Information processing method and apparatus, network function and storage medium

Abstract

The present disclosure provides an information processing method and apparatus, a network function and a storage medium. The method comprises: an MTLF receiving a first request sent by a first network function, wherein the first request is used for requesting to subscribe to a model or model information from the MTLF, and / or the first request carries an indication of energy consumption information or the energy consumption information; returning a first response to the first network function, wherein the first response carries or is used for indicating a first model or model information of the first model, and / or the first response carries first energy consumption information of the first model. The present disclosure can facilitate energy consumption control of the network function, and realize green energy saving.

Description

Information processing method, device, network function and storage medium

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This disclosure is based on and claims the priority of Chinese patent application with application number 202410038882.4 and application date January 10, 2024. The entire content of the Chinese patent application is hereby incorporated into this disclosure by reference. Technical Field

[0003] The present disclosure relates to the field of communication technologies, and in particular to an information processing method, device, network function, and storage medium. Background Art

[0004] Green energy conservation is gaining widespread attention from telecom operators and equipment manufacturers. Currently, the Network Data Analytics Function (NWDAF) architecture lacks a mechanism for processing energy consumption-related information. Summary of the Invention

[0005] To solve related technical problems, the embodiments of the present disclosure provide an information processing method, device, network function, and storage medium. The technical solution of the embodiments of the present disclosure is implemented as follows:

[0006] In a first aspect, an embodiment of the present disclosure provides an information processing method applied to a model training logic function (MTLF), comprising: receiving a first request sent by a first network function, wherein the first request is used to request the MTLF to subscribe to a model or model information, and / or the first request carries an indication of energy consumption information or energy consumption information; and returning a first response to the first network function, wherein the first response carries or is used to indicate a first model or model information of the first model, and / or the first response carries first energy consumption information of the first model.

[0007] In some embodiments, the first model representation is a model available to the first network function determined or obtained by the MTLF based on an indication of energy consumption information or energy consumption information carried in the first request; and / or, the first energy consumption information representation is energy consumption information determined or obtained based on a training process of the first model.

[0008] In some embodiments, the method further includes: determining or obtaining the first energy consumption information of the first model based on the second energy consumption information generated by the first model during the training phase; wherein the training phase includes: a training data acquisition phase, and / or a model training phase, and / or a model verification phase.

[0009] In some embodiments, the first model is trained based on a federated learning architecture; the MTLF is a server-side MTLF; determining the first energy consumption information of the first model based on the second energy consumption information generated by the first model during the training phase includes: receiving third energy consumption information sent by each client MTLF; and calculating the first energy consumption information of the first model based on the third energy consumption information sent by each client MTLF.

[0010] In some embodiments, the third energy consumption information represents energy consumption information generated by the corresponding local model during the training phase when the corresponding client MTLF trains the local model about the first model.

[0011] In some embodiments, the energy consumption information includes one or more of the following: the energy quota or energy limit of the model; the energy consumption grade or energy consumption level or energy grade or energy level of the model; the maximum number of times the model is used or the number of times the model is used; the validity period of the model or the life of the model.

[0012] In some embodiments, the energy consumption information represents energy consumption information of any one of the following categories: energy consumption; renewable capacity; carbon emissions.

[0013] In a second aspect, an embodiment of the present disclosure also provides an information processing method, applied to a first network function, the method comprising: sending a first request to the MTLF, wherein the first request is used to request the MTLF to subscribe to a model or model information, and / or the first request carries an indication of energy consumption information or energy consumption information; and receiving a first response returned by the MTLF, wherein the first response carries or is used to indicate a first model or model information of the first model, and / or the first response carries the first energy consumption information of the first model.

[0014] In some embodiments, the first model represents a model available to the first network function determined or obtained by the MTLF based on an indication of energy consumption information or energy consumption information carried in the first request; and / or, the first energy consumption information represents energy consumption information determined or obtained based on a training process of the first model.

[0015] In some embodiments, the method further includes: performing energy consumption control based on the first energy consumption information during use of the first model.

[0016] In some embodiments, the energy consumption information includes one or more of the following: the energy quota or energy limit of the model; the energy consumption grade or energy consumption level or energy grade or energy level of the model; the maximum number of times the model is used or the number of times the model is used; the validity period of the model or the life of the model.

[0017] In some embodiments, the energy consumption information represents energy consumption information of any one of the following categories: energy consumption; renewable capacity; carbon emissions.

[0018] In some embodiments, the first network function includes one of the following: an application function (AF); an analytics logical function (AnLF).

[0019] In a third aspect, an embodiment of the present disclosure also provides an information processing method, applied to AnLF, comprising: receiving a second request sent by a second network function, wherein the second request is used to request analysis data or analysis information about a first model; and returning a second response to the second network function, wherein the second response carries fourth energy consumption information.

[0020] In some embodiments, the fourth energy consumption information represents energy consumption information determined or obtained based on a reasoning process of the first model.

[0021] In the above solution, the second request carries first energy consumption information; the method also includes: determining whether to provide inference service for the second network function based on the first energy consumption information.

[0022] In some embodiments, the first energy consumption information represents energy consumption information determined or obtained based on a training process of the first model.

[0023] In some embodiments, the method further includes: determining fourth energy consumption information of the first model based on fifth energy consumption information generated by the first model in the inference stage; wherein the inference stage includes: a data collection stage, and / or an inference operation stage.

[0024] In some embodiments, the fifth energy consumption information generated in the data collection phase is determined based on the number of interactive signaling of AnLF in the data collection phase; and / or, the fifth energy consumption information generated in the reasoning operation phase is determined based on the computing energy consumption of AnLF in the reasoning operation phase.

[0025] In some embodiments, the method further includes: performing energy consumption control based on the first energy consumption information during the inference process of the first model.

[0026] In some embodiments, the energy consumption information includes one or more of the following: the energy quota or energy limit of the model; the energy consumption grade or energy consumption level or energy grade or energy level of the model; the maximum number of times the model is used or the number of times the model is used; the validity period of the model or the life of the model.

[0027] In some embodiments, the energy consumption information represents energy consumption information of any one of the following categories: energy consumption; renewable capacity; carbon emissions.

[0028] In a fourth aspect, an embodiment of the present disclosure also provides an information processing method, applied to a second network function, including: sending a second request to AnLF, wherein the second request is used to request analysis data or analysis information about the first model; and receiving a second response returned by AnLF, wherein the second response carries fourth energy consumption information.

[0029] In some embodiments, the fourth energy consumption information represents energy consumption information determined or obtained based on a reasoning process of the first model.

[0030] In some embodiments, the second request carries the first energy consumption information;

[0031] In some embodiments, the energy consumption information includes one or more of the following: the energy quota or energy limit of the model; the energy consumption grade or energy consumption level or energy grade or energy level of the model; the maximum number of times the model is used or the number of times the model is used; the validity period of the model or the life of the model.

[0032] In some embodiments, the energy consumption information represents energy consumption information of any one of the following categories: energy consumption; renewable capacity; carbon emissions.

[0033] In some embodiments, the second network function includes one of the following: AF; Policy Control Function (PCF); Fifth Generation Mobile Communication Technology Core Network (5GC, 5G Core) Network Function (NF, Network Function).

[0034] In the fifth aspect, an embodiment of the present disclosure also provides an information processing method, applied to a network exposure function (NEF), including: sending a third request to a third network function, wherein the third request is used to request the third network function to report sixth energy consumption information; and receiving the sixth energy consumption information returned by the third network function.

[0035] In some embodiments, the sixth energy consumption information represents energy consumption information of the terminal member.

[0036] In some embodiments, the method further includes: receiving a fourth request sent by a fourth network function, wherein the fourth request is used to request terminal member selection, and / or the fourth request carries a maximum energy consumption limit and / or an energy consumption limit of a single terminal member; returning a third response to the fourth network function, wherein the third response is used to indicate one or more candidate terminal members and / or carries seventh energy consumption information.

[0037] In some embodiments, the one or more candidate terminal members are determined or obtained by the NEF based on the sixth energy consumption information and the maximum energy consumption limit and / or the energy consumption limit of a single terminal member.

[0038] In some embodiments, the seventh energy consumption information represents energy consumption information of each terminal member of the one or more candidate terminal members, and / or the seventh energy consumption information represents total energy consumption information of the one or more candidate terminal members.

[0039] In some embodiments, the energy consumption information represents energy consumption information of any one of the following categories: energy consumption; renewable capacity; carbon emissions.

[0040] In some embodiments, the third network function represents a 5GC NF; and / or, the fourth network function represents an AF.

[0041] In a sixth aspect, an embodiment of the present disclosure further provides an information processing device, comprising: a first receiving unit, configured to receive a first request sent by a first network function, wherein the first request is used to request the MTLF to subscribe to a model or model information, and / or the first request carries an indication of energy consumption information or energy consumption information; a first sending unit, configured to return a first response to the first network function, wherein the first response carries or is used to indicate a first model or model information of the first model, and / or the first response carries first energy consumption information of the first model.

[0042] In the seventh aspect, an embodiment of the present disclosure also provides an information processing device, including: a second sending unit, used to send a first request to the MTLF, wherein the first request is used to request the MTLF to subscribe to a model or model information, and / or the first request carries an indication of energy consumption information or energy consumption information; a second receiving unit, used to receive a first response returned by the MTLF, wherein the first response carries or is used to indicate a first model or model information of the first model, and / or the first response carries the first energy consumption information of the first model.

[0043] In the eighth aspect, an embodiment of the present disclosure also provides an information processing device, including: a third receiving unit, used to receive a second request sent by a second network function, wherein the second request is used to request to obtain analysis data or analysis information about the first model; a third sending unit, used to return a second response to the second network function, wherein the second response carries fourth energy consumption information.

[0044] In the ninth aspect, an embodiment of the present disclosure also provides an information processing device, including: a fourth sending unit, used to send a second request to AnLF, wherein the second request is used to request to obtain analysis data or analysis information about the first model; a fourth receiving unit, used to receive a second response returned by AnLF, wherein the second response carries fourth energy consumption information.

[0045] In the tenth aspect, an embodiment of the present disclosure also provides an information processing device, including: a fifth sending unit, used to send a third request to a third network function, wherein the third request is used to request the third network function to report sixth energy consumption information; a fifth receiving unit, used to receive the sixth energy consumption information returned by the third network function.

[0046] In the eleventh aspect, an embodiment of the present disclosure also provides an MTLF, including: a first processor and a first communication interface; wherein the first communication interface is used to receive a first request sent by a first network function, wherein the first request is used to request the MTLF to subscribe to a model or model information, and / or the first request carries an indication of energy consumption information or energy consumption information; the first communication interface is also used to return a first response to the first network function, wherein the first response carries or is used to indicate a first model or model information of the first model, and / or the first response carries the first energy consumption information of the first model.

[0047] In the twelfth aspect, an embodiment of the present disclosure also provides a first network function, including: a second processor and a second communication interface; wherein the second communication interface is used to send a first request to the MTLF, wherein the first request is used to request the MTLF to subscribe to a model or model information, and / or the first request carries an indication of energy consumption information or energy consumption information; the second communication interface is also used to receive a first response returned by the MTLF, wherein the first response carries or is used to indicate a first model or model information of the first model, and / or the first response carries the first energy consumption information of the first model.

[0048] In the thirteenth aspect, an embodiment of the present disclosure also provides an AnLF, comprising: a third processor and a third communication interface; wherein the third communication interface is used to receive a second request sent by a second network function, wherein the second request is used to request to obtain analysis data or analysis information about the first model; the third communication interface is also used to return a second response to the second network function; the second response carries fourth energy consumption information.

[0049] In the fourteenth aspect, the embodiment of the present disclosure also provides a second network function, including: a fourth processor and a fourth communication interface; wherein the fourth communication interface is used to send a second request to AnLF, wherein the second request is used to request to obtain analysis data or analysis information about the first model; the fourth communication interface is used to receive a second response returned by AnLF, wherein the second response carries fourth energy consumption information.

[0050] In the fifteenth aspect, an embodiment of the present disclosure further provides a network function, comprising: a processor and a memory for storing a computer program that can be run on the processor, wherein the processor executes the steps of any of the above-mentioned information processing methods when running the computer program.

[0051] In the sixteenth aspect, an embodiment of the present disclosure further provides a storage medium on which a computer program is stored, wherein the computer program implements the steps of any of the above-mentioned information processing methods when executed by a processor.

[0052] The information processing method, device, network function and storage medium provided by the embodiments of the present disclosure provide relevant energy consumption information processing solutions for scenarios such as model training, model reasoning and terminal member selection under the NWDAF architecture, including the calculation and data exposure of relevant energy consumption information involved in the model training process, model reasoning process and terminal member selection process, which can help network functions achieve energy consumption control and realize green energy saving. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] FIG1 is a schematic diagram of a flow chart of an information processing method according to an embodiment of the present disclosure.

[0054] FIG2 is a schematic diagram of another information processing method implementation flow of the present disclosure.

[0055] FIG3 is a schematic diagram of an interactive flow of an information processing method disclosed herein.

[0056] FIG4 is a schematic diagram of the implementation flow of the third information processing method disclosed in the present invention.

[0057] FIG5 is a schematic diagram of the implementation flow of the fourth information processing method disclosed in the present invention.

[0058] FIG6 is a schematic diagram of an interaction flow of another information processing method disclosed herein.

[0059] FIG7 is a schematic diagram of the implementation flow of the fifth information processing method disclosed in the present invention.

[0060] FIG8 is a schematic diagram of the structure of an information processing device according to an embodiment of the present disclosure.

[0061] FIG9 is a schematic diagram of the structure of another information processing device according to an embodiment of the present disclosure.

[0062] FIG10 is a schematic diagram of the structure of a third information processing device according to an embodiment of the present disclosure.

[0063] FIG11 is a schematic diagram of the structure of the fourth information processing device according to an embodiment of the present disclosure.

[0064] FIG12 is a schematic diagram of the structure of the fifth information processing device according to an embodiment of the present disclosure.

[0065] FIG13 is a schematic diagram of the MTLF structure of an embodiment of the present disclosure.

[0066] FIG14 is a schematic diagram of the first network functional structure of an embodiment of the present disclosure.

[0067] FIG15 is a schematic diagram of the AnLF structure of an embodiment of the present disclosure.

[0068] FIG16 is a schematic diagram of the first network functional structure of an embodiment of the present disclosure.

[0069] FIG17 is a schematic diagram of the NEF structure of an embodiment of the present disclosure. DETAILED DESCRIPTION

[0070] At present, the issue of green energy conservation has received widespread attention from communication operators, communication equipment manufacturers, etc. in the industry. At this stage, under the NWDAF architecture, there is no information processing mechanism related to energy consumption. Based on this, in the embodiment of the present disclosure, an information processing mechanism related to energy consumption is provided for multiple network functions such as the model training logic function (MTLF), analysis logic function (AnLF), and network exposure function (NEF) under the NWDAF architecture, so that energy consumption information can be opened in multiple scenarios such as model training and model reasoning, and the provided energy consumption information can be effectively applied to scenarios such as energy consumption calculation or energy consumption control to achieve green energy conservation.

[0071] The present disclosure will be described in further detail below with reference to the accompanying drawings and embodiments.

[0072] First of all, it should be noted that the energy consumption information involved in all embodiments of the present disclosure can also be described as energy information (such as energy information), or as energy-related information (such as energy related information), or as energy saving information (such as energy saving information).

[0073] Furthermore, the energy consumption information involved in all embodiments of the present disclosure and other related descriptions equivalent to the energy consumption information mentioned above can represent any one of the following categories of energy consumption information: energy consumption; renewable energy; carbon emission.

[0074] All descriptions related to energy consumption information involved below can be understood as above and will not be repeated below.

[0075] For the model training scenario under the NWDAF architecture, the present disclosure provides an information processing method applied to MTLF. Referring to Figure 1, the method includes the following steps 101-102.

[0076] Step 101: Receive a first request sent by a first network function, wherein the first request is used to request the MTLF to subscribe to a model or model information, and / or the first request carries an indication of energy consumption information or energy consumption information.

[0077] Here, the first network function, as a consumer, that is, a user of the model, requests the MTLF to subscribe to a model. In actual application, the first network function includes one of the following: application function (AF); AnLF.

[0078] The first request sent by the first network function carries an indication of energy consumption information or energy consumption information, which is used to indicate relevant requirements or restrictions of the first network function on energy consumption control. For example, the energy consumption indication includes but is not limited to the energy quota or energy limit of the first network function, the energy consumption quota or energy consumption limit, the energy consumption grade or energy consumption level or energy grade or energy level, and the requirements or restrictions of the first network function on the maximum number of times a model is used and the validity period of the model.

[0079] Step 102: Return a first response to the first network function, wherein the first response carries or is used to indicate the first model or model information (such as trained ML Model Information) of the first model, and / or the first response carries first energy consumption information of the first model.

[0080] In one embodiment, the first model represents a model available to the first network function determined or obtained by the MTLF based on an indication of energy consumption information or energy consumption information carried in the first request; and / or, the first energy consumption information represents energy consumption information determined or obtained based on a training process of the first model.

[0081] Here, after receiving the first request, the MTLF determines, from one or more trained models, a first model that matches the indication or energy consumption information of the first network function based on the energy consumption information of the model during the training process. That is, the energy consumption of the first model can match the energy consumption requirement or energy consumption limit of the first network function, and the first model is the model available to the first network function. Afterwards, the MTLF returns a first response to the first network function. The first response carries or is used to indicate the first model, or carries or is used to indicate model information of the first model, and / or carries the first energy consumption information of the first model in the first response, so that the first network function can control energy consumption based on the first energy consumption information during the subsequent use of the first model. For example, during the inference process of the first model, the AnLF controls the number of inferences and the inference timeliness of the first model based on the maximum number of uses of the first model, the validity period of the model, etc., thereby achieving the purpose of energy consumption control.

[0082] In actual application, before step 101, MTLF needs to calculate and obtain the energy consumption information of each model during the training process, and the acquisition of energy consumption information during the training process covers different stages of model training. Based on this, in one embodiment, the method further includes: determining or obtaining first energy consumption information of the first model based on second energy consumption information generated by the first model at each training stage during the training stage.

[0083] The training phase includes: a training data collection phase, and / or a model training phase, and / or a model verification phase.

[0084] That is to say, MTLF needs to calculate the energy consumption information of the model in all or part of the stages of the training data collection stage, model training stage and model verification stage respectively, and finally calculate the overall energy consumption information of the model training process based on the energy consumption information of one or more training stages.

[0085] In addition, the energy consumption information of the model during training can include the energy consumption information of the MTLF when training the model independently. Alternatively, in a federated learning architecture, the energy consumption information of the model during training can also include the energy consumption information of each client MTLF (Client MTLF) when training the relevant local model. The server MTLF (Server MTLF) collects the energy consumption information of the client MTLF when training the relevant local model reported by each client MTLF, and finally calculates the overall energy consumption of the corresponding global model, that is, determines the energy consumption information of the corresponding model during training.

[0086] Based on this, in one embodiment, the first model is trained based on a federated learning architecture; the MTLF is a server-side MTLF;

[0087] The determining of the first energy consumption information of the first model based on the second energy consumption information generated by the first model in each training stage in the training stage includes: receiving the third energy consumption information sent by each client MTLF; and calculating the first energy consumption information of the first model based on the third energy consumption information sent by each client MTLF.

[0088] In one embodiment, the third energy consumption information represents energy consumption information generated by the corresponding local model in each training stage when the corresponding client MTLF trains the local model about the first model.

[0089] In the above embodiments, the energy consumption information of the model during training, including the energy consumption information involved in the MTLF independent training model or the federated learning architecture, includes one or more of the following:

[0090] Energy quotas or energy limits for the model;

[0091] the energy consumption class or energy consumption level or energy class or energy level of the model;

[0092] The maximum number of times the model is used or the number of times the model is used;

[0093] Model validity period or model usage period.

[0094] In the embodiment of the present disclosure, the energy quota of the model can also be described as the energy consumption quota of the model, or as the energy limit, or as the energy consumption limit, or as the energy efficiency quota of the model, or as the energy saving quota of the model.

[0095] Corresponding to the information processing method on the MTLF side above, an embodiment of the present disclosure also provides an information processing method applied to a first network function, which acts as a consumer, that is, a user of the model, including but not limited to network functions such as AF and AnLF.

[0096] Referring to FIG. 2 , the method includes the following steps 201 - 202 .

[0097] Step 201: Send a first request to the MTLF. The first request is used to request the MTLF to subscribe to a model or model information, and / or an indication of energy consumption information or energy consumption information carried in the first request.

[0098] Step 202: Receive a first response returned by the MTLF. The first response carries or is used to indicate a first model or model information of the first model, and / or the first response carries first energy consumption information of the first model.

[0099] In one embodiment, the first model represents a model available to the first network function determined by the MTLF based on an indication of energy consumption information or energy consumption information carried in the first request; and / or, the first energy consumption information represents energy consumption information determined or obtained based on a training process of the first model.

[0100] In one embodiment, the method further includes: performing energy consumption control based on the first energy consumption information during use of the first model.

[0101] In one embodiment, the energy consumption information includes one or more of the following:

[0102] Energy quotas or energy limits for the model;

[0103] the energy consumption class or energy consumption level or energy class or energy level of the model;

[0104] The maximum number of times the model is used or the number of times the model is used;

[0105] Model validity period or model usage period.

[0106] The relevant implementation principles or scheme descriptions of the information processing method on the first network function side provided in the embodiment of the present disclosure can be understood in the same way as the relevant descriptions of the information processing method on the MTLF side in the above embodiment, and will not be repeated here.

[0107] Corresponding to the information processing method on the MTLF side and the first network function side provided in the above embodiment, FIG3 shows an example of the interaction process of the corresponding information processing method, with reference to FIG3:

[0108] 1. The NWDAF Service Consumer sends Nnwdaf_MLModelProvision_Subscribe to the NWDAF containing MTLF, which carries the ES indication, i.e., the energy consumption indication of the NWDAF Service Consumer.

[0109] 2. NWDAF containing MTLF performs calculations based on ES indication and energy consumption information of the trained model to match the available model for the NWDAF Service Consumer.

[0110] If the NWDAF containing MTLF does not match the model available to the NWDAF Service Consumer, it sends Nnwdaf_MLModelProvision_Unsubscribe to the NWDAF Service Consumer.

[0111] 3. If the NWDAF containing MTLF matches a model available to the NWDAF Service Consumer, it sends Nnwdaf_MLModelProvision_Notify to the NWDAF Service Consumer, which carries the EE parameters, that is, the energy consumption information of the matched model.

[0112] For the model reasoning scenario under the NWDAF architecture, the embodiment of the present disclosure provides an information processing method applied to AnLF. Referring to Figure 4, the method includes:

[0113] Step 401: Receive a second request sent by a second network function, wherein the second request is used to request to obtain analysis data or analysis information about a first model.

[0114] Here, the second network function acts as a consumer of the first model and requests the AnLF to provide analytical data (Analytics Data) or analytical information of the first model.

[0115] The second network function includes one of the following: AF; PCF; 5GC NF.

[0116] Step 402: Return a second response to the second network function, wherein the second response carries fourth energy consumption information, wherein the fourth energy consumption information represents energy consumption information determined or obtained based on the reasoning process of the first model.

[0117] Here, after AnLF infers the first model and obtains the analysis data of the first model, it returns the fourth energy consumption information of the inference process of the first model to the second network function. In this way, the second network function, as a consumer, can obtain the relevant energy consumption information of the first model during the inference process.

[0118] In actual application, when AnLF infers the first model, it is necessary to calculate energy consumption information at each inference stage. Based on this, in one embodiment, the method further includes: determining fourth energy consumption information of the first model based on fifth energy consumption information generated at each inference stage of the first model. The inference stage includes: a data collection stage and / or an inference operation stage.

[0119] That is to say, AnLF needs to calculate the energy consumption information of all or part of the stages in the data acquisition stage and the inference operation stage respectively, and finally calculate the overall energy consumption information of the model inference process based on the energy consumption information of one or more stages.

[0120] In one embodiment, the fifth energy consumption information generated in the data collection phase is determined based on the number of interactive signaling of AnLF in the data collection phase; and / or, the fifth energy consumption information generated in the reasoning operation phase is determined based on the computing energy consumption of AnLF in the reasoning operation phase.

[0121] Specifically, in the data collection stage, AnLF can determine the energy consumption information of the first model in this stage according to the number of interactive signaling, that is, the fourth energy consumption information may include the energy consumption information determined based on the number of interactive signaling of AnLF in the data collection stage of the first model; in the reasoning operation stage, AnLF performs local calculations and determines the energy consumption information of the first model in this stage according to the energy consumption generated by the local calculations, that is, the fourth energy consumption information may include the energy consumption information determined based on the local calculation energy consumption of AnLF in the reasoning operation stage of the first model.

[0122] In one embodiment, the second request carries first energy consumption information, and the method further includes: determining whether to provide an inference service for the second network function based on the first energy consumption information. The first energy consumption information represents energy consumption information determined or obtained based on a training process of the first model.

[0123] Here, the first energy consumption information may include the energy consumption information of the MTLF when independently training the first model, or, under the federated learning architecture, the first energy consumption information may also include the energy consumption information of each client MTLF (Client MTLF) when training a local model related to the first model.

[0124] In actual application, AnLF determines whether the reasoning process of the first model meets the relevant requirements or restrictions of AnLF for energy consumption control based on the first energy consumption information and AnLF's own relevant requirements or restrictions on energy consumption control. If it is determined that the reasoning process of the first model meets the relevant requirements or restrictions of AnLF for energy consumption control, it determines to provide reasoning services for the second network function and performs reasoning of the first model.

[0125] During the inference process of the first model, AnLF can control the number of inferences performed on the first model and the inference time based on the maximum number of times the first model is used and the validity period of the model, thereby achieving the purpose of energy consumption control. That is, in one embodiment, the method further includes: during the inference process of the first model, performing energy consumption control based on the first energy consumption information.

[0126] In one embodiment, the energy consumption information includes one or more of the following: the energy quota or energy limit of the model; the energy consumption grade or energy consumption level or energy grade or energy level of the model; the maximum number of times the model is used or the number of times the model is used; the validity period of the model or the model usage period.

[0127] The energy quota of the model may also be described as the energy consumption quota of the model, or as the energy limit, or as the energy consumption limit, or as the energy efficiency quota of the model, or as the energy saving quota of the model.

[0128] Corresponding to the information processing method on the AnLF side above, the embodiment of the present disclosure also provides an information processing method applied to the second network function, which acts as a consumer, that is, the user of the model, including but not limited to network functions such as AF, PCF, and 5GC NF.

[0129] Referring to FIG. 5 , the method includes the following steps 501 - 502 .

[0130] Step 501: Send a second request to AnLF, wherein the second request is used to request to obtain analysis data or analysis data related to the first model.

[0131] Step 502: Receive a second response returned by AnLF, wherein the second response carries fourth energy consumption information.

[0132] In one embodiment, the fourth energy consumption information represents energy consumption information determined or obtained based on a reasoning process of the first model.

[0133] In one embodiment, the second request carries first energy consumption information, wherein the first energy consumption information represents energy consumption information determined or obtained based on a training process of the first model.

[0134] In one embodiment, the energy consumption information includes one or more of the following: the energy quota or energy limit of the model; the energy consumption grade or energy consumption level or energy grade or energy level of the model; the maximum number of times the model is used or the number of times the model is used; the validity period of the model or the model usage period.

[0135] The relevant implementation principles or scheme descriptions of the information processing method on the second network function side provided in the embodiment of the present disclosure can be understood in the same way as the relevant descriptions of the information processing method on the AnLF side in the above embodiment, and will not be repeated here.

[0136] Corresponding to the information processing method on the AnLF side and the second network function side provided in the above embodiment, FIG6 shows an example of the interaction process of the corresponding information processing method, with reference to FIG6:

[0137] 1. The NWDAF Service Consumer sends Nnwdaf_AnalyticsInfo_Request to AnLF, which carries EE Infor, that is, the first energy consumption information of the first model.

[0138] 2. After inferring the first model and obtaining the analysis data of the first model, AnLF sends Nnwdaf_AnalyticsInfo_Request Response to NWDAF Service Consumer, which carries EE parameters, that is, the analysis data of the first model.

[0139] For the scenario of member UE selection under the NWDAF architecture, the present disclosure provides an information processing method, which is applied to NEF. Referring to FIG7 , the method includes the following steps 701-702.

[0140] Step 701: Send a third request to a third network function, wherein the third request is used to request the third network function to report sixth energy consumption information.

[0141] Step 702: Receive the sixth energy consumption information returned by the third network function, wherein the sixth energy consumption information represents energy consumption information of the terminal member.

[0142] Here, the third network function may be a 5GC NF. After receiving the third request from the NEF, the 5GC NF returns the energy consumption information of the terminal member to the NEF for the NEF to use in terminal member selection. The 5GC NF calculates its own maximum energy consumption limit and / or its own energy consumption limit for a single terminal member and sends it to the NEF for use in the NEF's terminal member selection.

[0143] In actual application, before step 701, the NEF triggers a terminal member selection operation based on a request from the fourth network function. In this regard, in one embodiment, the method further includes: receiving a fourth request sent by the fourth network function, wherein the fourth request is used to request terminal member selection and / or the fourth request carries a maximum energy consumption limit and / or an energy consumption limit of a single terminal member; and returning a third response to the fourth network function, wherein the third response is used to indicate one or more candidate terminal members and / or carries the seventh energy consumption information.

[0144] In some embodiments, the one or more candidate terminal members are determined or obtained by the NEF based on the sixth energy consumption information and the maximum energy consumption limit and / or the energy consumption limit of a single terminal member.

[0145] Here, the fourth network function may be AF. The fourth request sent by the fourth network function carries a selection principle for terminal member selection by the fourth network function, including an energy consumption limit for a single terminal member and / or a total energy consumption limit for all selected terminal members, i.e., a maximum energy consumption limit.

[0146] In this way, NEF derives a candidate terminal list based on the selection principle for the terminal member selection operation provided by AF and the energy consumption information of the terminal member provided by 5GC NF. The candidate terminal list contains one or more candidate terminal members, each of which meets the energy consumption limit of AF for a single terminal member, and the total energy consumption limit of all candidate terminal members also meets the maximum energy consumption limit indicated by AF.

[0147] Afterwards, the NEF returns the candidate terminal list to the AF through a third response, and the returned third response carries the seventh energy consumption, wherein the seventh energy consumption information represents the energy consumption information of each terminal member in the one or more candidate terminal members, and / or the seventh energy consumption information represents the total energy consumption information of the one or more candidate terminal members. The seventh energy consumption information is used for the AF to perform energy consumption control.

[0148] In the above embodiments, relevant energy consumption information processing solutions are provided for scenarios such as model training, model reasoning, and terminal member selection under the NWDAF architecture. These solutions include the calculation and data exposure of relevant energy consumption information involved in the model training process, model reasoning process, and terminal member selection process, which can help network functions achieve energy consumption control and green energy saving.

[0149] In order to implement the information processing method on the MTLF side of the embodiment of the present disclosure, the embodiment of the present disclosure further provides an information processing device, which is provided on the MTLF. As shown in FIG8 , the device includes:

[0150] The first receiving unit 801 is configured to receive a first request sent by a first network function, wherein the first request is used to request the MTLF to subscribe to a model or model information, and / or the first request carries an indication of energy consumption information or energy consumption information;

[0151] The first sending unit 802 is used to return a first response to the first network function, wherein the first response carries or is used to indicate a first model or model information of the first model, and / or the first response carries first energy consumption information of the first model.

[0152] In one embodiment, the first model represents a model available to the first network function determined or obtained by the MTLF based on an indication of energy consumption information or energy consumption information carried in the first request; and / or, the first energy consumption information represents energy consumption information determined or obtained based on a training process of the first model.

[0153] In one embodiment, the device also includes: a first determination unit, used to determine or obtain the first energy consumption information of the first model based on the second energy consumption information generated by the first model in the training phase; wherein the training phase includes: a training data acquisition phase, and / or a model training phase, and / or a model verification phase.

[0154] In one embodiment, the first model is trained based on a federated learning architecture; the MTLF is a server MTLF; and the first determination unit is used to: receive third energy consumption information sent by each client MTLF; and calculate the first energy consumption information of the first model based on the third energy consumption information sent by each client MTLF.

[0155] In one embodiment, the third energy consumption information represents energy consumption information generated by the corresponding local model during the training phase when the corresponding client MTLF trains the local model about the first model.

[0156] In one embodiment, the energy consumption information includes one or more of the following: the energy quota or energy limit of the model; the energy consumption grade or energy consumption level or energy grade or energy level of the model; the maximum number of times the model is used or the number of times the model is used; the validity period of the model or the model usage period.

[0157] In one embodiment, the energy consumption information represents any one of the following categories of energy consumption information: energy consumption; renewable capacity; and carbon emissions.

[0158] In actual application, the first sending unit 801 and the first receiving unit 802 can be implemented by a communication interface in the information processing device; and the first determining unit can be implemented by a processor in the information processing device.

[0159] In order to implement the information processing method on the first network function side of the embodiment of the present disclosure, the embodiment of the present disclosure further provides an information processing device, which is provided on the first network function. As shown in FIG9 , the device includes:

[0160] The second sending unit 901 is configured to send a first request to the MTLF, wherein the first request is used to request the MTLF to subscribe to a model or model information, and / or an indication of energy consumption information or energy consumption information carried in the first request;

[0161] The second receiving unit 902 is configured to receive a first response returned by the MTLF, wherein the first response is used to indicate a first model or model information of the first model, and / or the first response carries or carries first energy consumption information of the first model.

[0162] In one embodiment, the first model represents a model available to the first network function determined or obtained by the MTLF based on an indication of energy consumption information or energy consumption information carried in the first request; and / or, the first energy consumption information represents energy consumption information determined or obtained based on a training process of the first model.

[0163] In one embodiment, the apparatus further includes: a first control unit configured to perform energy consumption control based on the first energy consumption information during use of the first model.

[0164] In one embodiment, the energy consumption information includes one or more of the following: the energy quota or energy limit of the model; the energy consumption grade or energy consumption level or energy grade or energy level of the model; the maximum number of times the model is used or the number of times the model is used; the validity period of the model or the model usage period.

[0165] In one embodiment, the energy consumption information represents any one of the following categories of energy consumption information: energy consumption; renewable capacity; and carbon emissions.

[0166] In one embodiment, the first network function includes one of the following: AF; AnLF.

[0167] In actual application, the second receiving unit 901 and the second sending unit 902 can be implemented by a communication interface in the information processing device; and the first control unit can be implemented by a processor in the information processing device.

[0168] In order to implement the information processing method on the AnLF side of the embodiment of the present disclosure, the embodiment of the present disclosure further provides an information processing device, which is provided on the AnLF. As shown in FIG10 , the device includes:

[0169] The third receiving unit 1001 is configured to receive a second request sent by a second network function, wherein the second request is used to request to obtain analysis data or analysis information about the first model;

[0170] The third sending unit 1002 is configured to return a second response to the second network function, where the second response carries fourth energy consumption information.

[0171] In one embodiment, the fourth energy consumption information represents energy consumption information determined or obtained based on the reasoning process of the first model.

[0172] In one embodiment, the second request carries first energy consumption information; the device further includes: a second determination unit, configured to determine whether to provide an inference service for the second network function based on the first energy consumption information.

[0173] In one embodiment, the first energy consumption information represents energy consumption information determined or obtained based on a training process of the first model.

[0174] In one embodiment, the device also includes: a third determination unit, used to determine the fourth energy consumption information of the first model based on the fifth energy consumption information generated by the first model in the reasoning stage; wherein the reasoning stage includes: a data acquisition stage, and / or an reasoning operation stage.

[0175] In one embodiment, the fifth energy consumption information generated in the data collection phase is determined based on the number of interactive signaling of AnLF in the data collection phase; and / or, the fifth energy consumption information generated in the reasoning operation phase is determined based on the computing energy consumption of AnLF in the reasoning operation phase.

[0176] In one embodiment, the apparatus further includes: a second control unit configured to perform energy consumption control based on the first energy consumption information during the inference process of the first model.

[0177] In one embodiment, the energy consumption information includes one or more of the following: the energy quota or energy limit of the model; the energy consumption grade or energy consumption level or energy grade or energy level of the model; the maximum number of times the model is used or the number of times the model is used; the validity period of the model or the model usage period.

[0178] In one embodiment, the energy consumption information represents any one of the following categories of energy consumption information: energy consumption; renewable capacity; and carbon emissions.

[0179] In actual application, the third receiving unit 1001 and the third sending unit 1002 can be implemented by a communication interface in the information processing device; the second determination unit, the third determination unit and the first control unit can be implemented by a processor in the information processing device.

[0180] In order to implement the information processing method on the second network function side of the embodiment of the present disclosure, the embodiment of the present disclosure further provides an information processing device, which is provided on the second network function, as shown in FIG11 , and includes:

[0181] The fourth sending unit 1101 is configured to send a second request to the AnLF, wherein the second request is used to request acquisition of analysis data or analysis information about the first model;

[0182] The fourth receiving unit 1102 is configured to receive a second response returned by AnLF, where the second response carries fourth energy consumption information.

[0183] In one embodiment, the fourth energy consumption information represents energy consumption information determined or obtained based on a reasoning process of the first model.

[0184] In one embodiment, the second request carries the first energy consumption information.

[0185] In one embodiment, the energy consumption information includes one or more of the following: the energy quota or energy limit of the model; the energy consumption grade or energy consumption level or energy grade or energy level of the model; the maximum number of times the model is used or the number of times the model is used; the validity period of the model or the model usage period.

[0186] In one embodiment, the energy consumption information represents any one of the following categories of energy consumption information: energy consumption; renewable capacity; and carbon emissions.

[0187] In one embodiment, the second network function includes one of the following: AF; PCF; 5GC NF.

[0188] In actual application, the fourth sending unit 1101 and the fourth receiving unit 1102 can be implemented by a communication interface in an information processing device.

[0189] In order to implement the information processing method on the NEF side of the embodiment of the present disclosure, the embodiment of the present disclosure further provides an information processing device, which is provided on the NEF. As shown in FIG12 , the device includes:

[0190] The fifth sending unit 1201 is configured to send a third request to a third network function, wherein the third request is used to request the third network function to report sixth energy consumption information.

[0191] The fifth receiving unit 1202 is configured to receive the sixth energy consumption information returned by the third network function.

[0192] In one embodiment, the sixth energy consumption information represents energy consumption information of the terminal member.

[0193] In one embodiment, the device also includes: a sixth receiving unit, used to receive a fourth request sent by a fourth network function, wherein the fourth request is used to request terminal member selection, and / or the fourth request carries a maximum energy consumption limit and / or an energy consumption limit of a single terminal member; a sixth sending unit, used to return a third response to the fourth network function, wherein the third response is used to indicate one or more candidate terminal members and / or carries seventh energy consumption information.

[0194] In one embodiment, the one or more candidate terminal members are determined or obtained by the NEF based on the sixth energy consumption information and the maximum energy consumption limit and / or the energy consumption limit of a single terminal member.

[0195] In one embodiment, the seventh energy consumption information represents energy consumption information of each terminal member among the one or more candidate terminal members, and / or the seventh energy consumption information represents total energy consumption information of the one or more candidate terminal members.

[0196] In one embodiment, the energy consumption information represents any one of the following categories of energy consumption information: energy consumption; renewable capacity; and carbon emissions.

[0197] In one embodiment, the third network function represents a 5GC NF; and / or, the fourth network function represents an AF.

[0198] In actual application, the fifth sending unit 1201 and the fifth receiving unit 1202, the sixth receiving unit and the sixth sending unit can be implemented by a communication interface in the information processing device.

[0199] It should be noted that the information processing device provided in the above embodiments is illustrated only by the division of the above-mentioned program modules when performing information processing. In actual applications, the above-mentioned processing can be assigned to different program modules as needed, that is, the internal structure of the device can be divided into different program modules to complete all or part of the above-described processing. In addition, the information processing device provided in the above embodiments and the information processing method embodiment are based on the same concept. The specific implementation process is detailed in the method embodiment and is not repeated here.

[0200] Based on the hardware implementation of the above program modules and in order to implement the method on the MTLF side of the embodiment of the present disclosure, the embodiment of the present disclosure further provides an MTLF, as shown in FIG13 , where the MTLF 1300 includes:

[0201] The first communication interface 1301 is capable of exchanging information with other network nodes;

[0202] The first processor 1302 is connected to the first communication interface 1301 to implement information exchange with other network nodes and is used to execute the methods provided by one or more technical solutions of the MTLF side when running a computer program. The computer program is stored in the first memory 1303.

[0203] Specifically, the first communication interface 1301 is used to receive a first request sent by a first network function, wherein the first request is used to request the MTLF to subscribe to a model or model information, and / or the first request carries an indication of energy consumption information or energy consumption information; the first communication interface 1301 is also used to return a first response to the first network function, wherein the first response carries or is used to indicate a first model or model information of the first model, and / or the first response carries the first energy consumption information of the first model.

[0204] In one embodiment, the first model represents a model available to the first network function determined or obtained by the MTLF based on an indication of energy consumption information or energy consumption information carried in the first request; and / or, the first energy consumption information represents energy consumption information determined or obtained based on a training process of the first model.

[0205] In one embodiment, the first processor 1302 is used to determine or obtain the first energy consumption information of the first model based on the second energy consumption information generated by the first model in the training phase; wherein the training phase includes: a training data acquisition phase, and / or a model training phase, and / or a model verification phase.

[0206] In one embodiment, the first model is trained based on a federated learning architecture; the MTLF is a server MTLF; the first processor 1302 is used to: receive third energy consumption information sent by each client MTLF; and calculate the first energy consumption information of the first model based on the third energy consumption information sent by each client MTLF.

[0207] In one embodiment, the third energy consumption information represents energy consumption information generated by the corresponding local model during the training phase when the corresponding client MTLF trains the local model about the first model.

[0208] In one embodiment, the energy consumption information includes one or more of the following: the energy quota or energy limit of the model; the energy consumption grade or energy consumption level or energy grade or energy level of the model; the maximum number of times the model is used or the number of times the model is used; the validity period of the model or the model usage period.

[0209] In one embodiment, the energy consumption information represents any one of the following categories of energy consumption information: energy consumption; renewable capacity; and carbon emissions.

[0210] It should be noted that the specific processing process of the first processor 1302 and the first communication interface 1301 can be understood by referring to the above method.

[0211] In practice, the various components within MTLF 1300 are coupled together via bus system 1304. It will be appreciated that bus system 1304 is used to enable communication between these components. In addition to a data bus, bus system 1304 also includes a power bus, a control bus, and a status signal bus. However, for clarity, all of these buses are labeled as bus system 1304 in FIG13 .

[0212] The first memory 1303 in the embodiment of the present disclosure is used to store various types of data to support the operation of the MTLF 1300. Examples of such data include any computer program used to operate on the MTLF 1300.

[0213] The methods disclosed in the above embodiments of the present disclosure can be applied to the first processor 1302 or implemented by the first processor 1302. The first processor 1302 may be an integrated circuit chip with signal processing capabilities. During implementation, each step of the above method can be completed by hardware integrated logic circuits or software instructions in the first processor 1302. The above first processor 1302 may be a general-purpose processor, a digital signal processor (DSP), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The first processor 1302 can implement or execute the various methods, steps, and logic block diagrams disclosed in the embodiments of the present disclosure. A general-purpose processor may be a microprocessor or any conventional processor. The steps of the methods disclosed in conjunction with the embodiments of the present disclosure can be directly implemented and executed by a hardware decoding processor, or by a combination of hardware and software modules in the decoding processor. The software module may be located in a storage medium located in the first memory 1303. The first processor 1302 reads the information in the first memory 1303 and, in conjunction with its hardware, completes the steps of the above method.

[0214] In an exemplary embodiment, the MTLF 1300 may be implemented by one or more application-specific integrated circuits (ASICs), DSPs, programmable logic devices (PLDs), complex programmable logic devices (CPLDs), field-programmable gate arrays (FPGAs), general-purpose processors, controllers, microcontrollers (MCUs), microprocessors, or other electronic components to perform the aforementioned method.

[0215] Based on the hardware implementation of the above program modules, and in order to implement the method on the first network function side of the embodiment of the present disclosure, the embodiment of the present disclosure further provides a first network function, as shown in FIG14 , the first network function 1400 includes:

[0216] The second communication interface 1401 is capable of exchanging information with other network nodes;

[0217] The second processor 1402 is connected to the second communication interface 1401 to implement information exchange with other network nodes and is configured to execute the methods provided by one or more technical solutions of the first network function side when running a computer program. The computer program is stored in the second memory 1403.

[0218] Specifically, the second communication interface 1401 is used to send a first request to the MTLF, wherein the first request is used to request the MTLF to subscribe to a model or model information, and / or the first request carries an indication of energy consumption information or energy consumption information; the second communication interface 1401 is also used to receive a first response returned by the MTLF, wherein the first response carries or is used to indicate a first model or model information of the first model, and / or the first response carries the first energy consumption information of the first model.

[0219] In one embodiment, the first model represents a model available to the first network function determined or obtained by the MTLF based on an indication of energy consumption information or energy consumption information carried in the first request; and / or, the first energy consumption information represents energy consumption information determined or obtained based on a training process of the first model.

[0220] In one embodiment, the second processor 1402 is configured to perform energy consumption control based on the first energy consumption information during use of the first model.

[0221] In one embodiment, the energy consumption information includes one or more of the following: the energy quota or energy limit of the model; the energy consumption grade or energy consumption level or energy grade or energy level of the model; the maximum number of times the model is used or the number of times the model is used; the validity period of the model or the model usage period.

[0222] In one embodiment, the energy consumption information represents any one of the following categories of energy consumption information: energy consumption; renewable capacity; and carbon emissions.

[0223] In one embodiment, the first network function includes one of the following: AF; AnLF.

[0224] It should be noted that the specific processing procedures of the second processor 1402 and the second communication interface 1401 can be understood by referring to the above method.

[0225] Of course, in actual application, the various components in first network function 1400 are coupled together via bus system 1404. It will be appreciated that bus system 1404 is used to implement connectivity and communication between these components. In addition to a data bus, bus system 1404 also includes a power bus, a control bus, and a status signal bus. However, for clarity, in FIG14 , all of these buses are labeled as bus system 1404.

[0226] The second memory 1403 in the embodiment of the present disclosure is used to store various types of data to support the operation of the first network function 1400. Examples of such data include any computer program used to operate on the first network function 1400.

[0227] The methods disclosed in the above embodiments of the present disclosure can be applied to or implemented by the second processor 1402. The second processor 1402 may be an integrated circuit chip with signal processing capabilities. During implementation, each step of the above method can be completed by hardware integrated logic circuits or software instructions in the second processor 1402. The above second processor 1402 may be a general-purpose processor, a DSP, or other programmable logic device, a discrete gate or transistor logic device, a discrete hardware component, etc. The second processor 1402 can implement or execute the various methods, steps, and logic block diagrams disclosed in the embodiments of the present disclosure. A general-purpose processor may be a microprocessor or any conventional processor. The steps of the methods disclosed in the embodiments of the present disclosure can be directly implemented and executed by a hardware decoding processor, or by a combination of hardware and software modules in the decoding processor. The software modules may be located in a storage medium located in the second memory 1403. The second processor 1402 reads the information in the second memory 1403 and, in conjunction with its hardware, completes the steps of the above method.

[0228] In an exemplary embodiment, the first network function 1400 may be implemented by one or more ASICs, DSPs, PLDs, CPLDs, FPGAs, general-purpose processors, controllers, MCUs, Microprocessors, or other electronic components to perform the aforementioned method.

[0229] Based on the hardware implementation of the above program modules, and in order to implement the method on the AnLF side of the embodiment of the present disclosure, the embodiment of the present disclosure further provides an AnLF, as shown in FIG15 , the AnLF 1500 includes:

[0230] The third communication interface 1501 is capable of exchanging information with other network nodes;

[0231] The third processor 1502 is connected to the third communication interface 1501 to implement information exchange with other network nodes and is used to execute the method provided by one or more technical solutions of the AnLF side when running a computer program. The computer program is stored in the third memory 1503.

[0232] Specifically, the third communication interface 1501 is used to receive a second request sent by a second network function, wherein the second request is used to request to obtain analysis data or analysis information about the first model; the third communication interface 1501 is also used to return a second response to the second network function, wherein the second response carries fourth energy consumption information.

[0233] In one embodiment, the fourth energy consumption information represents energy consumption information determined or obtained based on a reasoning process of the first model.

[0234] In one embodiment, the second request carries first energy consumption information; and the third processor 1502 is configured to determine whether to provide an inference service for the second network function based on the first energy consumption information.

[0235] In one embodiment, the first energy consumption information represents energy consumption information determined or obtained based on a training process of the first model.

[0236] In one embodiment, the third processor 1502 is used to determine the fourth energy consumption information of the first model based on the fifth energy consumption information generated by the first model in the reasoning stage; wherein the reasoning stage includes: a data acquisition stage, and / or an reasoning operation stage.

[0237] In one embodiment, the fifth energy consumption information generated in the data collection phase is determined based on the number of interactive signaling of AnLF in the data collection phase; and / or, the fifth energy consumption information generated in the reasoning operation phase is determined based on the computing energy consumption of AnLF in the reasoning operation phase.

[0238] In one embodiment, the third processor 1502 is configured to perform energy consumption control based on the first energy consumption information during the inference process of the first model.

[0239] In one embodiment, the energy consumption information includes one or more of the following: the energy quota or energy limit of the model; the energy consumption grade or energy consumption level or energy grade or energy level of the model; the maximum number of times the model is used or the number of times the model is used; the validity period of the model or the model usage period.

[0240] In one embodiment, the energy consumption information represents any one of the following categories of energy consumption information: energy consumption; renewable capacity; and carbon emissions.

[0241] Of course, in actual use, the various components in AnLF 1500 are coupled together via bus system 1504. It will be appreciated that bus system 1504 is used to enable communication between these components. In addition to a data bus, bus system 1504 also includes a power bus, a control bus, and a status signal bus. However, for clarity, in FIG15 , each bus is labeled as bus system 1504.

[0242] The third memory 1503 in the embodiment of the present disclosure is used to store various types of data to support the operation of the AnLF 1500. Examples of such data include any computer program used to operate on the AnLF 1500.

[0243] The methods disclosed in the above embodiments of the present disclosure can be applied to or implemented by the third processor 1502. The third processor 1502 may be an integrated circuit chip with signal processing capabilities. During implementation, each step of the above method can be completed by hardware integrated logic circuits or software instructions in the third processor 1502. The third processor 1502 may be a general-purpose processor, a DSP, or other programmable logic device, a discrete gate or transistor logic device, a discrete hardware component, etc. The third processor 1502 can implement or execute the various methods, steps, and logic block diagrams disclosed in the embodiments of the present disclosure. A general-purpose processor may be a microprocessor or any conventional processor. The steps of the methods disclosed in the embodiments of the present disclosure can be directly implemented and executed by a hardware decoding processor, or by a combination of hardware and software modules in the decoding processor. The software modules may be located in a storage medium located in the third memory 1503. The third processor 1502 reads information from the third memory 1503 and, in conjunction with its hardware, completes the steps of the above method.

[0244] In an exemplary embodiment, the AnLF 1500 may be implemented by one or more ASICs, DSPs, PLDs, CPLDs, FPGAs, general-purpose processors, controllers, MCUs, Microprocessors, or other electronic components to perform the aforementioned methods.

[0245] Based on the hardware implementation of the above program modules, and in order to implement the method of the second network function side of the embodiment of the present disclosure, the embodiment of the present disclosure further provides a second network function, as shown in Figure 16, the second network function 1600 includes:

[0246] The third communication interface 1601 is capable of exchanging information with other network nodes;

[0247] The third processor 1602 is connected to the third communication interface 1601 to implement information exchange with other network nodes and is configured to execute the methods provided by one or more technical solutions of the second network function side when running a computer program. The computer program is stored in the third memory 1603.

[0248] Specifically, the third communication interface 1601 is used to send a second request to AnLF, wherein the second request is used to request to obtain analysis data or analysis information about the first model; the third communication interface 1601 is also used to receive a second response returned by AnLF, wherein the second response carries fourth energy consumption information.

[0249] In one embodiment, the fourth energy consumption information represents energy consumption information determined or obtained based on a reasoning process of the first model.

[0250] In one embodiment, the second request carries the first energy consumption information.

[0251] In one embodiment, the energy consumption information includes one or more of the following: the energy quota or energy limit of the model; the energy consumption grade or energy consumption level or energy grade or energy level of the model; the maximum number of times the model is used or the number of times the model is used; the validity period of the model or the model usage period.

[0252] In one embodiment, the energy consumption information represents any one of the following categories of energy consumption information: energy consumption; renewable capacity; and carbon emissions.

[0253] In one embodiment, the second network function includes one of the following: AF; PCF; 5GC NF.

[0254] Of course, in actual application, the various components in second network function 1600 are coupled together via bus system 1604. It will be appreciated that bus system 1604 is used to implement connectivity and communication between these components. In addition to a data bus, bus system 1604 also includes a power bus, a control bus, and a status signal bus. However, for clarity, in FIG16 , all of these buses are labeled as bus system 1604.

[0255] The third memory 1603 in the embodiment of the present disclosure is used to store various types of data to support the operation of the second network function 1600. Examples of such data include any computer program used to operate on the second network function 1600.

[0256] The methods disclosed in the above embodiments of the present disclosure can be applied to or implemented by the third processor 1602. The third processor 1602 may be an integrated circuit chip with signal processing capabilities. During implementation, each step of the above method can be completed by hardware integrated logic circuits or software instructions in the third processor 1602. The third processor 1602 may be a general-purpose processor, a DSP, or other programmable logic device, a discrete gate or transistor logic device, or a discrete hardware component. The third processor 1602 can implement or execute the various methods, steps, and logic block diagrams disclosed in the embodiments of the present disclosure. A general-purpose processor may be a microprocessor or any conventional processor. The steps of the methods disclosed in the embodiments of the present disclosure can be directly implemented and executed by a hardware decoding processor, or by a combination of hardware and software modules in the decoding processor. The software modules may be located in a storage medium located in the third memory 1603. The third processor 1602 reads information from the third memory 1603 and, in conjunction with its hardware, completes the steps of the above method.

[0257] In an exemplary embodiment, the second network function 1600 may be implemented by one or more ASICs, DSPs, PLDs, CPLDs, FPGAs, general-purpose processors, controllers, MCUs, Microprocessors, or other electronic components to perform the aforementioned method.

[0258] Based on the hardware implementation of the above program modules and in order to implement the method on the NEF side of the embodiment of the present disclosure, the embodiment of the present disclosure further provides an NEF, as shown in FIG17 , the NEF 1700 includes:

[0259] The third communication interface 1701 is capable of exchanging information with other network nodes;

[0260] The third processor 1702 is connected to the third communication interface 1701 to implement information exchange with other network nodes and is configured to execute the methods provided by one or more technical solutions of the NEF side when running a computer program. The computer program is stored in the third memory 1703.

[0261] Specifically, the third communication interface 1701 is used to send a third request to the third network function, where the third request is used to request the third network function to report sixth energy consumption information.

[0262] The third communication interface 1701 is further configured to receive the sixth energy consumption information returned by the third network function.

[0263] In one embodiment, the sixth energy consumption information represents energy consumption information of the terminal member.

[0264] In one embodiment, the third communication interface 1701 is also used to receive a fourth request sent by a fourth network function, wherein the fourth request is used to request terminal member selection, and / or the fourth request carries a maximum energy consumption limit and / or an energy consumption limit of a single terminal member; the third communication interface 1701 is also used to return a third response to the fourth network function, wherein the third response is used to indicate one or more candidate terminal members and / or carries seventh energy consumption information.

[0265] In one embodiment, the one or more candidate terminal members are determined or obtained by the NEF based on the sixth energy consumption information and the maximum energy consumption limit and / or the energy consumption limit of a single terminal member.

[0266] In one embodiment, the seventh energy consumption information represents energy consumption information of each terminal member among the one or more candidate terminal members, and / or the seventh energy consumption information represents total energy consumption information of the one or more candidate terminal members.

[0267] In one embodiment, the energy consumption information represents any one of the following categories of energy consumption information: energy consumption; renewable capacity; and carbon emissions.

[0268] In one embodiment, the third network function represents a 5GC NF; and / or, the fourth network function represents an AF.

[0269] In practice, the various components within NEF 1700 are coupled together via bus system 1704. It will be appreciated that bus system 1704 is used to enable communication between these components. In addition to a data bus, bus system 1704 also includes a power bus, a control bus, and a status signal bus. However, for clarity, all of these buses are labeled as bus system 1704 in FIG. 17 .

[0270] The third memory 1703 in the embodiment of the present disclosure is used to store various types of data to support the operation of the NEF 1700. Examples of such data include any computer program used to operate on the NEF 1700.

[0271] The methods disclosed in the above embodiments of the present disclosure can be applied to or implemented by the third processor 1702. The third processor 1702 may be an integrated circuit chip with signal processing capabilities. During implementation, each step of the above method can be completed by hardware integrated logic circuits or software instructions in the third processor 1702. The third processor 1702 may be a general-purpose processor, a DSP, or other programmable logic device, a discrete gate or transistor logic device, or a discrete hardware component. The third processor 1702 can implement or execute the various methods, steps, and logic block diagrams disclosed in the embodiments of the present disclosure. A general-purpose processor may be a microprocessor or any conventional processor. The steps of the methods disclosed in the embodiments of the present disclosure can be directly implemented and executed by a hardware decoding processor, or by a combination of hardware and software modules in the decoding processor. The software modules may be located in a storage medium located in the third memory 1703. The third processor 1702 reads information from the third memory 1703 and, in conjunction with its hardware, completes the steps of the above method.

[0272] In an exemplary embodiment, NEF 1700 may be implemented by one or more ASICs, DSPs, PLDs, CPLDs, FPGAs, general-purpose processors, controllers, MCUs, Microprocessors, or other electronic components to perform the aforementioned methods.

[0273] It is understood that the memories (first memory 1303, second memory 1403, third memory 1503, fourth memory 1603, and fifth memory 1703) of the embodiments of the present disclosure may be volatile memories or non-volatile memories, or may include both volatile and non-volatile memories. The non-volatile memories may be read-only memories (ROMs), programmable read-only memories (PROMs), erasable programmable read-only memories (EPROMs), electrically erasable programmable read-only memories (EEPROMs), ferromagnetic random access memories (FRAMs), flash memories, magnetic surface memories, optical disks, or compact disc read-only memories (CD-ROMs); and the magnetic surface memories may be magnetic disk memories or magnetic tape memories. Volatile memory can be random access memory (RAM), which acts as external cache memory.By way of example and not limitation, many forms of RAM are available, such as static random access memory (SRAM), synchronous static random access memory (SSRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDRSDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM), and direct rambus random access memory (DRRAM). The memory described in the embodiments of the present disclosure is intended to include, but is not limited to, these and any other suitable types of memory.

[0274] In an exemplary embodiment, the present disclosure also provides a storage medium, namely, a computer storage medium, specifically, a non-transitory computer-readable storage medium, which may include, for example, a first memory 1303 storing a computer program. The computer program may be executed by the first processor 1302 of the MLTF 1300 to complete the steps of the aforementioned MLTF-side method. Alternatively, a second memory 1403 storing a computer program may be executed by the second processor 1402 of the first network function 1400 to complete the steps of the aforementioned first network node-side method. Alternatively, a third memory 1503 storing a computer program may be executed by the third processor 1502 of the AnLF 1500 to complete the steps of the aforementioned AnLF-side method. Alternatively, a fourth memory 1603 storing a computer program may be executed by the fourth processor 1602 of the second network function 1600 to complete the steps of the aforementioned second network function-side method. For another example, the fifth memory 1703 for storing computer programs may be executed by the fifth processor 1702 of the NEF 1700 to complete the steps of the aforementioned NEF-side method.

[0275] The computer-readable storage medium may be a memory such as FRAM, ROM, PROM, EPROM, EEPROM, Flash Memory, magnetic surface storage, optical disk, or CD-ROM.

[0276] It should be noted that: "first", "second", etc. are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence.

[0277] The term "and / or" herein is merely a description of the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can represent three situations: A exists alone, A and B exist at the same time, and B exists alone. In addition, the terms "one or more" and "one or more" herein represent any combination of at least two of any one or more of a plurality. For example, including at least one of A, B, and C can represent including any one or more elements selected from the set consisting of A, B, and C. In addition, the technical solutions described in the embodiments of the present disclosure can be arbitrarily combined without conflict.

[0278] In the embodiments of the present disclosure, the network function may also be referred to as a network element, an entity, a network device, a network side device, etc.

[0279] The above description is merely a preferred embodiment of the present disclosure and is not intended to limit the scope of protection of the present disclosure.

Claims

1. An information processing method, applied to a model training logic function MTLF, includes: Receiving a first request sent by a first network function, where the first request is used to request to subscribe to a model or model information from the MTLF, and / or the first request carries an indication of energy consumption information or energy consumption information; And Returning a first response to the first network function, where the first response carries or is used to indicate a first model or model information of the first model, and / or the first response carries first energy consumption information of the first model.

2. The method according to claim 1, wherein The first model represents a model available to the first network function determined or obtained by the MTLF based on the indication of energy consumption information or energy consumption information carried in the first request; And / or, the first energy consumption information represents energy consumption information determined or obtained based on the training process of the first model.

3. The method according to claim 1, further includes: Determining or obtaining the first energy consumption information of the first model based on second energy consumption information generated during the training phase of the first model, where the training phase includes: a training data collection phase, and / or, a model training phase, and / or, a model verification phase.

4. The method according to claim 3, wherein, The first model is trained based on a federated learning architecture; the MTLF is a server MTLF; Determining the first energy consumption information of the first model based on the second energy consumption information generated during the training phase of the first model includes: Receiving third energy consumption information sent by each client MTLF; and Calculating the first energy consumption information of the first model based on the third energy consumption information sent by each client MTLF.

5. The method according to claim 4, wherein The third energy consumption information represents the energy consumption information generated by the corresponding local model during the training phase when the corresponding client MTLF trains the local model regarding the first model.

6. The method according to any one of claims 1 to 5, wherein, The energy consumption information includes one or more of the following: The energy quota or energy limit of the model; The energy consumption level or energy level or energy grade or energy level of the model; The maximum number of times the model is used or the number of times the model is used; The valid period of model use or the model use term.

7. The method according to any one of claims 1 to 5, wherein The energy consumption information represents the energy consumption information of any of the following categories: Energy consumption; Renewable capacity; Carbon emissions.

8. An information processing method, applied to a first network function, the method includes: Sending a first request to the MTLF, where the first request is used to request to subscribe to a model or model information from the MTLF, and / or the first request carries an indication of energy consumption information or energy consumption information; Receiving a first response returned by the MTLF, where the first response carries or is used to indicate a first model or model information of the first model, and / or the first response carries first energy consumption information of the first model.

9. The method according to claim 8, wherein The first model represents a model available to the first network function determined or obtained by the MTLF based on the indication of energy consumption information or energy consumption information carried in the first request; And / or, the first energy consumption information represents energy consumption information determined or obtained based on the training process of the first model.

10. The method according to claim 8, further includes: During the process of using the first model, performing energy consumption control based on the first energy consumption information.

11. The method according to any one of claims 8 to 10, wherein The energy consumption information includes one or more of the following: The energy quota or energy limit of the model; The energy consumption level or energy consumption grade or energy level or energy grade of the model; The maximum number of times the model is used or the number of times the model is used; The valid period of model use or the model use term.

12. The method according to any one of claims 8 to 10, wherein The energy consumption information characterizes the energy consumption information of any of the following categories: Energy consumption; Renewable capacity; Carbon emissions.

13. The method according to any one of claims 8 to 10, wherein The first network function includes one of the following: Application function AF; Analysis logic function AnLF.

14. An information processing method, applied to AnLF, includes: Receiving a second request sent by a second network function, where the second request is used to request to obtain analysis data or analysis information about a first model; And Returning a second response to the second network function, where the second response carries fourth energy consumption information.

15. The method according to claim 14, wherein, The fourth energy consumption information characterizes the energy consumption information determined or obtained based on the inference process of the first model.

16. The method according to claim 14, wherein, The first energy consumption information is carried in the second request; the method further includes: Determining whether to provide an inference service for the second network function based on the first energy consumption information.

17. The method according to claim 16, wherein, The first energy consumption information characterizes the energy consumption information determined or obtained based on the training process of the first model.

18. The method according to claim 14, further includes: Determining the fourth energy consumption information of the first model based on the fifth energy consumption information generated in the inference stage of the first model, where the inference stage includes: a data collection stage, and / or, an inference operation stage.

19. The method according to claim 18, wherein, The fifth energy consumption information generated in the data collection stage is determined based on the number of interaction signaling messages of AnLF in the data collection stage; and / or, the fifth energy consumption information generated in the inference operation stage is determined based on the computing energy consumption of AnLF in the inference operation stage.

20. The method according to claim 14, further includes: Performing energy consumption control based on the first energy consumption information during the inference process of the first model.

21. The method according to any one of claims 14 to 20, wherein The energy consumption information includes one or more of the following: The energy quota or energy limit of the model; The energy consumption level or energy consumption grade or energy level or energy grade of the model; The maximum number of times the model is used or the number of times the model is used; The valid period of model use or the model use term.

22. The method according to any one of claims 14 to 20, wherein, The energy consumption information characterizes the energy consumption information of any of the following categories: Energy consumption; Renewable capacity; Carbon emissions.

23. An information processing method, applied to a second network function, includes: Sending a second request to AnLF, where the second request is used to request to obtain analysis data or analysis information about a first model; Receiving a second response returned by AnLF, where the second response carries fourth energy consumption information.

24. The method according to claim 23, wherein, The fourth energy consumption information characterizes the energy consumption information determined or obtained based on the inference process of the first model.

25. The method according to claim 23, wherein The first energy consumption information is carried in the second request.

26. The method according to any one of claims 23 to 25, wherein, The energy consumption information includes one or more of the following: The energy quota or energy limit of the model; The energy consumption level or energy consumption grade or energy level or energy grade of the model; The maximum number of times the model is used or the number of times the model is used; The valid period of model use or the model use term.

27. The method according to any one of claims 23 to 25, wherein, The energy consumption information characterizes the energy consumption information of any of the following categories: Energy consumption; Renewable capacity; Carbon emissions.

28. The method according to any one of claims 23 to 25, wherein The second network function includes one of the following: AF; Policy Control Function (PCF); 5th Generation Mobile Communication Technology Core Network (5GC) Network Function (NF).

29. An information processing method, applied to the NEF, includes: Sending a third request to a third network function, where the third request is used to request the third network function to report sixth energy consumption information; And Receiving the sixth energy consumption information returned by the third network function.

30. The method according to claim 29, wherein, The sixth energy consumption information characterizes the energy consumption information of terminal members.

31. The method according to claim 29, further includes: Receiving a fourth request sent by a fourth network function, where the fourth request is used to request terminal member selection, and / or the fourth request carries a maximum energy consumption limit and / or an energy consumption limit for a single terminal member; And Returning a third response to the fourth network function, where the third response is used to indicate one or more candidate terminal members and / or carry seventh energy consumption information.

32. The method according to claim 31, wherein The one or more candidate terminal members are determined or obtained by the NEF based on the sixth energy consumption information and the maximum energy consumption limit and / or the energy consumption limit for a single terminal member.

33. The method according to claim 31, wherein, The seventh energy consumption information characterizes the energy consumption information of each terminal member among the one or more candidate terminal members, and / or, the seventh energy consumption information characterizes the total energy consumption information of the one or more candidate terminal members.

34. The method according to any one of claims 29 to 33, wherein The energy consumption information characterizes the energy consumption information of any one of the following categories: Energy consumption; Renewable capacity; Carbon emissions.

35. The method according to any one of claims 29 to 33, wherein The third network function represents 5GC NF; and / or, the fourth network function represents AF.

36. An information processing device includes: A first receiving unit, configured to receive a first request sent by a first network function, where the first request is used to request the MTLF to subscribe to a model or model information, and / or the first request carries an indication of energy consumption information or energy consumption information; And A first sending unit, configured to return a first response to the first network function, where the first response carries or is used to indicate a first model or the model information of the first model, and / or, the first response carries the first energy consumption information of the first model.

37. An information processing device includes: A second sending unit, configured to send a first request to the MTLF, where the first request is used to request the MTLF to subscribe to a model or model information, and / or the first request carries an indication of energy consumption information or energy consumption information; And A second receiving unit, configured to receive a first response returned by the MTLF, where the first response carries or is used to indicate a first model or the model information of the first model, and / or, the first response carries the first energy consumption information of the first model.

38. An information processing device includes: A third receiving unit, configured to receive a second request sent by a second network function, where the second request is used to request to obtain analysis data or analysis information about a first model; And A third sending unit, configured to return a second response to the second network function, where the second response carries fourth energy consumption information.

39. An information processing device includes: A fourth sending unit, configured to send a second request to AnLF, where the second request is used to request to obtain analysis data or analysis information about a first model; and A fourth receiving unit, configured to receive a second response returned by AnLF, where the second response carries fourth energy consumption information.

40. An information processing device, comprising: A fifth sending unit, configured to send a third request to a third network function, where the third request is used to request the third network function to report sixth energy consumption information; and A fifth receiving unit, configured to receive the sixth energy consumption information returned by the third network function.

41. A MTLF, comprising: A first processor and a first communication interface; wherein, The first communication interface is configured to receive a first request sent by a first network function, where the first request is used to request to subscribe to a model or model information from MTLF, and / or the first request carries an indication of energy consumption information or energy consumption information; and The first communication interface is further configured to return a first response to the first network function, where the first response carries or is used to indicate a first model or model information of the first model, and / or the first response carries first energy consumption information of the first model.

42. A first network function, comprising: A second processor and a second communication interface; wherein, The second communication interface is configured to send a first request to MTLF, where the first request is used to request to subscribe to a model or model information from MTLF, and / or the first request carries an indication of energy consumption information or energy consumption information; and The second communication interface is further configured to receive a first response returned by MTLF, where the first response carries or is used to indicate a first model or model information of the first model, and / or the first response carries first energy consumption information of the first model.

43. An AnLF, comprising: A third processor and a third communication interface; wherein, The third communication interface is configured to receive a second request sent by a second network function, where the second request is used to request to obtain analysis data or analysis information about a first model; and The third communication interface is further configured to return a second response to the second network function, where the second response carries fourth energy consumption information.

44. A second network function, comprising: A fourth processor and a fourth communication interface; wherein, The fourth communication interface is configured to send a second request to AnLF, where the second request is used to request to obtain analysis data or analysis information about a first model; and The fourth communication interface is configured to receive a second response returned by AnLF, where the second response carries fourth energy consumption information.

45. A network function, comprising: A processor and a memory for storing a computer program that can run on the processor, wherein, when the processor is used to run the computer program, it executes the steps of the method according to any one of claims 1 to 7; or executes the steps of the method according to any one of claims 8 to 13; or executes the steps of the method according to any one of claims 14 to 22; or executes the steps of the method according to any one of claims 23 to 28; or executes the steps of the method according to any one of claims 29 to 35.

46. A storage medium having a computer program stored thereon, wherein, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 7; or implements the steps of the method according to any one of claims 8 to 13; or implements the steps of the method according to any one of claims 14 to 22; or executes the steps of the method according to any one of claims 23 to 28; or implements the steps of the method according to any one of claims 29 to 35.

Images