CN117062185A - Federal learning node discovery and registration method and device, storage medium and equipment - Google Patents
Federal learning node discovery and registration method and device, storage medium and equipment Download PDFInfo
- Publication number
- CN117062185A CN117062185A CN202210492707.3A CN202210492707A CN117062185A CN 117062185 A CN117062185 A CN 117062185A CN 202210492707 A CN202210492707 A CN 202210492707A CN 117062185 A CN117062185 A CN 117062185A
- Authority
- CN
- China
- Prior art keywords
- data analysis
- federal learning
- functional entity
- discovery
- analysis functional
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 87
- 238000007405 data analysis Methods 0.000 claims abstract description 284
- 230000006870 function Effects 0.000 claims description 70
- 238000004458 analytical method Methods 0.000 claims description 60
- 230000004044 response Effects 0.000 claims description 33
- 238000004590 computer program Methods 0.000 claims description 5
- 238000004891 communication Methods 0.000 abstract description 4
- 238000010586 diagram Methods 0.000 description 13
- 238000012549 training Methods 0.000 description 10
- 238000010801 machine learning Methods 0.000 description 9
- 238000007726 management method Methods 0.000 description 6
- 238000012545 processing Methods 0.000 description 6
- 230000008859 change Effects 0.000 description 5
- 230000003993 interaction Effects 0.000 description 5
- 230000003287 optical effect Effects 0.000 description 3
- 230000006978 adaptation Effects 0.000 description 2
- 238000012517 data analytics Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 239000003999 initiator Substances 0.000 description 2
- 239000013307 optical fiber Substances 0.000 description 2
- 230000000644 propagated effect Effects 0.000 description 2
- 238000012546 transfer Methods 0.000 description 2
- 206010063385 Intellectualisation Diseases 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 238000013523 data management Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000003252 repetitive effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W40/00—Communication routing or communication path finding
- H04W40/24—Connectivity information management, e.g. connectivity discovery or connectivity update
- H04W40/246—Connectivity information discovery
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/50—Service provisioning or reconfiguring
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W60/00—Affiliation to network, e.g. registration; Terminating affiliation with the network, e.g. de-registration
- H04W60/02—Affiliation to network, e.g. registration; Terminating affiliation with the network, e.g. de-registration by periodical registration
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Software Systems (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Artificial Intelligence (AREA)
- Computer And Data Communications (AREA)
Abstract
The disclosure provides a federal learning node discovery and registration method and device, a storage medium and equipment, and relates to the technical field of communication. The related federal learning node discovery method comprises the following steps: acquiring an NF discovery request from a server-side data analysis functional entity, wherein the NF discovery request is used for requesting to discover a client-side data analysis functional entity conforming to federal learning conditions of the server-side data analysis functional entity; according to the NF discovery request, a first client data analysis functional entity which accords with the federal learning condition of the server data analysis functional entity is discovered in the registered client data analysis functional entities; and returning the information of the first client data analysis functional entity to the server data analysis functional entity. According to the embodiment of the invention, the server-side data analysis functional entity can find that the client-side data analysis functional entity meeting the federal learning condition participates in the federal learning task, and the finding efficiency of federal learning participants is improved.
Description
Technical Field
The disclosure relates to the technical field of communication, and in particular relates to a federal learning node discovery and registration method and device, a storage medium and equipment.
Background
At present, federal learning can carry out joint learning modeling on the premise of meeting the requirements of data privacy, safety and supervision, and the problem of data island is solved. NWDAF (Network Data Analytics Function, network data analysis function) is a network element in 5GC (5G core network), and can provide analysis services to NFs (Network Functions, network function), afs (Application function ), and OAM (Operation, administration, and Management). NWDAF contains at least one of AnLF (Analytics Logical Function, analytical logic function) and MTLF (Model Training Logical Function, model training logic function).
The enabling technology of federal learning towards NWDAF is one of the main research contents of 5G network intellectualization, namely, training an ML (Machine learning) model by cooperation of one Server NWDAF (i.e., NWDAF as a Server, hereinafter also referred to as a Server NWDAF) and a plurality of clients NWDAFs (i.e., NWDAF as clients, hereinafter also referred to as clients NWDAF), wherein the Client NWDAF trains a local ML model locally by using its own data and shares it to the Server NWDAF, and the Server NWDAF aggregates the local ML models from different clients NWDAF into a global or optimal ML model and sends it back to the Client NWDAF. Only NWDAF with MTLF can support model training function, and participants of federal learning have complete autonomous authority on their local data, and can autonomously decide whether to join or when to join federal learning to perform joint learning modeling. However, the server NWDAF as the federal learning task initiator generally cannot learn the situation of the client NWDAF, so that it is difficult for the server NWDAF to find the client NWDAF that meets federal learning conditions.
It should be noted that the information disclosed in the above background section is only for enhancing understanding of the background of the present disclosure and thus may include information that does not constitute prior art known to those of ordinary skill in the art.
Disclosure of Invention
The embodiment of the disclosure provides a federal learning node discovery and registration method and device, a storage medium and equipment, and at least solves the problem that a server NWDAF is difficult to discover a client NWDAF conforming to federal learning conditions because the server NWDAF serving as a federal learning task initiator cannot generally learn the client NWDAF.
According to a first aspect of embodiments of the present disclosure, there is provided a federal learning node discovery method, including: acquiring a network function NF discovery request from a server-side data analysis functional entity, wherein the NF discovery request is used for requesting to discover a client-side data analysis functional entity which accords with federal learning conditions of the server-side data analysis functional entity; according to the NF discovery request, a first client data analysis functional entity which accords with federal learning conditions of the server data analysis functional entity is discovered in registered client data analysis functional entities; and returning the information of the first client data analysis functional entity to the server data analysis functional entity.
Optionally, the NF discovery request includes: information whether there is a capability to support federal learning, an analysis identity, and NF type.
Optionally, the NF discovery request further includes: information whether to be added to the federal learning task.
Optionally, the method further comprises: before acquiring a network function NF discovery request from a server data analysis function entity, acquiring a registration request from a second client data analysis function entity, where the registration request is used to request to register configuration information of the second client data analysis function entity, and the configuration information includes: information whether there is a capability to support federal learning; storing the configuration information, the analysis identification and the NF type; and storing the configuration information.
Optionally, the configuration information further includes: information whether to be added to the federal learning task.
Optionally, the method includes: and acquiring a configuration information updating request from the registered client data analysis functional entity, wherein the configuration information updating request is used for requesting to update whether information of whether the registered client data analysis functional entity is willing to join in a federal learning task or not.
According to a second aspect of the embodiments of the present disclosure, there is also provided a federal learning node registration method, including: the method comprises the steps that a client data analysis functional entity sends a registration request to a discovery network element, wherein the registration request is used for requesting to register configuration information of the client data analysis functional entity, and the configuration information comprises the following components: information about whether there is federal learning supporting capability, analysis identity, and network function NF type.
Optionally, the configuration information further includes: information whether to be added to the federal learning task.
Optionally, the method further comprises: and the client data analysis functional entity sends a configuration information update request to the discovery network element, wherein the configuration information update request is used for requesting to update whether information of whether the client data analysis functional entity is willing to join in a federal learning task or not in the configuration information of the client data analysis functional entity.
Optionally, the method further comprises: acquiring a federal learning service request from a server-side data analysis functional entity, wherein the federal learning service request is used for inquiring whether the client-side data analysis functional entity is willing to join a federal learning task; and sending a federal learning service request response message to the server-side data analysis functional entity according to the federal learning service request.
According to a third aspect of the embodiments of the present disclosure, there is also provided a federal learning node discovery method, including: sending a network function NF discovery request to a discovery network element, wherein the NF discovery request comprises: information whether there is federal learning supporting capability, analysis identity, and NF type; and acquiring an NF discovery request response message returned by the discovery network element.
Optionally, the NF discovery request further includes: information whether to be added to the federal learning task.
Optionally, the NF discovery request response message includes information of the first client data analysis functional entity, and the method further includes: sending a federal learning service request to the first client data analysis functional entity, the federal learning service request being used to query whether the first client data analysis functional entity is willing to join a federal learning task; and receiving a federal learning service request response message returned by the first client data analysis functional entity.
According to a fourth aspect of embodiments of the present disclosure, there is also provided a federal learning node discovery apparatus, including: the system comprises a first acquisition module, a second acquisition module and a server-side data analysis function entity, wherein the first acquisition module is used for acquiring a network function NF discovery request from the server-side data analysis function entity, and the NF discovery request is used for requesting to discover a client-side data analysis function entity which accords with federal learning conditions of the server-side data analysis function entity; the discovery module is used for discovering a first client data analysis functional entity which accords with the federal learning condition of the server data analysis functional entity in the registered client data analysis functional entities according to the NF discovery request; and the return module is used for returning the information of the first client data analysis functional entity to the server data analysis functional entity.
According to a fifth aspect of embodiments of the present disclosure, there is also provided a federal learning node registration apparatus, including: the first sending module is configured to send a registration request to a discovery network element by a client data analysis functional entity, where the registration request is used to request registration of configuration information of the client data analysis functional entity, and the configuration information at least includes: information whether there is a capability to support federal learning.
According to a sixth aspect of the embodiments of the present disclosure, there is also provided a federal learning node discovery apparatus, including: a second sending module, configured to send a network function NF discovery request to a discovery network element, where the NF discovery request includes: information whether there is federal learning supporting capability, analysis identity, and NF type; and the second acquisition module is used for acquiring the NF discovery request response message returned by the discovery network element.
According to a seventh aspect of the embodiments of the present disclosure, there is also provided an electronic device, including: a processor; and a memory for storing executable instructions of the processor; wherein the processor is configured to perform any one of the federal learning node discovery methods or any one of the federal learning node registration methods provided by embodiments of the present disclosure via execution of the executable instructions.
According to an eighth aspect of the embodiments of the present disclosure, there is further provided a computer readable storage medium having stored thereon a computer program, wherein the computer program, when executed by a processor, implements any one of the federal learning node discovery methods or any one of the federal learning node registration methods provided by the embodiments of the present disclosure.
According to the federal learning node discovery, registration method, device, storage medium and equipment, a first data analysis functional entity client conforming to federal learning conditions of a server data analysis functional entity is discovered in registered client data analysis functional entities according to an acquired NF discovery request of the server data analysis functional entity, and information of the first data analysis functional entity client is returned to the server data analysis functional entity, so that the server data analysis functional entity can discover that the client data analysis functional entity conforming to federal learning conditions participates in federal learning tasks before federal learning tasks begin, and additional expenditure caused by the fact that the discovered client data analysis functional entity does not conform to the conditions is avoided, and efficiency of discovering federal learning participants is improved.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the disclosure and together with the description, serve to explain the principles of the disclosure. It will be apparent to those of ordinary skill in the art that the drawings in the following description are merely examples of the disclosure and that other drawings may be derived from them without undue effort.
FIG. 1 is a schematic diagram of a federal learning system according to an embodiment of the present disclosure;
FIG. 2 is a flow chart illustrating a federal learning node discovery method according to an exemplary embodiment of the present disclosure;
FIG. 3 is a flowchart illustrating a federal learning node discovery method according to an exemplary embodiment of the present disclosure;
FIG. 4 is a flowchart illustrating a federal learning node discovery method according to an exemplary embodiment of the present disclosure;
FIG. 5 is a flowchart illustrating a federal learning node registration method according to an exemplary embodiment of the present disclosure;
FIG. 6 is a flowchart illustrating a federal learning node registration method according to an exemplary embodiment of the present disclosure;
FIG. 7 is a flowchart illustrating a federal learning node registration method according to an exemplary embodiment of the present disclosure;
FIG. 8 is a flowchart illustrating a federal learning node discovery method according to an exemplary embodiment of the present disclosure;
FIG. 9 is a schematic diagram illustrating a federal learning node registration and discovery method according to an exemplary embodiment of the present disclosure;
FIG. 10 is a schematic diagram illustrating a federal learning node registration and discovery method according to an exemplary embodiment of the present disclosure;
FIG. 11 is a schematic diagram of a federal learning node discovery apparatus according to an exemplary embodiment of the present disclosure;
FIG. 12 is a schematic diagram of a federal learning node registration apparatus according to an exemplary embodiment of the present disclosure;
FIG. 13 is a schematic diagram of a federal learning node discovery apparatus according to an exemplary embodiment of the present disclosure;
fig. 14 is a schematic structural view of an electronic device according to an exemplary embodiment of the present disclosure.
Detailed Description
Example embodiments will now be described more fully with reference to the accompanying drawings. However, the exemplary embodiments may be embodied in many forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the concept of the example embodiments to those skilled in the art. The described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.
Furthermore, the drawings are merely schematic illustrations of the present disclosure and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and thus a repetitive description thereof will be omitted. Some of the block diagrams shown in the figures are functional entities and do not necessarily correspond to physically or logically separate entities. These functional entities may be implemented in software or in one or more hardware modules or integrated circuits or in different networks and/or processor devices and/or microcontroller devices.
Fig. 1 is a schematic diagram of a federal learning system according to an embodiment of the present disclosure, as shown in fig. 1, including a server data analysis function 102 and one or more client data analysis functions (e.g., client data analysis function 104-client data analysis function 10 n) in communication with the server data analysis function 102, and a discovery network element 106. The server data analysis functional entity 102 and one or more client data analysis functional entities (e.g., the client data analysis functional entity 104 to the client data analysis functional entity 10 n) each have the capability of supporting federal learning, the client data analysis functional entity can use its own data to train and share the local ML model to the server data analysis functional entity, and the server data analysis functional entity aggregates the local ML models from different client data analysis functional entities into a global or optimal ML model and sends it back to the client data analysis functional entity. Wherein n is an integer greater than or equal to 1.
For example, any one of the server-side data analysis functional entity 102 or the one or more client-side data analysis functional entities 104 to 10n may be NWDAF in the 5G network architecture, or MDAF (Management Data Analytics Function, management data analysis function) of a network manager. The discovery network element 106 supports registration, discovery, update, and authentication functions for network functions or network services. For example, the discovery network element 106 may be an NRF (Network Repository function, network storage function) or UDM (Unified Data Management ) network element or UDR (Unified Data Repository, unified data repository) in a 5G network architecture.
Fig. 2 is a flow chart illustrating a federal learning node discovery method, which may be performed by a discovery network element, according to an exemplary embodiment of the present disclosure, as shown in fig. 2, the method comprising:
in step S202, an NF (Network Founction, network function) discovery request from a server-side data analysis functional entity is acquired, where the NF discovery request is used to request to discover a client-side data analysis functional entity that meets federal learning conditions of the server-side data analysis functional entity;
In an exemplary embodiment, at least information indicating whether there is a federal learning condition with a capability to support federal learning, NF type, and analysis identity (analysis ID) in the server data analysis function entity, wherein NF type includes, but is not limited to, AMF (Access and Mobility Management Function ), SMF (Session Management Function, session management function), and NWDAF; the analysis identity may be set to NF load information (data transfer), for example, to indicate that the federal learning model is used for analysis of NF data transfer, and Network Performance (network performance), for example, to indicate that the federal learning model is used for analysis of network performance.
In step S204, according to the NF discovery request, a first client data analysis functional entity that meets federal learning conditions of the server data analysis functional entity is discovered in the registered client data analysis functional entities;
the discovery network element can store configuration information of one or more registered client data analysis functional entities, and the discovery network element can match the configuration information of each registered client data analysis functional entity with federal learning conditions of the server data analysis functional entity so as to discover one or more first client data analysis functional entities which accord with the federal learning conditions of the server data analysis functional entity.
In step S206, information of the first client data analysis functional entity is returned to the server data analysis functional entity.
In an exemplary embodiment, the client data analysis functional entity takes NWDAF as an example, and the discovery network element discovers one or more candidate NWDAF instances meeting federal learning conditions of the server data analysis functional entity in the registered NWDAF, and may return the one or more candidate NWDAF instances to the NF consumer, that is, the server data analysis functional entity. Wherein each candidate NWDAF instance may further comprise filtering information of the ML model related to the analysis identity, such as S-nsai (Single Network Slice Selection Assistance Information ), and region of interest, etc.
According to the federal learning node discovery method, a first data analysis functional entity client conforming to federal learning conditions of a server data analysis functional entity is discovered in registered client data analysis functional entities according to an acquired NF discovery request of the server data analysis functional entity, and information of the first data analysis functional entity client is returned to the server data analysis functional entity, so that the server data analysis functional entity can discover that the client data analysis functional entity conforming to federal learning conditions participates in federal learning tasks before federal learning tasks begin, additional expenses caused by the fact that the discovered client data analysis functional entity does not conform to the conditions are avoided, and efficiency of discovering federal learning participants is improved.
In an embodiment of the present disclosure, the NF discovery request may include:
information whether there is a capability to support federal learning, an analysis identity, and NF type.
In an exemplary embodiment, before the federal learning task starts, the server-side data analysis functional entity needs to discover that the client-side data analysis functional entity meeting the current federal learning condition participates in the current federal learning task, and before the server-side data analysis functional entity starts the current federal learning task, the server-side data analysis functional entity sends an NF discovery request to the discovery network element, where the NF discovery request may include information for supporting federal learning, an analysis identifier for identifying an analysis type of the current federal learning task, a type of the client-side data analysis functional entity to participate in the current federal learning, and an NF type described above.
In an embodiment of the present disclosure, the NF discovery request may further include: information whether to be added to the federal learning task.
In an exemplary embodiment, for the case that the NF discovery request includes information about whether to join the federal learning task, after the discovery network element obtains the NF discovery request, the discovery network element may search for the client data analysis functional entity registered with the information about whether to join the federal learning task in the configuration information of the registered client data analysis functional entity, and return the searched information of the client data analysis functional entity to the server data analysis functional entity, based on which the server data analysis functional entity does not need to query whether the client data analysis functional entity is willing to join the federal learning task in a manner of performing data interaction with the client data analysis functional entity, and may reduce the number of data interactions between the server data analysis functional entity and the client data analysis functional entity.
FIG. 3 is a flow chart illustrating a federal learning node discovery method according to an exemplary embodiment of the present disclosure, as shown in FIG. 3, the method may further include:
in step S302, before obtaining a network function NF discovery request from a server network data analysis function entity, a registration request from a second client data analysis function entity is obtained, where the registration request is used to request to register configuration information of the second client data analysis function entity, and the configuration information includes: information whether there is federal learning supporting capability, analysis identity, and NF type;
it should be noted that the second client data analysis functional entity may be the same client data analysis functional entity as the first client data analysis functional entity, or may be a different client data analysis functional entity from the first client data analysis functional entity.
In an exemplary embodiment, the client data analysis functional entity requesting to register on the discovery network element may include a data analysis functional entity with federal learning supporting capability, or may include a data analysis functional entity without federal learning supporting capability, and for the data analysis functional entity with federal learning supporting capability, the configuration information registered by the data analysis functional entity may include information with federal learning supporting capability, an analysis identifier, and an NF type. And for the data analysis functional entity which does not have the capability of supporting federal learning, the registered configuration information can only comprise the information which does not have the capability of supporting federal learning, or can also have the NF type.
In step S304, the configuration information is stored.
In an exemplary embodiment, the discovery network element stores configuration information of the client data analysis function entity in the discovery network element after receiving the configuration information of the client data analysis function entity.
In an embodiment of the present disclosure, the configuration information may further include:
information whether to be added to the federal learning task.
Illustratively, for a client data analysis functional entity with federal learning-supporting capabilities, its configuration information may include: information with the ability to support federal learning, analysis identification, and NF type. Alternatively, the configuration information may include information having the ability to support federal learning, an analysis identifier, NF type, and information whether it is willing to join federal learning tasks. Wherein, whether a data analysis functional entity has the capability of supporting federal learning is a capability of the network element, the capability does not change with time or change of conditions, so the capability is registered as configuration information, and the updating of subsequent configuration information of the data analysis functional entity is not involved. However, for a data analysis functional entity, whether to be added to the federal learning task is not a capability of the network element, and the information may change with time or condition, so that registering whether to be added to the federal learning task as configuration information may involve updating subsequent configuration information of the data analysis functional entity, but registering the information as configuration information may reduce data interaction between the server data analysis functional entity and the client data network element during discovery of the client data analysis functional entity that meets federal learning conditions.
FIG. 4 is a flowchart illustrating a federal learning node discovery method according to an exemplary embodiment of the present disclosure, as shown in FIG. 4, which may further include, based on the method shown in FIG. 2:
in step S402, a configuration information update request from the registered client data analysis functional entity is acquired, where the configuration information update request is used to request updating of information about whether the registered client data analysis functional entity is willing to join in a federal learning task or not in the configuration information.
The registered client data analysis functional entity refers to a client data analysis functional entity which has registered configuration information in a discovery network element, and the registered configuration information comprises information about whether the client data analysis functional entity is willing to join in a federal learning task.
In an exemplary embodiment, the configuration information update request may further indicate that there is an analysis identifier corresponding to the federal learning task. When the registered client data analysis functional entity is willing to join the federal learning task, for example, the original registered client data analysis functional entity is willing to join the federal learning task corresponding to the specified analysis identifications, the client data analysis functional entity is subsequently willing to join the federal learning task, the client data analysis functional entity is not willing to join the federal learning task corresponding to one or more analysis identifications among the specified analysis identifications, so the client data analysis functional entity needs to inform the discovery network element of the change, so as to realize the update of the configuration information of the client data analysis functional entity stored in the discovery network element, for example, the original client data analysis functional entity 1 is willing to join the analysis identification a, the analysis identification B and the analysis identification C respectively correspond to three federal learning tasks, the client data analysis functional entity 1 is subsequently willing to join the federal learning task, the client data analysis functional entity 1 is not willing to join the federal learning task corresponding to the analysis identification a, and the client data analysis functional entity 1 can send a configuration information update request to the discovery network element, and the configuration information update request can include: information that the federal learning task is not willing to be added and an analysis identifier a are used for indicating that the client data analysis functional entity 1 is not willing to be added to the federal learning task corresponding to the analysis identifier a.
Fig. 5 is a flowchart illustrating a federal learning node registration method that may be performed by a client data analysis functional entity, as shown in fig. 5, according to an exemplary embodiment of the present disclosure, the method comprising:
in step S502, a client data analysis functional entity sends a registration request to a discovery network element, where the registration request is used to request to register configuration information of the client data analysis functional entity, where the configuration information includes: information whether there is a capability to support federal learning, an analysis identity, and NF type.
After the client data analysis functional entity sends the registration request to the discovery network element, the method may further include:
in step S504, the client data analysis functional entity receives the registration request response message returned by the discovery network element.
The registration request response message may include information that the client data analysis function entity is successfully registered or that the registration is failed.
In an exemplary embodiment, for a client data analysis functional entity that does not have the capability to support federal learning, its configuration information registered with the discovery network element may include only information that does not have the capability to support federal learning. Alternatively, NF types may also be included. And for a client data analysis functional entity with the capability of supporting federal learning, the configuration information registered with the discovery network element comprises the information with the capability of supporting federal learning, the NF type and the analysis identifier.
According to the federal learning node registration method, the client data analysis functional entity registers information of whether the client data analysis functional entity has the capacity of supporting federal learning as configuration information on the discovery network element, so that the server data analysis functional entity can discover the client data analysis functional entity meeting federal learning conditions before a federal learning task starts, and therefore additional expenditure caused by the fact that the discovered data analysis functional entity does not meet the conditions can be avoided, and efficiency of discovering federal learning participants can be improved.
In an embodiment of the present disclosure, the configuration information may further include: information whether to be added to the federal learning task.
In an exemplary embodiment, when registering information about whether the client data analysis functional entity has the capability of supporting federal learning with the discovery network element, the client data analysis functional entity may include information about whether the client data analysis functional entity is willing to join federal learning tasks in configuration information, or may not include the information. The analysis identifier and NF type may be registered when the client data analysis functional entity registers with the discovery network element for the first time, or may be registered together with information about whether the client data analysis functional entity has the capability of supporting federal learning, which is not specifically limited in the embodiment of the present disclosure. The advantages and disadvantages of the two registration methods, including whether to participate in the federal learning task and whether to not included in the configuration information, are described in detail above, and are not described here.
FIG. 6 is a flowchart illustrating a federal learning node registration method according to an exemplary embodiment of the present disclosure, as shown in FIG. 6, which may further include, based on the method shown in FIG. 5:
in step S602, the client data analysis functional entity sends a configuration information update request to the discovery network element, where the configuration information update request is used to request updating of information about whether the client data analysis functional entity is willing to join in a federal learning task in the configuration information of the client data analysis functional entity.
In an embodiment of the present disclosure, the NF discovery request may further include: information whether to be added to the federal learning task.
In an exemplary embodiment, for the case that the NF discovery request includes information about whether to join the federal learning task, after the discovery network element obtains the NF discovery request, the discovery network element may search for the client data analysis functional entity registered with the information about whether to join the federal learning task in the configuration information of the registered client data analysis functional entity, and return the searched information of the client data analysis functional entity to the server data analysis functional entity, based on which the server data analysis functional entity does not need to query whether the client data analysis functional entity is willing to join the federal learning task in a manner of performing data interaction with the client data analysis functional entity, and may reduce the number of data interactions between the server data analysis functional entity and the client data analysis functional entity.
In an exemplary embodiment, the client data analysis functional entity registers, with the discovery network element, not only information about whether the client data analysis functional entity has the capability of supporting federal learning, but also information about whether the client data analysis functional entity is willing to join a federal learning task, so when a change occurs in a situation that the client data analysis functional entity is willing to join the federal learning task, the client data analysis functional entity needs to send a configuration information update request to the discovery network element to request to update the information about whether the client data analysis functional entity stored in the discovery network element is willing to join the federal learning task.
FIG. 7 is a flowchart illustrating a federal learning node registration method according to an exemplary embodiment of the present disclosure, as shown in FIG. 7, which may further include, based on the method shown in FIG. 5:
in step S702, a federal learning service request from a server-side data analysis functional entity is obtained, where the federal learning service request is used to inquire whether the client-side data analysis functional entity is willing to join a federal learning task;
in an exemplary embodiment, if the client data analysis functional entity does not register information about whether to join federal learning with the discovery network element, the server data analysis functional entity needs to send a federal learning service request to the candidate client data analysis functional entity returned by the discovery network element in the discovery process of the client data analysis functional entity meeting federal learning conditions, so as to inquire whether the candidate client data analysis functional entity is willing to join the current federal learning task. Wherein, the federal learning service request can include: an analysis identification identifying a type of federal learning.
In step S704, a federal learning service request response message is sent to the server-side data analysis functional entity according to the federal learning service request.
In an exemplary embodiment, the client data analysis functional entity may determine whether to participate in the current federal learning task of the server data analysis functional entity according to its own situation, if the client data analysis functional entity has a wish to participate in the federal learning task, a positive federal learning service request response message may be sent to the server data analysis functional entity, and if the client data analysis functional entity does not wish to participate in the federal learning task, a negative federal learning service request response message may be sent to the server data analysis functional entity.
Fig. 8 is a flowchart illustrating a federal learning node discovery method that may be performed by a server-side data analysis functional entity, as shown in fig. 8, according to an exemplary embodiment of the present disclosure, the method comprising:
in step S802, an NF discovery request is sent to a discovery network element, where the NF discovery request includes: information whether there is federal learning supporting capability, analysis identity, and NF type;
in an exemplary embodiment, before performing federal learning, the server-side data analysis functional entity may determine, according to information of a federal learning task to be currently performed, an analysis identifier and an NF type corresponding to a participant in the federal learning (i.e., the client-side data analysis functional entity), send an NF discovery request to the discovery network element, where the NF discovery request carries information supporting federal learning capability, the analysis identifier and the NF type. The discovery network element can discover the client data analysis functional entity which accords with the learning condition of the federal learning task to be executed by the server data analysis functional entity according to the information in the NF discovery request.
In step S804, an NF discovery request response message returned by the discovery network element is obtained.
In an exemplary embodiment, after sending an NF discovery request to a discovery network element, a server side data analysis functional entity includes information of one or more first client side data analysis functional entities in an NF discovery request response message returned by the discovery network element, and when the first client side data analysis functional entity registers in the discovery network element, the first client side data analysis functional entity does not register information about whether to join in a federal learning task, in which case, after receiving the NF discovery request response message, the server side data analysis functional entity needs to further confirm whether the first client side data analysis functional entity in the response message is willing to join in the current federal learning task. Based on this, the federal learning node discovery method of the embodiments of the present disclosure may further include: sending a federal learning service request to a first client data analysis functional entity in the discovery request response message, wherein the federal learning service request is used for inquiring whether the first client data analysis functional entity is willing to join a federal learning task; and receiving a federal learning service request response returned by the first client data analysis functional entity. Wherein, the federal learning service request can further comprise an analysis identifier for identifying the analysis type of the current federal learning task. The federal learning service request response message returned by the first client data analysis functional entity may be affirmative, indicating that the federal learning task of the server data analysis functional entity is willing to be added, or the federal learning service request effect message returned by the first client data analysis functional entity may be also negative, indicating that the federal learning task of the server data analysis functional entity is unwilling to be added.
In an embodiment of the present disclosure, the NF discovery request response message includes information of the first client data analysis functional entity, and based on this, the federal learning node discovery method may further include:
sending a federal learning service request to the first client data analysis functional entity, wherein the federal learning service request comprises: the analysis identifier is used for inquiring whether the client data analysis functional entity is willing to join in a federal learning task or not by the federal learning service request;
and receiving a federal learning service request response returned by the client data analysis functional entity.
In the following, fig. 9 and fig. 10 are taken as an example, a server data analysis functional entity is taken as an example of a server NWDAF, a Client data analysis functional entity is taken as an example of a Client NWDAF, and a network element is found as an example of an NRF in the examples of fig. 9 and fig. 10.
Fig. 9 is a schematic diagram illustrating a federal learning node registration and discovery method according to an exemplary embodiment of the present disclosure, as shown in fig. 9, the method including:
step S902: the Client NWDAF (for example, client NWDAF1 … Client NWDAFn) sends NF registration request information to the NRF, registers a configuration file (Client NWDAF profile, which is an example of the above configuration information) of the Client NWDAF to the NRF, where the configuration file includes NF types (types), whether a model training logic function MTLF is included (i.e., whether there is a capability to support federal learning), an analysis identifier (analysis ID), whether it is willing to join a federal learning task, and the like;
Wherein NF types is set to NWDAF;
an analysis identifier (analysis ID) is used to indicate the type of federal learning;
step S904: the NRF stores the configuration file of the Client NWDAF and sends an NF registration response message to the Client NWDAF;
step S906: the Server NWDAF sends NF discovery request information to the NRF;
step S908: the NRF determines whether there is a Client NWDAF that meets the conditions, including NF types, whether it includes a model training logic function MTLF, an analysis ID, whether it is willing to join a federal learning task, etc., and sends an NF discovery request response to the Server NWDAF, returning one or more clients NWDAFs (e.g., client NWDAF 1, …, N) that have the ability to support federal learning and are willing to join the federal learning task.
FIG. 10 is a schematic diagram illustrating a federal learning node registration and discovery method, as shown in FIG. 10, according to an exemplary embodiment of the present disclosure, including:
step S1002: the Client NWDAF sends NF registration request information to the NRF, registers a configuration file (Client NWDAF profile) of the Client NWDAF into the NRF, wherein the configuration file comprises NF types, whether a model training logic function MTLF (i.e. whether the model training logic function MTLF has the capability of supporting federal learning), analysis identification (analysis ID) and the like;
Wherein NF types is set to NWDAF, analysis identity (analysis ID) is used to indicate the type of federal learning;
step S1004: the NRF stores the configuration file of the Client NWDAF and sends an NF registration response message to the Client NWDAF;
step S1006: the Server NWDAF sends NF discovery request information to the NRF;
step S1008: the NRF judges whether the Client NWDAF meets the condition or not, and comprises NF types, whether a model training logic function MTLF (namely whether the model training logic function MTLF has the capability of supporting the federal learning or not), analysis identification (analysis ID) and the like, and sends NF discovery response information to the Server NWDAF to return one or more Client NWDAF supporting the federal learning technology;
step S1010: the Server NWDAF sends federal learning service request information to the Client NWDAF, including whether the Client is willing to join federal learning tasks or not;
step S1012: the Client NWDAF sends a federal learning service request response message to the Server NWDAF, including whether to join the federal learning task or not, and the like.
Fig. 11 is a schematic structural diagram of a federal learning node discovery apparatus according to an exemplary embodiment of the present disclosure, and as shown in fig. 11, the apparatus 110 includes:
a first obtaining module 112, configured to obtain a network function NF discovery request from a server data analysis functional entity, where the NF discovery request is used to request to discover a client data analysis functional entity that meets federal learning conditions of the server data analysis functional entity;
A discovery module 114, configured to discover, according to the NF discovery request, a first client data analysis functional entity that meets federal learning conditions of the server data analysis functional entity from registered client data analysis functional entities;
and the return module 116 is configured to return information of the first client data analysis functional entity to the server data analysis functional entity.
In an embodiment of the present disclosure, the NF discovery request may include:
information whether there is a capability to support federal learning, an analysis identity, and NF type.
In an embodiment of the present disclosure, the NF discovery request may further include:
information whether to be added to the federal learning task.
In an embodiment of the present disclosure, the federal learning node discovery apparatus may further include:
a third obtaining module, configured to obtain a registration request from a second client data analysis functional entity before obtaining a network function NF discovery request from the server data analysis functional entity, where the registration request is used to request to register configuration information of the second client data analysis functional entity, and the configuration information includes: information whether there is federal learning supporting capability, analysis identity, and NF type; and storing the configuration information.
In an embodiment of the present disclosure, the configuration information may further include:
information whether to be added to the federal learning task.
In an embodiment of the present disclosure, the federal learning node discovery apparatus may further include:
and the fourth acquisition module is used for acquiring a configuration information updating request from the third client data analysis functional entity, wherein the configuration information updating request is used for requesting to update whether information of the federal learning task is willing to be added in the configuration information of the third client data analysis functional entity.
Fig. 12 is a schematic structural diagram of a federal learning node registration apparatus according to an exemplary embodiment of the present disclosure, and as shown in fig. 12, the apparatus 120 includes:
a first sending module 122, configured to send a registration request to a discovery network element by a client data analysis functional entity, where the registration request is used to request to register configuration information of the client data analysis functional entity, where the configuration information includes: information whether there is a capability to support federal learning, an analysis identity, and NF type.
In an embodiment of the disclosure, the configuration information further includes:
information whether to be added to the federal learning task.
In an embodiment of the present disclosure, the federal learning node registration apparatus may further include:
and the third sending module is used for sending a configuration information updating request to the discovery network element, wherein the configuration information updating request is used for requesting to update whether information of a federal learning task is willing to be added in the configuration information of the client data analysis functional entity.
In an embodiment of the present disclosure, the federal learning node registration apparatus may further include: a fifth obtaining module, configured to obtain a federal learning service request from a server-side data analysis functional entity, where the federal learning service request includes: the analysis identifier is used for inquiring whether the client data analysis functional entity is willing to join in a federal learning task or not by the federal learning service request;
and the fourth sending module is used for sending a federal learning service request response message to the server-side data analysis functional entity according to the federal learning service request.
Fig. 13 is a schematic structural diagram of a federal learning node discovery apparatus according to an exemplary embodiment of the present disclosure, and as shown in fig. 13, the apparatus 130 includes:
a second sending module 132, configured to send a network function NF discovery request to a discovery network element, where the NF discovery request includes: information whether there is federal learning supporting capability, analysis identity, and NF type;
A second obtaining module 134, configured to obtain an NF discovery request response message returned by the discovery network element.
In an embodiment of the present disclosure, the NF discovery request may further include:
information whether to be added to the federal learning task.
In an embodiment of the present disclosure, the federal learning node discovery apparatus further includes:
a fifth sending module, configured to send a federal learning service request to a first client data analysis functional entity in the discovery request response message, where the federal learning service request is used to query whether the first client data analysis functional entity is willing to join a federal learning task;
and the receiving module is used for receiving the federal learning service request response message returned by the first client data analysis functional entity.
The embodiment of the disclosure also provides an electronic device, including: a processor; and a memory for storing executable instructions of the processor; wherein the processor is configured to perform any one of the federal learning node discovery methods or any one of the federal learning node registration methods provided by embodiments of the present disclosure via execution of the executable instructions.
The embodiment of the disclosure also provides a computer readable storage medium, on which a computer program is stored, which when executed by a processor, implements any one of the federal learning node discovery methods or any one of the federal learning node registration methods provided by the embodiments of the disclosure.
Those skilled in the art will appreciate that the various aspects of the invention may be implemented as a system, method, or program product. Accordingly, aspects of the invention may be embodied in the following forms, namely: an entirely hardware embodiment, an entirely software embodiment (including firmware, micro-code, etc.) or an embodiment combining hardware and software aspects may be referred to herein as a "circuit," module "or" system.
An electronic device 1400 according to such an embodiment of the invention is described below with reference to fig. 14. The electronic device 1400 shown in fig. 14 is merely an example and should not be construed as limiting the functionality and scope of use of embodiments of the present invention.
As shown in fig. 14, the electronic device 1400 is embodied in the form of a general purpose computing device. Components of electronic device 1400 may include, but are not limited to: the at least one processing unit 1410, the at least one memory unit 1420, and a bus 1430 connecting the different system components (including the memory unit 1420 and the processing unit 1410).
Wherein the storage unit stores program code that is executable by the processing unit 1410 such that the processing unit 1410 performs steps according to various exemplary embodiments of the present invention described in the above section of the "exemplary method" of the present specification.
The memory unit 1420 may include readable media in the form of volatile memory units, such as Random Access Memory (RAM) 14201 and/or cache memory 14202, and may further include Read Only Memory (ROM) 14203.
The memory unit 1420 may also include a program/utility 14204 having a set (at least one) of program modules 14205, such program modules 14205 including, but not limited to: an operating system, one or more application programs, other program modules, and program data, each or some combination of which may include an implementation of a network environment.
Bus 1430 may be a local bus representing one or more of several types of bus structures including a memory unit bus or memory unit controller, a peripheral bus, an accelerated graphics port, a processing unit, or using any of a variety of bus architectures.
The electronic device 1400 may also communicate with one or more external devices 1500 (e.g., keyboard, pointing device, bluetooth device, etc.), one or more devices that enable a user to interact with the electronic device 600, and/or any device (e.g., router, modem, etc.) that enables the electronic device 1400 to communicate with one or more other computing devices. Such communication may occur through an input/output (I/O) interface 1450. Also, electronic device 1400 may communicate with one or more networks such as a Local Area Network (LAN), a Wide Area Network (WAN), and/or a public network, such as the Internet, through network adapter 1460. As shown, the network adapter 1460 communicates with other modules of the electronic device 1400 via the bus 1430. It should be appreciated that although not shown, other hardware and/or software modules may be used in connection with electronic device 1400, including, but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, data backup storage systems, and the like.
In an exemplary embodiment of the present disclosure, a computer-readable storage medium having stored thereon a program product capable of implementing the method described above in the present specification is also provided. In some possible embodiments, the various aspects of the invention may also be implemented in the form of a program product comprising program code for causing a terminal device to carry out the steps according to the various exemplary embodiments of the invention as described in the "exemplary methods" section of this specification, when said program product is run on the terminal device.
A program product for implementing the above method according to an embodiment of the present invention is described, which may employ a portable compact disc read-only memory (CD-ROM) and comprise program code and may be run on a terminal device, such as a personal computer. However, the program product of the present invention is not limited thereto, and in this document, a readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.
The program product may employ any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium can be, for example, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples (a non-exhaustive list) of the readable storage medium would include the following: an electrical connection having one or more wires, a portable disk, a hard disk, random Access Memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
The computer readable signal medium may include a data signal propagated in baseband or as part of a carrier wave with readable program code embodied therein. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination of the foregoing. A readable signal medium may also be any readable medium that is not a readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.
Program code embodied on a readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.
Program code for carrying out operations of the present invention may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, C++ or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computing device, partly on the user's device, as a stand-alone software package, partly on the user's computing device, partly on a remote computing device, or entirely on the remote computing device or server. In the case of remote computing devices, the remote computing device may be connected to the user computing device through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computing device (e.g., connected via the Internet using an Internet service provider).
It should be noted that although in the above detailed description several modules or units of a device for action execution are mentioned, such a division is not mandatory. Indeed, the features and functionality of two or more modules or units described above may be embodied in one module or unit in accordance with embodiments of the present disclosure. Conversely, the features and functions of one module or unit described above may be further divided into a plurality of modules or units to be embodied.
Furthermore, although the steps of the methods in the present disclosure are depicted in a particular order in the drawings, this does not require or imply that the steps must be performed in that particular order or that all illustrated steps be performed in order to achieve desirable results. Additionally or alternatively, certain steps may be omitted, multiple steps combined into one step to perform, and/or one step decomposed into multiple steps to perform, etc.
From the above description of embodiments, those skilled in the art will readily appreciate that the example embodiments described herein may be implemented in software, or may be implemented in software in combination with the necessary hardware. Thus, the technical solution according to the embodiments of the present disclosure may be embodied in the form of a software product, which may be stored in a non-volatile storage medium (may be a CD-ROM, a U-disk, a mobile hard disk, etc.) or on a network, including several instructions to cause a computing device (may be a personal computer, a server, a mobile terminal, or a network device, etc.) to perform the method according to the embodiments of the present disclosure.
Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure disclosed herein. This application is intended to cover any adaptations, uses, or adaptations of the disclosure following, in general, the principles of the disclosure and including such departures from the present disclosure as come within known or customary practice within the art to which the disclosure pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the disclosure being indicated by the following claims.
Claims (18)
1. A federal learning node discovery method, comprising:
acquiring a network function NF discovery request from a server-side data analysis functional entity, wherein the NF discovery request is used for requesting to discover a client-side data analysis functional entity which accords with federal learning conditions of the server-side data analysis functional entity;
according to the NF discovery request, a first client data analysis functional entity which accords with federal learning conditions of the server data analysis functional entity is discovered in registered client data analysis functional entities;
and returning the information of the first client data analysis functional entity to the server data analysis functional entity.
2. The method of claim 1, wherein the NF discovery request includes:
information whether there is a capability to support federal learning, an analysis identity, and NF type.
3. The method of claim 2, wherein the NF discovery request further comprises:
information whether to be added to the federal learning task.
4. The method according to claim 1, wherein the method further comprises:
before acquiring a network function NF discovery request from a server data analysis function entity, acquiring a registration request from a second client data analysis function entity, where the registration request is used to request to register configuration information of the second client data analysis function entity, and the configuration information includes: information whether there is federal learning supporting capability, analysis identity, and NF type;
and storing the configuration information.
5. The method of claim 4, wherein the configuration information further comprises:
information whether to be added to the federal learning task.
6. A method according to claim 3, characterized in that the method comprises:
and acquiring a configuration information updating request from the registered client data analysis functional entity, wherein the configuration information updating request is used for requesting to update whether information of whether the registered client data analysis functional entity is willing to join in a federal learning task or not.
7. A federal learning node registration method, comprising:
the method comprises the steps that a client data analysis functional entity sends a registration request to a discovery network element, wherein the registration request is used for requesting to register configuration information of the client data analysis functional entity, and the configuration information comprises the following components: information about whether there is federal learning supporting capability, analysis identity, and network function NF type.
8. The method of claim 7, wherein the configuration information further comprises:
information whether to be added to the federal learning task.
9. The method of claim 7, wherein the method further comprises:
and the client data analysis functional entity sends a configuration information update request to the discovery network element, wherein the configuration information update request is used for requesting to update whether information of whether the client data analysis functional entity is willing to join in a federal learning task or not in the configuration information of the client data analysis functional entity.
10. The method of claim 7, wherein the method further comprises:
acquiring a federal learning service request from a server-side data analysis functional entity, wherein the federal learning service request is used for inquiring whether the client-side data analysis functional entity is willing to join a federal learning task;
And sending a federal learning service request response message to the server-side data analysis functional entity according to the federal learning service request.
11. A federal learning node discovery method, comprising:
sending a network function NF discovery request to a discovery network element, wherein the NF discovery request comprises: information whether there is federal learning supporting capability, analysis identity, and NF type;
and acquiring an NF discovery request response message returned by the discovery network element.
12. The method of claim 11, wherein the NF discovery request further comprises:
information whether to be added to the federal learning task.
13. The method of claim 11, wherein the NF discovery request response message includes information of the first client data analysis function entity, the method further comprising:
sending a federal learning service request to the first client data analysis functional entity, the federal learning service request being used to query whether the first client data analysis functional entity is willing to join a federal learning task;
and receiving a federal learning service request response message returned by the first client data analysis functional entity.
14. A federal learning node discovery apparatus, comprising:
the system comprises a first acquisition module, a second acquisition module and a server-side data analysis function entity, wherein the first acquisition module is used for acquiring a network function NF discovery request from the server-side data analysis function entity, and the NF discovery request is used for requesting to discover a client-side data analysis function entity which accords with federal learning conditions of the server-side data analysis function entity;
the discovery module is used for discovering a first client data analysis functional entity which accords with the federal learning condition of the server data analysis functional entity in the registered client data analysis functional entity according to the NF discovery request;
and the return module is used for returning the information of the first client data analysis functional entity to the server data analysis functional entity.
15. A federal learning node registration apparatus, comprising:
the first sending module is configured to send a registration request to a discovery network element by a client data analysis functional entity, where the registration request is used to request registration of configuration information of the client data analysis functional entity, and the configuration information at least includes: information whether there is a capability to support federal learning.
16. A federal learning node discovery apparatus, comprising:
a second sending module, configured to send a network function NF discovery request to a discovery network element, where the NF discovery request includes: information whether there is federal learning supporting capability, analysis identity, and NF type;
and the second acquisition module is used for acquiring the NF discovery request response message returned by the discovery network element.
17. An electronic device, comprising:
a processor; and
a memory for storing executable instructions of the processor;
wherein the processor is configured to perform the federal learning node discovery method of any one of claims 1-6, 11-13 or the federal learning node registration method of any one of claims 7-10 via execution of the executable instructions.
18. A computer readable storage medium having stored thereon a computer program, wherein the computer program when executed by a processor implements the federal learning node discovery method according to any one of claims 1 to 6, 11 to 13 or the federal learning node registration method according to any one of claims 7 to 10.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210492707.3A CN117062185A (en) | 2022-05-07 | 2022-05-07 | Federal learning node discovery and registration method and device, storage medium and equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210492707.3A CN117062185A (en) | 2022-05-07 | 2022-05-07 | Federal learning node discovery and registration method and device, storage medium and equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117062185A true CN117062185A (en) | 2023-11-14 |
Family
ID=88663247
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210492707.3A Pending CN117062185A (en) | 2022-05-07 | 2022-05-07 | Federal learning node discovery and registration method and device, storage medium and equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117062185A (en) |
-
2022
- 2022-05-07 CN CN202210492707.3A patent/CN117062185A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110413418B (en) | Cache synchronization device and method, cache synchronization system and electronic equipment | |
| CN109547524B (en) | User behavior storage method, device, equipment and storage medium based on Internet of things | |
| CN110493028A (en) | A kind of clustered deploy(ment) method, system, device and computer readable storage medium | |
| CN110996372B (en) | Message routing method, device and system and electronic equipment | |
| CN114745724A (en) | Access processing method and device, electronic equipment and computer readable medium | |
| CN114513552A (en) | Data processing method, device, equipment and storage medium | |
| WO2024109543A1 (en) | Vehicle-to-cloud communication method based on service-oriented architecture, and storage medium | |
| US20240086850A1 (en) | Method, apparatus, device and storage medium for data processing | |
| CN117896241A (en) | DDS software and hardware cooperative transmission method based on FPGA and RapidIO | |
| CN114640657A (en) | Multi-registration center fusion method and device | |
| CN116782345A (en) | Communication method, communication device, storage medium, and electronic apparatus | |
| CN115412993A (en) | Relay discovery method, system, device and storage medium | |
| CN117062185A (en) | Federal learning node discovery and registration method and device, storage medium and equipment | |
| CN111581576A (en) | Development processing method and device based on micro-service and storage medium | |
| CN109962834B (en) | Information processing method, system, terminal and computer storage medium | |
| CN111897887B (en) | Parameter configuration method, device, system, electronic equipment and storage medium | |
| CN113347234A (en) | Network information acquisition method, device, system, computer equipment and storage medium | |
| CN110830600B (en) | Address acquisition method, address sending method and device | |
| CN114996216A (en) | Document processing method, device, equipment and medium based on tree structure | |
| CN114979128A (en) | Cross-region communication method and device and electronic equipment | |
| JP7447339B2 (en) | Communication methods and systems in service management and orchestration | |
| CN112203113B (en) | Video stream structuring method and device, electronic equipment and computer readable medium | |
| US7743385B2 (en) | System and method for simplification of data structure in wireless communications | |
| CN116545777B (en) | User category switching method and device, storage medium and electronic equipment | |
| CN114900519B (en) | Capability calling method, capability calling device, storage medium and electronic equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |