CN113992694A - Block chain link point cluster monitoring method and equipment based on federal learning - Google Patents
Block chain link point cluster monitoring method and equipment based on federal learning Download PDFInfo
- Publication number
- CN113992694A CN113992694A CN202111167018.7A CN202111167018A CN113992694A CN 113992694 A CN113992694 A CN 113992694A CN 202111167018 A CN202111167018 A CN 202111167018A CN 113992694 A CN113992694 A CN 113992694A
- Authority
- CN
- China
- Prior art keywords
- node
- block chain
- cluster
- federal learning
- monitoring
- 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
- 238000012544 monitoring process Methods 0.000 title claims abstract description 49
- 238000000034 method Methods 0.000 title claims abstract description 33
- 230000006399 behavior Effects 0.000 claims abstract description 24
- 230000001360 synchronised effect Effects 0.000 claims abstract description 22
- 238000013461 design Methods 0.000 claims abstract description 17
- 238000012549 training Methods 0.000 claims description 39
- 230000006978 adaptation Effects 0.000 claims description 13
- 238000004891 communication Methods 0.000 claims description 4
- 238000004590 computer program Methods 0.000 claims description 4
- 230000003993 interaction Effects 0.000 claims description 3
- 230000002159 abnormal effect Effects 0.000 abstract description 4
- 238000010586 diagram Methods 0.000 description 5
- 230000000694 effects Effects 0.000 description 3
- 230000002776 aggregation Effects 0.000 description 2
- 238000004220 aggregation Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 230000003044 adaptive effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000015556 catabolic process Effects 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000002955 isolation Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/10—Protocols in which an application is distributed across nodes in the network
- H04L67/104—Peer-to-peer [P2P] networks
- H04L67/1044—Group management mechanisms
-
- 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
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/14—Network analysis or design
- H04L41/145—Network analysis or design involving simulating, designing, planning or modelling of a network
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/14—Network analysis or design
- H04L41/147—Network analysis or design for predicting network behaviour
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L63/00—Network architectures or network communication protocols for network security
- H04L63/04—Network architectures or network communication protocols for network security for providing a confidential data exchange among entities communicating through data packet networks
- H04L63/0407—Network architectures or network communication protocols for network security for providing a confidential data exchange among entities communicating through data packet networks wherein the identity of one or more communicating identities is hidden
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L63/00—Network architectures or network communication protocols for network security
- H04L63/14—Network architectures or network communication protocols for network security for detecting or protecting against malicious traffic
- H04L63/1408—Network architectures or network communication protocols for network security for detecting or protecting against malicious traffic by monitoring network traffic
- H04L63/1416—Event detection, e.g. attack signature detection
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L63/00—Network architectures or network communication protocols for network security
- H04L63/14—Network architectures or network communication protocols for network security for detecting or protecting against malicious traffic
- H04L63/1408—Network architectures or network communication protocols for network security for detecting or protecting against malicious traffic by monitoring network traffic
- H04L63/1425—Traffic logging, e.g. anomaly detection
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L2209/00—Additional information or applications relating to cryptographic mechanisms or cryptographic arrangements for secret or secure communication H04L9/00
- H04L2209/46—Secure multiparty computation, e.g. millionaire problem
Landscapes
- Engineering & Computer Science (AREA)
- Computer Security & Cryptography (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Computer Hardware Design (AREA)
- Theoretical Computer Science (AREA)
- Mathematical Physics (AREA)
- Physics & Mathematics (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- General Physics & Mathematics (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a block chain node cluster monitoring method and equipment based on federal learning, which utilize the characteristic of distributed data node data privacy protection of federal learning, design a synchronous intelligent contract of a federal learning model aiming at node monitoring, and can carry out prediction monitoring on node behaviors in a block chain cluster by means of privacy transaction on the premise of ensuring the privacy safety of node data, giving an illegal abnormal node image, judging the behaviors of the cluster nodes in advance and ensuring the safety of block chain assets. And outputting behavior images such as jitter and legality judgment results of the target block chain nodes through a multi-dimensional image formed by the transaction amount, the transaction object, the consensus condition, the transaction frequency, the broadcasting frequency, the network bandwidth and the like of the nodes.
Description
Technical Field
The invention relates to the technical field of block chains, in particular to a block chain link point cluster monitoring method and equipment based on federal learning.
Background
Block chain technology has been widely used, such as in finance, civil, government, judicial, enterprise, etc. However, the blockchain also faces its own problems and challenges, and there are a large number of node clusters in the blockchain, and some illegal nodes may perform illegal actions in the clusters, which may cause damage to the entire blockchain cluster. A method that can monitor and predict the behavior of blockchain cluster nodes is particularly important.
Federal learning enables each participating mechanism to cooperatively train a machine learning model under the condition that original data are not directly exchanged, and in the existing engineering technology, cooperative training of each mechanism depends on a centralized third-party cooperative node to realize control, aggregation and key management, so that the problems of privacy risks and single-point faults exist.
Disclosure of Invention
The invention aims to provide a block link point cluster monitoring method and equipment based on federal learning, aiming at the defects of the prior art.
In order to achieve the purpose, the invention has the following technical scheme:
the invention provides a block chain link point cluster monitoring method based on federal learning, which comprises the following steps:
in the block chain cluster, each node trains a node monitoring federated learning training model of a local node according to a multidimensional image data set of the local node;
after the local model training is finished, the latest model parameters are sent to a federal learning model synchronous intelligent contract through privacy transaction, the node behavior portrait result is sent to a service contract through privacy transaction, chaining is carried out, and an account book is recorded after consensus;
and synchronizing intelligent contract synchronization model parameters among the block chain nodes through the federal learning model, and triggering the local nodes to update the local model, so that the nodes in the chain are synchronized with the latest nodes to monitor the federal learning training model.
Further, the data dimensions of the multi-dimensional image dataset comprise: the system comprises a transaction object, a transaction amount, transaction time, transaction frequency, transaction times, node broadcasting times, block size, block falling time, consensus time, a consensus signature check result, consensus voting, network load and network communication delay.
Furthermore, the multidimensional image data set is mainly collected from a block chain cluster and used as training data of a node monitoring Federal learning training model, the image data set can be specified through a configuration file, an image data set configuration interface is designed to realize dynamic configuration, and a data set collection interface is designed.
Furthermore, the portrait dataset configuration interface can read configuration files and send configuration information to the block chain nodes through transactions, and after consensus, the node monitoring federal learning training model parameters are updated.
Furthermore, the data collection interface realizes the acquisition of the cluster node monitoring multi-dimensional image data from the block chain cluster.
Further, the design of the federal learning model synchronous intelligent contract comprises the following steps: initializing parameters; receiving the latest model parameters sent by the local node; synchronizing the latest model parameters to each node of the block chain cluster, and triggering each node to update a local model; and querying model parameters.
Further, the design of the business contract comprises: and chaining the node behavior representation results and inquiring the node behavior representation results.
Further, the federated learning training result, namely the block chain cluster node portrait, is stored on the block chain node, and the monitoring result is displayed through the block chain interface adaptation layer.
Furthermore, the adaptation layer is responsible for interaction of the node behavior portrait result and monitoring display of the blockchain cluster nodes, and comprises a server and an adaptation layer interface, wherein the node behavior portrait result is obtained from the blockchain cluster, and then the portrait result is sent to the front end through the server to be displayed on the display layer; the adaptation layer interface comprises: the method comprises the following steps of obtaining a node running condition, obtaining a node multidimensional portrait dataset, obtaining whether a node is attacked or not, obtaining node abnormity early warning information and the like.
Another aspect of the present invention provides a computer apparatus, comprising: a memory and a processor; the memory having stored thereon a computer program executable by the processor; and when the processor runs the computer program, executing the steps of the block link point cluster monitoring method based on the federal learning.
The invention has the beneficial effects that: according to the method, the characteristic of distributed data node data privacy protection by federal learning is utilized, a federal learning model synchronous intelligent contract is designed aiming at node monitoring, and by means of privacy transaction, on the premise that cluster node data is not exchanged, the node behaviors in a block chain cluster can be predicted and monitored while the privacy and the safety of the node data are ensured, illegal abnormal node images are given, the behaviors of the cluster nodes are judged in advance, and the safety of block chain assets is ensured. And outputting behavior images such as jitter and legality judgment results of the target block chain nodes through a multi-dimensional image formed by the transaction amount, the transaction object, the consensus condition, the transaction frequency, the broadcasting frequency, the network bandwidth and the like of the nodes.
Drawings
FIG. 1 is an overall architecture diagram of a block chain node point cluster monitoring method based on federated learning according to the present invention;
FIG. 2 is a flow chart of a block link point cluster monitoring method based on federated learning provided by the present invention;
FIG. 3 is a schematic diagram of a design of a node monitoring federated learning training model provided in an embodiment of the present invention;
FIG. 4 is a schematic diagram of a multi-dimensional image dataset design according to an embodiment of the present invention;
FIG. 5 is a schematic diagram of design of a federated learning model synchronous intelligent contract provided by an embodiment of the present invention;
fig. 6 is a schematic diagram of an adaptation layer design provided in an embodiment of the present invention.
Detailed Description
For better understanding of the technical solutions of the present application, the following detailed descriptions of the embodiments of the present application are provided with reference to the accompanying drawings.
It should be understood that the embodiments described are only a few embodiments of the present application, and not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
The terminology used in the embodiments of the present application is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. As used in the examples of this application and the appended claims, the singular forms "a", "an", and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.
The block link point cluster monitoring method based on the federal learning provided by the invention is structurally shown in fig. 1, and mainly comprises a node monitoring federal learning training model, a synchronous intelligent contract of the federal learning model, an interface adaptation layer and a monitoring display layer.
In the block chain cluster, each node is trained according to the data set of the local node, and the data dimension mainly comprises: the method comprises the steps that a transaction object, a transaction amount, a transaction frequency, a broadcast frequency, a block size, consensus time, a consensus signature check result, consensus voting, block falling time, network load and the like are only executed locally at a node and are not shared by other nodes, privacy and safety of data are guaranteed, and model parameters are uploaded to a federal learning model synchronous intelligent contract after the node of the local node monitors the federal learning training model for training.
By utilizing the characteristic that nodes in a block chain share data, after one node trains a local model and sends the latest model parameters to a federal learning model synchronous intelligent contract through privacy transaction, the updated model parameters are synchronized to other nodes through consensus, and the other nodes perform local synchronization after receiving the relevant parameters of the updated model, so that the synchronization of the federal learning training model is realized.
And storing the federal learning training result to the block chain node, and displaying the monitoring result through the block chain interface adaptation layer.
According to the method, on the premise that the data privacy of each node is guaranteed, the node monitoring federal learning training model is synchronized through an intelligent contract, the behavior portrayal of the block chain cluster nodes is realized, the safe operation of the block chain cluster can be guaranteed, the cluster nodes are predicted to portray, illegal nodes are distinguished in advance, and the safety of the assets on the chain is guaranteed.
As shown in fig. 2, the method of the present invention specifically includes:
1. carrying out multi-dimensional data acquisition on a local node of a block chain, and sending the multi-dimensional data to a node monitoring federal learning training model of the local node for training;
2. after the local model training is finished, sending model parameters to a federal learning model synchronous intelligent contract through private transaction, sending a node behavior portrait result to a service contract through private transaction, carrying out chain linking, and recording an account book after consensus;
3. and synchronously training the models among the nodes of the block chain through a federal learning model synchronous intelligent contract, triggering the local nodes to update the local training models, enabling the nodes in the chain to be synchronous with the latest nodes to monitor the federal learning training models, and displaying the monitoring results through an adaptation layer.
The specific design of each part is described in detail below.
Firstly, designing a node monitoring federal learning training model, as shown in fig. 3, specifically:
1. each participant utilizes a local data training model to send model parameters to a federal learning model synchronous intelligent contract, chains are carried out, and the model parameters are synchronized to each node of a block chain through the federal learning model synchronous intelligent contract;
2. each participant node updates the local model.
In traditional federal learning, distributed model training based on samples can be regarded, all data are distributed to different machines, each machine downloads a model from a server, then the model is trained by using local data, and then parameters needing to be updated are returned to the server; the server aggregates the parameters returned by each machine, updates the model and feeds back the latest model to each machine. The method of performing aggregation model through the central server is prone to a single point of failure risk, for example, when a server node fails or is utilized by an attacker, the whole training system is prone to breakdown. According to the invention, through the combination of federal learning and block chains, and the design of a synchronous intelligent contract, the centralization of convergence of all participants is realized, the single-point fault risk is eliminated, the fault tolerance of the federal learning is improved, meanwhile, the data of all the participants are not shared by utilizing the isolation of the data among the block chain nodes, the data privacy protection is improved, the synchronization of model parameters is realized by utilizing the characteristic of data sharing among the block chain nodes, and the centralization effect is achieved.
Meanwhile, for the block chain cluster, the federal learning is utilized to achieve the training effect of sharing data without data sharing, the training accuracy is greatly improved on the premise of ensuring the data privacy, the cluster node behaviors are well monitored, the safe operation of the whole block chain system is ensured, some abnormal nodes are distinguished, the prediction effect is played, the block chain is prevented from happening in the bud, and the safety of the block chain assets is ensured.
Two, multi-dimensional image dataset design
The multidimensional image data set is mainly collected from a block chain cluster and used as training data of a node monitoring federal learning training model, the image data set can be specified through a configuration file, when different data sets are selected, the monitoring image has different side points, an image data set configuration interface is designed, dynamic configuration can be achieved, and a data set collection interface is designed, as shown in fig. 4.
The multi-dimensional image data set mainly comprises: the system comprises a transaction object, a transaction amount, transaction time, transaction frequency, transaction times, node broadcasting times, block size, block falling time, consensus time, a consensus signature check result, consensus voting, network load, network communication delay and the like.
The related design of the data set interface mainly comprises an image data set configuration interface and a data set acquisition interface.
The portrait dataset configuration interface can read configuration files and send configuration information to the blockchain nodes through transactions, and after consensus, federal learning model parameters are updated.
The data set acquisition interface mainly realizes that cluster node monitoring multi-dimensional image data is acquired from a block chain cluster, and mainly comprises the following steps: the method comprises the steps of obtaining a transaction object interface, obtaining a transaction amount interface, obtaining a transaction time interface, obtaining a transaction frequency interface, obtaining a transaction number interface, obtaining a node broadcast number interface, obtaining a block size interface, obtaining a block falling time interface, obtaining a consensus signature check result interface, obtaining a consensus voting result interface, obtaining a network load interface and obtaining a network communication delay interface.
Synchronous intelligent contract design of three-federal learning model
The contract adopts a privacy transaction mode to ensure the privacy of uplink data of each node, as shown in fig. 5, the contract mainly includes:
initialization: initializing parameters;
receiving a synchronization parameter: receiving model parameters sent by a node;
model synchronization: the system is responsible for synchronizing the latest model parameters to each node and triggering each node to update a local model;
and (3) inquiring model parameters: and (4) inquiring the parameters of the model.
Fourth, business contract design
The main functions of the service contract are to uplink the node behavior portrait of the training result and query the portrait result, and mainly include:
training results and chaining: chaining node behavior portrait results;
and (3) training result query: and inquiring the node behavior portrait result.
Design of adaptive layer
As shown in fig. 6, the system is mainly responsible for interaction between behavior portrait results of blockchain nodes and monitoring display of blockchain cluster nodes, and includes a server program and an adaptation layer interface, where the system acquires user portrait results from a blockchain cluster, and then sends the portrait results to a front end through the server to be displayed on a display layer. The system mainly comprises the following interfaces: the method comprises the steps of obtaining node operation conditions, obtaining a node multidimensional portrait dataset, obtaining whether a node is attacked or not, obtaining node abnormity early warning information and the like.
Sixthly, monitoring display design
The main relevant demonstration of being responsible for node monitoring, draw a portrait display function including front end program, node monitoring, mainly have: displaying the running condition of the cluster nodes, displaying the multi-dimensional image data set of the cluster nodes, displaying whether the cluster nodes attack or not, displaying abnormal early warning information of the cluster nodes and the like.
In one embodiment, a computer device is provided, which includes a memory and a processor, where the memory stores computer readable instructions, and the computer readable instructions, when executed by the processor, cause the processor to execute the steps in the block link point cluster monitoring method based on federal learning in the foregoing embodiments.
In one embodiment, a storage medium storing computer readable instructions is provided, which when executed by one or more processors, cause the one or more processors to perform the steps of the block link point cluster monitoring method based on federated learning in the above embodiments. The storage medium may be a nonvolatile storage medium.
Those skilled in the art will appreciate that all or part of the steps in the methods of the above embodiments may be implemented by associated hardware instructed by a program, which may be stored in a computer-readable storage medium, and the storage medium may include: read Only Memory (ROM), Random Access Memory (RAM), magnetic or optical disks, and the like.
The above description is only for the purpose of illustrating the preferred embodiments of the one or more embodiments of the present disclosure, and is not intended to limit the scope of the one or more embodiments of the present disclosure, and any modifications, equivalent substitutions, improvements, etc. made within the spirit and principle of the one or more embodiments of the present disclosure should be included in the scope of the one or more embodiments of the present disclosure.
Claims (10)
1. A block chain link point cluster monitoring method based on federal learning is characterized by comprising the following steps:
in the block chain cluster, each node trains a node monitoring federated learning training model of a local node according to a multidimensional image data set of the local node;
after the local model training is finished, the latest model parameters are sent to a federal learning model synchronous intelligent contract through privacy transaction, the node behavior portrait result is sent to a service contract through privacy transaction, chaining is carried out, and an account book is recorded after consensus;
and synchronizing intelligent contract synchronization model parameters among the block chain nodes through the federal learning model, and triggering the local nodes to update the local model, so that the nodes in the chain are synchronized with the latest nodes to monitor the federal learning training model.
2. A block-link point cluster monitoring method based on federal learning as claimed in claim 1, wherein the data dimensions of the multi-dimensional image dataset include: the system comprises a transaction object, a transaction amount, transaction time, transaction frequency, transaction times, node broadcasting times, block size, block falling time, consensus node signature and signature checking results, consensus voting, network load and network communication delay.
3. The method for monitoring the block chain link point cluster based on the federal learning of claim 1, wherein the multidimensional image data set is mainly collected from the block chain cluster and used as a node to monitor the training data of the federal learning training model, the image data set can be specified through a configuration file, an image data set configuration interface is designed to realize dynamic configuration, and a data set collection interface is designed.
4. A block link point cluster monitoring method based on federated learning as defined in claim 4, wherein the image dataset configuration interface can read configuration files and send configuration information to block link nodes through transactions, and after consensus, the nodes will be updated to monitor federated learning training model parameters.
5. The method for monitoring a blockchain link point cluster based on federated learning as recited in claim 4, wherein the data set collection interface implements acquisition of cluster node monitoring multi-dimensional image data from a blockchain cluster.
6. A block link point cluster monitoring method based on federal learning as claimed in claim 1, wherein the design of the federal learning model synchronous intelligent contract comprises: initializing parameters; receiving the latest model parameters sent by the local node; synchronizing the latest model parameters to each node of the block chain cluster, and triggering each node to update a local model; and querying model parameters.
7. A block link point cluster monitoring method based on federal learning as claimed in claim 1, wherein the design of the service contract comprises: and chaining the node behavior representation results and inquiring the node behavior representation results.
8. The method for monitoring the block chain link point cluster based on the federal learning as claimed in claim 1, wherein the federal learning training result, namely the block chain cluster node portrait, is stored on the block chain node, and the monitoring result is displayed through a block chain interface adaptation layer.
9. The method for monitoring the block chain link point cluster based on the federal study is characterized in that the adaptation layer is responsible for interaction of the node behavior portrait result and monitoring and displaying of the block chain cluster nodes and comprises a server and an adaptation layer interface, wherein the node behavior portrait result is obtained from the block chain cluster, and then the portrait result is sent to the front end through the server to be displayed on the display layer; the adaptation layer interface comprises: the method comprises the following steps of obtaining a node running condition, obtaining a node multidimensional portrait dataset, obtaining whether a node is attacked or not, obtaining node abnormity early warning information and the like.
10. A computer device, comprising: a memory and a processor; the memory having stored thereon a computer program executable by the processor; the processor, when executing the computer program, performs the method of any of claims 1 to 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111167018.7A CN113992694A (en) | 2021-10-01 | 2021-10-01 | Block chain link point cluster monitoring method and equipment based on federal learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111167018.7A CN113992694A (en) | 2021-10-01 | 2021-10-01 | Block chain link point cluster monitoring method and equipment based on federal learning |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113992694A true CN113992694A (en) | 2022-01-28 |
Family
ID=79737603
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111167018.7A Pending CN113992694A (en) | 2021-10-01 | 2021-10-01 | Block chain link point cluster monitoring method and equipment based on federal learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113992694A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114818011A (en) * | 2022-06-27 | 2022-07-29 | 国网智能电网研究院有限公司 | Federal learning method and system suitable for carbon credit evaluation and electronic equipment |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111666460A (en) * | 2020-05-27 | 2020-09-15 | 中国平安财产保险股份有限公司 | User portrait generation method and device based on privacy protection and storage medium |
| CN111698322A (en) * | 2020-06-11 | 2020-09-22 | 福州数据技术研究院有限公司 | Medical data safety sharing method based on block chain and federal learning |
| CN112329940A (en) * | 2020-11-02 | 2021-02-05 | 北京邮电大学 | Personalized model training method and system combining federal learning and user portrait |
| CN112631605A (en) * | 2020-12-31 | 2021-04-09 | 深圳前海微众银行股份有限公司 | Code compiling method, device, equipment and storage medium of federal learning model |
| CN112949760A (en) * | 2021-03-30 | 2021-06-11 | 平安科技（深圳）有限公司 | Model precision control method and device based on federal learning and storage medium |
| CN113408746A (en) * | 2021-06-22 | 2021-09-17 | 深圳大学 | Block chain-based distributed federal learning method and device and terminal equipment |
-
2021
- 2021-10-01 CN CN202111167018.7A patent/CN113992694A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111666460A (en) * | 2020-05-27 | 2020-09-15 | 中国平安财产保险股份有限公司 | User portrait generation method and device based on privacy protection and storage medium |
| CN111698322A (en) * | 2020-06-11 | 2020-09-22 | 福州数据技术研究院有限公司 | Medical data safety sharing method based on block chain and federal learning |
| CN112329940A (en) * | 2020-11-02 | 2021-02-05 | 北京邮电大学 | Personalized model training method and system combining federal learning and user portrait |
| CN112631605A (en) * | 2020-12-31 | 2021-04-09 | 深圳前海微众银行股份有限公司 | Code compiling method, device, equipment and storage medium of federal learning model |
| CN112949760A (en) * | 2021-03-30 | 2021-06-11 | 平安科技（深圳）有限公司 | Model precision control method and device based on federal learning and storage medium |
| CN113408746A (en) * | 2021-06-22 | 2021-09-17 | 深圳大学 | Block chain-based distributed federal learning method and device and terminal equipment |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114818011A (en) * | 2022-06-27 | 2022-07-29 | 国网智能电网研究院有限公司 | Federal learning method and system suitable for carbon credit evaluation and electronic equipment |
| CN114818011B (en) * | 2022-06-27 | 2022-09-27 | 国网智能电网研究院有限公司 | Federal learning method and system suitable for carbon credit evaluation and electronic equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112001502B (en) | Federal learning training method and device for high-delay network environment robustness | |
| CN103812849B (en) | A kind of local cache update method, system, client and server | |
| CN106610854A (en) | Model update method and device | |
| CN106095869A (en) | Advertisement information processing method, subscriber equipment, background server and system | |
| CN112235323B (en) | Evidence obtaining method and device based on block chain, electronic equipment and readable storage medium | |
| CN107690077A (en) | The method and apparatus for monitoring net cast interim card | |
| CN109905492B (en) | Safety operation management system and method based on distributed modular data center | |
| CN108369550B (en) | Real-time alteration of data from different sources | |
| CN109669795A (en) | Crash info processing method and processing device | |
| CN105338564B (en) | A kind of client adaptation method, client, server and system | |
| CN110162334A (en) | A kind of code administration method, apparatus, storage medium and computer program product | |
| CN113992694A (en) | Block chain link point cluster monitoring method and equipment based on federal learning | |
| CN111010429B (en) | Method and system for managing equipment running state based on platform of Internet of things | |
| JP6587370B1 (en) | Document management system | |
| CN112448923A (en) | Information sharing method, device, system, electronic device and storage medium | |
| CN103399776A (en) | Creation method and system for reusable MOCK | |
| CN104219272B (en) | Buffering updating method, terminal and system | |
| CN111092935B (en) | Data sharing method and virtual training device for machine learning | |
| CN107633026A (en) | Data syn-chronization abnormality eliminating method, device and server | |
| CN109561127A (en) | Method, equipment and the computer-readable medium synchronous for the data in software defined network | |
| CN109696316B (en) | Train remote monitoring system | |
| CN109344073A (en) | Application software testing method, apparatus, computer equipment and storage medium | |
| CN104468505A (en) | Safety audit log playing method and device | |
| CN112306788A (en) | Program dynamic monitoring method and device | |
| CN109614429A (en) | The method for realizing application access and database access behavior relevancy based on kernel-driven |
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 |