policy query response.

5. The information transmission method according to claim 4, wherein: The AI ​​model request message also carries overhead related information; The overhead related information includes: at least one of: data type information, data size information, and data dimension information; the model strategy information carried by the AI ​​model strategy query response includes: overhead limit information; The information transmission method further includes: Determine, according to the overhead related information, the overhead information of the AI ​​service corresponding to the AI ​​model request message; the overhead information includes: at least one of: computing time information, computing resource overhead information, and storage resource overhead information; In the case where the first determination result indicates that the AI ​​service model applied for by the terminal is not within the subscription model range corresponding to the terminal, according to the AI ​​model request message, the locally stored AI model information and the AI The model strategy query response carries the model strategy information to determine the AI ​​model information, including: When the first determination result indicates a first situation, or when the first determination result indicates the first situation and the overhead information does not satisfy the overhead limit information, determine the AI ​​model information according to the overhead information, the AI ​​model request message, the locally stored AI model information, and the model policy information carried by the AI ​​model policy query response; The first situation refers to a situation where the AI ​​service model applied for by the terminal is not within the scope of the subscription model corresponding to the terminal.

6. The information transmission method according to claim 1 or 2, wherein: The AI ​​model request message carries AIRR information of artificial intelligence reasoning result requirement; and the AI ​​model strategy query request carries the AIRR information and AI business type information.

7. The information transmission method according to claim 6, wherein: Feedback of an AI model response message to the terminal according to the AI ​​model strategy query response includes: Determine the AI ​​model information according to the model strategy information and the candidate model information carried by the AI ​​model strategy query response; According to the AI ​​model information, an AI model response message is fed back to the terminal.

8. The information transmission method according to claim 7, wherein: The AI ​​model request message also carries overhead related information; The overhead related information includes: at least one of: data type information, data size information, and data dimension information; the model strategy information carried by the AI ​​model strategy query response includes: overhead limit information; The information transmission method further includes: Determine, according to the overhead related information, the overhead information of the AI ​​service corresponding to the AI ​​model request message; the overhead information includes: at least one of: computing time information, computing resource overhead information, and storage resource overhead information; The determining the AI ​​model information according to the model strategy information and the candidate model information carried by the AI ​​model strategy query response includes: Determine the AI ​​model information according to the overhead information, the model strategy information carried by the AI ​​model strategy query response, and the candidate model information.

9. The information transmission method according to claim 6, wherein: Feedback of an AI model response message to the terminal according to the AI ​​model strategy query response includes: When the AI ​​model policy query response indicates that there is no model policy information corresponding to the terminal, sending an AI model training request to a third core network device; the AI ​​model training request carries the AI ​​service type information and the candidate AI model information; Receiving an AI model training response fed back by the third core network device; Determining AI model information according to the AI ​​model training response; According to the AI ​​model information, an AI model response message is fed back to the terminal.

10. The information transmission method according to claim 9, wherein: The AI ​​model request message also carries overhead related information; The overhead related information includes: at least one of: data type information, data size information, and data dimension information; the model strategy information carried by the AI ​​model strategy query response includes: overhead limit information; The information transmission method further includes: Determine, according to the overhead related information, the overhead information of the AI ​​service corresponding to the AI ​​model request message; the overhead information includes: at least one of: computing time information, computing resource overhead information, and storage resource overhead information; The determining the AI ​​model information according to the AI ​​model training response includes: Determine AI model information based on the overhead information and the AI ​​model training response.

11. An information transmission method, applied to a second core network device, the method comprising: Receiving an AI model policy query request for a terminal sent by a first core network device; According to the AI ​​model policy query request, an AI model policy query response for the terminal is fed back to the first core network device.

12. The information transmission method according to claim 11, wherein: The AI ​​model strategy query request carries the terminal identifier of the terminal; The feeding back an AI model policy query response for the terminal to the first core network device according to the AI ​​model policy query request includes: According to the terminal identifier, an AI model policy query response for the terminal is fed back to the first core network device.

13. The information transmission method according to claim 11, wherein: The AI ​​model strategy query request carries AIRR information and AI service type information; The feeding back an AI model policy query response for the terminal to the first core network device according to the AI ​​model policy query request includes: Determine, according to the AIRR information and the AI ​​business type information, whether there is an AI historical policy corresponding to the AI ​​model policy query request, to obtain a second determination result; Based on the second determination result, an AI model policy query response for the terminal is fed back to the first core network device.

14. The information transmission method according to claim 13, wherein: The feeding back an AI model policy query response for the terminal to the first core network device according to the second determination result includes: If the second determination result indicates that there is an AI historical policy corresponding to the AI ​​model policy query request, feeding back an AI model policy query response for the terminal to the first core network device according to the AI ​​historical policy; the AI ​​historical policy includes: model policy information and candidate model information; When the second determination result indicates that there is no AI historical policy corresponding to the AI ​​model policy query request, an AI model policy query response indicating that there is no model policy information corresponding to the terminal is fed back to the first core network device.

15. An information transmission method, applied to a terminal, the method comprising: Sending an AI model request message to the first core network device; Receiving an AI model response message fed back by the first core network device; The AI ​​model response message carries the AI ​​model Model information.

16. The information transmission method according to claim 15, wherein: Before sending the AI ​​model request message to the first core network device, the method further includes: Sending an AI model discovery message to the first core network device; the AI ​​model discovery message carries AIRD information; Receive the AI ​​model discovery response fed back by the first core network device.

17. The information transmission method according to claim 15, wherein: The AI ​​model request message carries identification information of the AI ​​service model applied for by the terminal; And / or, the AI ​​model request message carries overhead related information; The overhead related information includes: at least one of data type information, data size information, and data dimension information; And / or, the AI ​​model request message carries AIRR information.

18. An information transmission method, applied to a third core network device, the method comprising: Receiving an AI model training request sent by the first core network device; The AI ​​model training request carries AI service type information and candidate AI model information; According to the AI ​​model training request, an AI model training response is fed back to the first core network device, and AI model training information corresponding to the AI ​​model training request is sent to the second core network device.

19. The information transmission method according to claim 18, wherein: The feeding back an AI model training response to the first core network device according to the AI ​​model training request includes: According to the AI ​​business type information and the candidate AI model information, candidate AI model training is performed, and evaluation results are obtained; Based on the evaluation result, an AI model training response is fed back to the first core network device.

20. The information transmission method according to claim 19, wherein: The AI ​​model training request also carries AIRR information; The performing candidate AI model training according to the AI ​​business type information and the candidate AI model information, and obtaining an evaluation result, includes: According to the AI ​​business type information and the candidate AI model information, candidate AI model training is performed to obtain a training result; Determining the weight of the evaluation index according to the AIRR information; An evaluation result is obtained according to the weights and the training results.

21. An information transmission device, the information transmission device being a first core network device, the device comprising a memory, a transceiver, and a processor: A memory for storing a computer program; a transceiver for transmitting and receiving data under the control of the processor; and a processor for reading the computer program in the memory and performing the following operations: Receiving, through the transceiver, an artificial intelligence AI model request message sent by a terminal; According to the AI ​​model request message, sending an AI model policy query request for the terminal to the second core network device through the transceiver; Receiving, by the transceiver, an AI model policy query response for the terminal fed back by the second core network device; According to the AI ​​model strategy query response, an AI model response message is fed back to the terminal; the AI ​​model response message carries AI model information.

22. The information transmission device according to claim 21, wherein: The operations also include: Before receiving the artificial intelligence AI model request message sent by the terminal, receiving the AI ​​model discovery message sent by the terminal through the transceiver; the AI ​​model discovery message carries the artificial intelligence service requirement description AIRD information; According to the AIRD information, the AI ​​service type information is determined, and an AI model discovery response is fed back to the terminal through the transceiver.

23. The information transmission device according to claim 21, wherein: The AI ​​model request message carries identification information of the AI ​​service model applied for by the terminal; Feedback of an AI model response message to the terminal according to the AI ​​model strategy query response includes: Determine, according to the AI ​​model policy query response and the identification information, whether the AI ​​service model applied for by the terminal is within the subscription model range corresponding to the terminal, to obtain a first determination result; Acquire AI model information according to the first determination result; According to the AI ​​model information, an AI model response message is fed back to the terminal.

24. The information transmission device according to claim 23, wherein: The obtaining AI model information according to the first determination result includes: When the first determination result indicates that the AI ​​service model applied for by the terminal is not within the scope of the subscription model corresponding to the terminal, the AI ​​model information corresponding to the terminal is determined according to the AI ​​model request message, the stored AI model information and the model policy information carried by the AI ​​model policy query response.

25. The information transmission device according to claim 24, wherein: The AI ​​model request message also carries overhead related information; The overhead related information includes: at least one of: data type information, data size information, and data dimension information; the model strategy information carried by the AI ​​model strategy query response includes: overhead limit information; The operations also include: Determine, according to the overhead related information, the overhead information of the AI ​​service corresponding to the AI ​​model request message; the overhead information includes: at least one of: computing time information, computing resource overhead information, and storage resource overhead information; The step of determining the AI ​​model information according to the AI ​​model request message, the locally stored AI model information, and the model policy information carried by the AI ​​model policy query response, when the first determination result indicates that the AI ​​service model applied for by the terminal is not within the subscription model range corresponding to the terminal, includes: When the first determination result indicates a first situation, or when the first determination result indicates the first situation and the overhead information does not satisfy the overhead limit information, determine the AI ​​model information according to the overhead information, the AI ​​model request message, the locally stored AI model information, and the model policy information carried by the AI ​​model policy query response; Among them, the first situation refers to that the AI ​​service model applied by the terminal is not in the subscription model corresponding to the terminal Situation within the scope.

26. The information transmission device according to claim 21 or 22, wherein: The AI ​​model request message carries AIRR information of artificial intelligence reasoning result requirement; and the AI ​​model strategy query request carries the AIRR information and AI business type information.

27. The information transmission device according to claim 26, wherein: The feeding back an AI model response message to the terminal according to the AI ​​model strategy query response includes: Determine the AI ​​model information according to the model strategy information and the candidate model information carried by the AI ​​model strategy query response; According to the AI ​​model information, an AI model response message is fed back to the terminal.

28. The information transmission device according to claim 27, wherein: The AI ​​model request message also carries overhead related information; The overhead related information includes: at least one of: data type information, data size information, and data dimension information; the model strategy information carried by the AI ​​model strategy query response includes: overhead limit information; The operations also include: Determine, according to the overhead related information, the overhead information of the AI ​​service corresponding to the AI ​​model request message; the overhead information includes: at least one of: computing time information, computing resource overhead information, and storage resource overhead information; The determining the AI ​​model information according to the model strategy information and the candidate model information carried by the AI ​​model strategy query response includes: Determine the AI ​​model information according to the overhead information, the model strategy information carried by the AI ​​model strategy query response, and the candidate model information.

29. The information transmission device according to claim 26, wherein: The feeding back an AI model response message to the terminal according to the AI ​​model strategy query response includes: When the AI ​​model policy query response indicates that there is no model policy information corresponding to the terminal, sending an AI model training request to a third core network device through the transceiver; the AI ​​model training request carries the AI ​​service type information and the candidate AI model information; Receiving, through the transceiver, an AI model training response fed back by the third core network device; Determining AI model information according to the AI ​​model training response; According to the AI ​​model information, an AI model response message is fed back to the terminal.

30. The information transmission device according to claim 29, wherein: The AI ​​model request message also carries overhead related information; The overhead related information includes: at least one of: data type information, data size information, and data dimension information; the model strategy information carried by the AI ​​model strategy query response includes: overhead limit information; The operations also include: Determine, according to the overhead related information, the overhead information of the AI ​​service corresponding to the AI ​​model request message; the overhead information includes: at least one of: computing time information, computing resource overhead information, and storage resource overhead information; The determining the AI ​​model information according to the AI ​​model training response includes: Determine AI model information based on the overhead information and the AI ​​model training response.

31. An information transmission device, the information transmission device being a second core network device, comprising a memory, a transceiver, and a processor: A memory for storing a computer program; a transceiver for transmitting and receiving data under the control of the processor; and a processor for reading the computer program in the memory and performing the following operations: Receiving, by the transceiver, an AI model policy query request for the terminal sent by the first core network device; According to the AI ​​model policy query request, an AI model policy query response for the terminal is fed back to the first core network device.

32. The information transmission device according to claim 31, wherein: The AI ​​model strategy query request carries the terminal identifier of the terminal; The feeding back an AI model policy query response for the terminal to the first core network device according to the AI ​​model policy query request includes: According to the terminal identifier, an AI model policy query response for the terminal is fed back to the first core network device.

33. The information transmission device according to claim 31, wherein: The AI ​​model strategy query request carries AIRR information and AI service type information; The feeding back an AI model policy query response for the terminal to the first core network device according to the AI ​​model policy query request includes: Determine, according to the AIRR information and the AI ​​business type information, whether there is an AI historical policy corresponding to the AI ​​model policy query request, to obtain a second determination result; Based on the second determination result, an AI model policy query response for the terminal is fed back to the first core network device.

34. The information transmission device according to claim 33, wherein: The feeding back an AI model policy query response for the terminal to the first core network device according to the second determination result includes: If the second determination result indicates that there is an AI historical policy corresponding to the AI ​​model policy query request, feeding back an AI model policy query response for the terminal to the first core network device according to the AI ​​historical policy; the AI ​​historical policy includes: model policy information and candidate model information; When the second determination result indicates that there is no AI historical policy corresponding to the AI ​​model policy query request, an AI model policy query response indicating that there is no model policy information corresponding to the terminal is fed back to the first core network device.

35. An information transmission device, the information transmission device is a terminal, comprising a memory, a transceiver, and a processor: A memory for storing a computer program; a transceiver for transmitting and receiving data under the control of the processor; and a processor for reading the computer program in the memory and performing the following operations: Sending an AI model request message to the first core network device through the transceiver; An AI model response message fed back by the first core network device is received through the transceiver; the AI ​​model response message carries AI model information.

36. The information transmission device according to claim 35, wherein: The operations also include: Before sending the AI ​​model request message to the first core network device, sending an AI model discovery message to the first core network device through the transceiver; the AI ​​model discovery message carries AIRD information; An AI model discovery response fed back by the first core network device is received through the transceiver.

37. The information transmission device according to claim 35, wherein: The AI ​​model request message carries identification information of the AI ​​service model applied for by the terminal; And / or, the AI ​​model request message carries overhead related information; The overhead related information includes: at least one of data type information, data size information, and data dimension information; And / or, the AI ​​model request message carries AIRR information.

38. An information transmission device, the information transmission device being a third core network device, the device comprising a memory, a transceiver, and a processor: A memory for storing a computer program; a transceiver for transmitting and receiving data under the control of the processor; and a processor for reading the computer program in the memory and performing the following operations: Receiving, by the transceiver, an AI model training request sent by the first core network device; the AI ​​model training request carries AI service type information and candidate AI model information; According to the AI ​​model training request, an AI model training response is fed back to the first core network device, and AI model training information corresponding to the AI ​​model training request is sent to the second core network device through the transceiver.

39. The information transmission device according to claim 38, wherein: The feeding back an AI model training response to the first core network device according to the AI ​​model training request includes: According to the AI ​​business type information and the candidate AI model information, candidate AI model training is performed, and evaluation results are obtained; Based on the evaluation result, an AI model training response is fed back to the first core network device.

40. The information transmission device according to claim 39, wherein: The AI ​​model training request also carries AIRR information; The performing candidate AI model training according to the AI ​​business type information and the candidate AI model information, and obtaining an evaluation result, includes: According to the AI ​​business type information and the candidate AI model information, candidate AI model training is performed to obtain a training result; Determining the weight of the evaluation index according to the AIRR information; An evaluation result is obtained according to the weights and the training results.

41. An information transmission device, applied to a first core network device, the device comprising: A first receiving unit, configured to receive an artificial intelligence AI model request message sent by a terminal; A first sending unit, configured to send an AI model policy query request for the terminal to the second core network device according to the AI ​​model request message; A second receiving unit is used to receive an AI model policy query for the terminal fed back by the second core network device. response; The first feedback unit is used to feed back an AI model response message to the terminal according to the AI ​​model strategy query response; the AI ​​model response message carries AI model information.

42. The information transmission device according to claim 41, further comprising: A third receiving unit is used to receive an AI model discovery message sent by the terminal before receiving the artificial intelligence AI model request message sent by the terminal; The AI ​​model discovery message carries AIRD information describing artificial intelligence business requirements; The first processing unit is used to determine the AI ​​service type information according to the AIRD information, and to feed back an AI model discovery response to the terminal.

43. The information transmission device according to claim 41, wherein: The AI ​​model request message carries identification information of the AI ​​service model applied for by the terminal; The feeding back an AI model response message to the terminal according to the AI ​​model strategy query response includes: Determine, according to the AI ​​model policy query response and the identification information, whether the AI ​​service model applied for by the terminal is within the subscription model range corresponding to the terminal, to obtain a first determination result; Acquire AI model information according to the first determination result; According to the AI ​​model information, an AI model response message is fed back to the terminal.

44. The information transmission device according to claim 43, wherein: The obtaining AI model information according to the first determination result includes: When the first determination result indicates that the AI ​​service model applied for by the terminal is not within the scope of the subscription model corresponding to the terminal, the AI ​​model information corresponding to the terminal is determined according to the AI ​​model request message, the stored AI model information and the model policy information carried by the AI ​​model policy query response.

45. The information transmission device according to claim 44, wherein: The AI ​​model request message also carries overhead related information; The overhead related information includes: at least one of: data type information, data size information, and data dimension information; the model strategy information carried by the AI ​​model strategy query response includes: overhead limit information; The information transmission device further includes: A first determining unit, configured to determine, according to the overhead related information, overhead information of the AI ​​service corresponding to the AI ​​model request message; the overhead information includes: at least one of calculation time consumption information, calculation resource overhead information, and storage resource overhead information; The step of determining the AI ​​model information according to the AI ​​model request message, the locally stored AI model information, and the model policy information carried by the AI ​​model policy query response, when the first determination result indicates that the AI ​​service model applied for by the terminal is not within the subscription model range corresponding to the terminal, includes: When the first determination result indicates a first situation, or when the first determination result indicates the first situation and the overhead information does not satisfy the overhead limit information, determine the AI ​​model information according to the overhead information, the AI ​​model request message, the locally stored AI model information, and the model policy information carried by the AI ​​model policy query response; Among them, the first situation refers to that the AI ​​service model applied by the terminal is not in the subscription model corresponding to the terminal Situation within the scope.

46. ​​The information transmission device according to claim 41 or 42, wherein: The AI ​​model request message carries AIRR information of artificial intelligence reasoning result requirement; and the AI ​​model strategy query request carries the AIRR information and AI business type information.

47. The information transmission device according to claim 46, wherein: Feedback of an AI model response message to the terminal according to the AI ​​model strategy query response includes: Determine the AI ​​model information according to the model strategy information and the candidate model information carried by the AI ​​model strategy query response; According to the AI ​​model information, an AI model response message is fed back to the terminal.

48. The information transmission device according to claim 47, wherein: The AI ​​model request message also carries overhead related information; The overhead related information includes: at least one of: data type information, data size information, and data dimension information; the model strategy information carried by the AI ​​model strategy query response includes: overhead limit information; The information transmission device further includes: A second determining unit is configured to determine, according to the overhead related information, overhead information of the AI ​​service corresponding to the AI ​​model request message; the overhead information includes: at least one of calculation time consumption information, calculation resource overhead information, and storage resource overhead information; The determining the AI ​​model information according to the model strategy information and the candidate model information carried by the AI ​​model strategy query response includes: Determine the AI ​​model information according to the overhead information, the model strategy information carried by the AI ​​model strategy query response, and the candidate model information.

49. The information transmission device according to claim 46, wherein: Feedback of an AI model response message to the terminal according to the AI ​​model strategy query response includes: When the AI ​​model policy query response indicates that there is no model policy information corresponding to the terminal, sending an AI model training request to a third core network device; the AI ​​model training request carries the AI ​​service type information and the candidate AI model information; Receiving an AI model training response fed back by the third core network device; Determining AI model information according to the AI ​​model training response; According to the AI ​​model information, an AI model response message is fed back to the terminal.

50. The information transmission device according to claim 49, wherein: The AI ​​model request message also carries overhead related information; The overhead related information includes: at least one of: data type information, data size information, and data dimension information; the model strategy information carried by the AI ​​model strategy query response includes: overhead limit information; The information transmission device further includes: A third determining unit is used to determine, according to the overhead related information, the overhead information of the AI ​​service corresponding to the AI ​​model request message; the overhead information includes: at least one of calculation time consumption information, calculation resource overhead information and storage resource overhead information; The determining the AI ​​model information according to the AI ​​model training response includes: Determine AI model information based on the overhead information and the AI ​​model training response.

51. An information transmission device, applied to a second core network device, wherein: include: A fourth receiving unit, configured to receive an AI model policy query request for a terminal sent by the first core network device; The second feedback unit is used to feedback an AI model policy query response for the terminal to the first core network device according to the AI ​​model policy query request.

52. The information transmission device according to claim 51, wherein: The AI ​​model strategy query request carries the terminal identifier of the terminal; The feeding back an AI model policy query response for the terminal to the first core network device according to the AI ​​model policy query request includes: According to the terminal identifier, an AI model policy query response for the terminal is fed back to the first core network device.

53. The information transmission device according to claim 51, wherein: The AI ​​model strategy query request carries AIRR information and AI service type information; The feeding back an AI model policy query response for the terminal to the first core network device according to the AI ​​model policy query request includes: Determine, according to the AIRR information and the AI ​​business type information, whether there is an AI historical policy corresponding to the AI ​​model policy query request, to obtain a second determination result; Based on the second determination result, an AI model policy query response for the terminal is fed back to the first core network device.

54. The information transmission device according to claim 53, wherein: The feeding back an AI model policy query response for the terminal to the first core network device according to the second determination result includes: If the second determination result indicates that there is an AI historical policy corresponding to the AI ​​model policy query request, feeding back an AI model policy query response for the terminal to the first core network device according to the AI ​​historical policy; the AI ​​historical policy includes: model policy information and candidate model information; When the second determination result indicates that there is no AI historical policy corresponding to the AI ​​model policy query request, an AI model policy query response indicating that there is no model policy information corresponding to the terminal is fed back to the first core network device.

55. An information transmission device, applied to a terminal, comprising: A second sending unit, configured to send an AI model request message to the first core network device; The fifth receiving unit is used to receive the AI ​​model response message fed back by the first core network device; the AI ​​model response message carries AI model information.

56. The information transmission device according to claim 55, further comprising: A third sending unit, configured to send an AI model discovery message to the first core network device before sending the AI ​​model request message to the first core network device; The AI ​​model discovery message carries AIRD information; The sixth receiving unit is used to receive the AI ​​model discovery response fed back by the first core network device.

57. The information transmission device according to claim 55, wherein: The AI ​​model request message carries identification information of the AI ​​service model applied for by the terminal; And / or, the AI ​​model request message carries overhead related information; The overhead related information includes: at least one of data type information, data size information, and data dimension information; And / or, the AI ​​model request message carries AIRR information.

58. An information transmission device, applied to a third core network device, the device comprising: A seventh receiving unit, configured to receive an AI model training request sent by the first core network device; The AI ​​model training request carries AI service type information and candidate AI model information; The third feedback unit is used to feedback an AI model training response to the first core network device according to the AI ​​model training request, and to send AI model training information corresponding to the AI ​​model training request to the second core network device.

59. The information transmission device according to claim 58, wherein: The feeding back an AI model training response to the first core network device according to the AI ​​model training request includes: According to the AI ​​business type information and the candidate AI model information, candidate AI model training is performed, and evaluation results are obtained; Based on the evaluation result, an AI model training response is fed back to the first core network device.

60. The information transmission device according to claim 59, wherein: The AI ​​model training request also carries AIRR information; The performing candidate AI model training according to the AI ​​business type information and the candidate AI model information, and obtaining an evaluation result, includes: According to the AI ​​business type information and the candidate AI model information, candidate AI model training is performed to obtain a training result; Determining the weight of the evaluation index according to the AIRR information; An evaluation result is obtained according to the weights and the training results.

61. A non-transitory readable storage medium storing a computer program, wherein the computer program is used to cause a processor to execute the method according to any one of claims 1 to 20.

Images