CN110287268A - A kind of digital asset processing method and system based on block chain - Google Patents
A kind of digital asset processing method and system based on block chain Download PDFInfo
- Publication number
- CN110287268A CN110287268A CN201910581679.0A CN201910581679A CN110287268A CN 110287268 A CN110287268 A CN 110287268A CN 201910581679 A CN201910581679 A CN 201910581679A CN 110287268 A CN110287268 A CN 110287268A
- Authority
- CN
- China
- Prior art keywords
- digital asset
- information
- data
- algorithm
- block chain
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2465—Query processing support for facilitating data mining operations in structured databases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/27—Replication, distribution or synchronisation of data between databases or within a distributed database system; Distributed database system architectures therefor
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
-
- 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
- H04L63/0428—Network architectures or network communication protocols for network security for providing a confidential data exchange among entities communicating through data packet networks wherein the data content is protected, e.g. by encrypting or encapsulating the payload
- H04L63/0442—Network architectures or network communication protocols for network security for providing a confidential data exchange among entities communicating through data packet networks wherein the data content is protected, e.g. by encrypting or encapsulating the payload wherein the sending and receiving network entities apply asymmetric encryption, i.e. different keys for encryption and decryption
-
- 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
- H04L67/1097—Protocols in which an application is distributed across nodes in the network for distributed storage of data in networks, e.g. transport arrangements for network file system [NFS], storage area networks [SAN] or network attached storage [NAS]
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L9/00—Cryptographic mechanisms or cryptographic arrangements for secret or secure communications; Network security protocols
- H04L9/06—Cryptographic mechanisms or cryptographic arrangements for secret or secure communications; Network security protocols the encryption apparatus using shift registers or memories for block-wise or stream coding, e.g. DES systems or RC4; Hash functions; Pseudorandom sequence generators
- H04L9/0643—Hash functions, e.g. MD5, SHA, HMAC or f9 MAC
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Computer Security & Cryptography (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- General Physics & Mathematics (AREA)
- Probability & Statistics with Applications (AREA)
- Computing Systems (AREA)
- Fuzzy Systems (AREA)
- Artificial Intelligence (AREA)
- Computer Hardware Design (AREA)
- Software Systems (AREA)
- Computational Linguistics (AREA)
- Power Engineering (AREA)
- Life Sciences & Earth Sciences (AREA)
- Mathematical Physics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
A kind of digital asset treating method and apparatus based on block chain, the described method comprises the following steps: (S1) receives digital asset information；A variety of different digital asset information are received, and information fusion is carried out to the digital asset information；(S2) digital asset information processing；In all digital asset fuse informations, classified using data mining algorithm to the digital asset received, and sorted digital asset information is stored, while improving the precision of sorted information using data mining algorithm again；(S3) it is further processed using algorithm of the ant group algorithm to classification output, seeks optimal digital asset information；(S4) by treated, data pass through Encryption Algorithm, algorithm etc. of knowing together uploads to block chain；(S5) user obtains digital asset information by block chain.The present invention can efficiently solve the inconvenient technology drawback of traditional data assets information screening, and required data are found from mass digital assets information data, and the data are encrypted by block chain, transmits, is shared.
Description
Technical field
The present invention relates to block chain technical fields, and relate more specifically to a kind of digital asset processing side based on block chain
Method and system.
Background technique
Digital asset (Digital assets) refers to enterprise or individual possesses or what is controlled exists with spreadsheet format
, hold in daily activities, in case sell or the non-monetary asset in production process.The security performance of digital asset
Determine the life of people's items, production activity.With the development of communication technology, the various communication technologys gradually penetrate into digital processing
In technology.Block chain due to decentralization, openly, transparent, the advantages that can not distorting be applied to the various occasions of data processing
In, it can be realized different business demands in the block platform chain with different blocks chain node.
With the continuous development of block chain technology, block chain technological penetration to every field, such as bank, hospital, enterprise,
Finance etc., since the digital asset information content of various industries is bigger, digital asset message structure is distributed more scattered, Yong Hu
In use process, a large amount of digital asset information data is caused to transfer difficulty, it is difficult to look for from mass digital assets information data
It to required data, and realizes the permanent storage of required data, makes the use suffering of digital asset information data, and safe
Property is poor.
Summary of the invention
In view of the deficiencies of the prior art, the present invention discloses a kind of digital asset processing method and system based on block chain,
The inconvenient technology drawback of traditional data assets information screening can be efficiently solved, convenient for from mass digital assets information data
Find required data, and by the data by block chain encryption, transmission, shared, make user fast implement data identification and
Sharing, the present invention have been had the advantage that using block chain: mutual reliability is high, data can not distort, dates back, interconnects mutually
Logical, distributed storage, decentralization etc..
The invention adopts the following technical scheme:
A kind of digital asset processing method based on block chain, comprising the following steps:
(S1) digital asset information is received；A variety of different digital asset information are received, and letter is carried out to the digital asset information
Breath fusion；
(S2) digital asset information processing；In all digital asset fuse informations, using data mining algorithm to receiving
Digital asset classify, and sorted digital asset information is stored, while using data mining algorithm again
Improve the precision of sorted information；
(S3) it is further processed using algorithm of the ant group algorithm to classification output, seeks optimal digital asset information；
(S4) by treated, data pass through Encryption Algorithm, algorithm etc. of knowing together uploads to block chain；
(S5) user obtains digital asset information by block chain.
As the further technical solution of the present invention, the step of the digital asset information processing are as follows:
(S21) the digital asset information is divided by same attribute using the sorting algorithm in the data mining algorithm
Class screens user from a large amount of information identical digital asset information according to categorical attribute；
(S22) the sorted digital asset information of the sorting algorithm is further learnt again using ant group algorithm, realizes number
The accurate processing of assets information obtains more accurate data.
As the further technical solution of the present invention, the sorting algorithm is any one in following algorithm: decision tree
Algorithm, Cluster Classification algorithm, BP neural network algorithm, algorithm of support vector machine, VSM method, Bayes Piao sorting algorithm or k- are close
Adjacent element algorithm.
As the further technical solution of the present invention, the Cluster Classification algorithm is K-means clustering algorithm, wherein described
The step of K-means clustering algorithm are as follows:
(1) sample data is chosen in mass digital assets information, and is selected in initial cluster according to selected sample data
Heart point, in sample data, the digital assets information data of random extraction K, using the digital asset information as sample number of clusters
According to the center of set, and the threshold value T of the number of iterations is set, wherein K > 50,0 < T < 10；
(2) digital asset message sample cluster point is divided, the point of each digital asset message sample aggregate of data is divided into following number
In the point of word assets information sample cluster:
The point of cluster represented by the center nearest apart from the digital asset message sample, make the digital asset message sample with
The central point that the central point of initial cluster is nearest is divided into one kind；
Wherein, the distance between the nearest center of the digital asset message sample and the represented point of cluster formula are as follows:
d；
Wherein x, y respectively indicate different digital asset message samples, and n indicates the dimension of digital asset message sample, d(x, y)
Each digital asset is calculated according to the central point of the cluster sample of each digital asset message sample for Euclidean distance
The distance between message sample and these central sample parameters, and according to minimum range by corresponding digital asset message sample
Re-start division；
(3) digital asset information sample is indicated with the central point at each sample number strong point in different digital assets information sample cluster
The central point of this sample cluster calculates every again according to the central point of different parameters data or different clustering information sample datas
A number the distance between assets information sample data central point and these clustering information data centers, and according to minimum range
Again division is re-started to respective digital assets sample data, calculated minimum data will forms matrix D every time, then are as follows:
；
Wherein, x is the set of the minimum value found out；
(4) it judges whether to iterate to calculate, if the number of iterations is equal to given threshold T, does not have to iterative calculation, if iteration
Number is not identical as given threshold, then repartitions digital asset message sample cluster point, and return step (2) repeats step
(2) and (3).
As the further technical solution of the present invention, in BP neural network algorithm calculating, in which:
Adjust the formula of output layer power system are as follows:
;
Adjust the formula of hidden layer weight coefficient are as follows:
For the accurate function model of quadratic form of the input pattern pair in each digital asset message sample are as follows:
;
For total accurate function expression of N number of digital asset message sample:
。
As the further technical solution of the present invention, the step of the ant group algorithm are as follows:
(1) it initializes；By the digital asset information initializing of block chain, the total group y(t of initialization of digital asset information is chosen),
If y(t)=ymax, enable digital asset information as ant element, when initial, all elements of ant matrix of elements are initialized as 0,
Then the initial position of the ant element is randomly choosed；
(2) m ant element is randomly placed in n position, if the cycle-index that the ant element finds path is Nc, press
Nc+ 1 sequence is recycled；
(3) ant element taboo list call number k=1 is set, is recycled by k+1；
(4) state transition probability formula according to the following formula calculates the probability of ant selection position j；
；
Wherein, δ is visibility factor, and the visibility factor indicates that the inverse of the distance between different location, α are that pheromones are dense
Spend relatively important parameter, β is the relatively important index of visibility factor, Node be connected directly with position i and ant element still
The set of unbeaten position；
(5) selection has the position of maximum rating transition probability, ant element is moved to described general with maximum rating transfer
The position of rate, and the position is logged into taboo list；
(6) judge, if having accessed all positions in set, enable k < m, wherein m is the number of position, then is executed by k+1
Circulate operation updates the information content in each path if not accessed all positions in set；
(7) it checks termination condition, checks whether and meet termination condition, the termination condition is that ant selects the probability of position j big
In 80%, if meeting the termination condition, further operating is carried out；
(8) judge whether to form new group, if the termination condition is that ant selects the probability of position j less than 80%,
New group is formed, then Pheromone Matrix is updated again, the method for update is to recalculate minimum data matrix D；
(9) judge whether to meet and terminate genetic condition, when meeting termination genetic condition, the termination genetic condition is the ant
Ant selects the probability of position j to be greater than 80%, then exports calculated result.
The present invention also uses following technical scheme:
A kind of digital asset device based on block chain, described device include:
Client receives a variety of different digital asset information, and to the digital asset information for receiving digital asset information
Carry out information fusion；
Assets information processing system is used for digital asset information processing, according to data fusion information, to the data information received
Classify, and sorted information is stored, while using data mining algorithm to the essence for improving sorted information
Degree, and be further processed by ant group algorithm model using algorithm of the ant group algorithm to classification output, seek optimal number money
Produce information；
Block platform chain handles information for receiving treated digital asset, and to treated data carry out Encryption Algorithm,
Common recognition algorithm；
Node server makes user obtain digital asset information by block chain.
As the further technical solution of the present invention, the client be integrated with user log-in block, information management module,
Data inquiry module or quota control module, wherein the user log-in block is for making user obtain digital asset information；Institute
Information management module is stated for being arranged, transferring the digital asset information；The data inquiry module is for inquiring the number
Assets information, the quota control module are used to manage the capacity of the digital asset information.
As the further technical solution of the present invention, the assets information processing system includes data receipt unit, data
Acquiring unit, data storage cell, taxon and ant group algorithm model, wherein the output end of the data receipt unit and institute
State the input terminal connection of data capture unit, the data receipt unit, data capture unit, data storage cell, grouping sheet
Member and ant group algorithm model are connect with data storage cell, and the output end of the taxon is defeated with the ant group algorithm model
Enter end connection；Wherein:
The data receipt unit is used for for obtaining digital asset information, the data capture unit from the data receiver list
Member extract digital asset sample data, the data storage cell for store the data receipt unit, data capture unit,
Taxon or ant group algorithm mode input or input information, the taxon are used for the digital asset information according to institute
The categorical attribute for stating taxon setting is sorted out, and the ant group algorithm model is used for the number for exporting the taxon
Assets information advanced optimizes.
As the further technical solution of the present invention, the block platform chain is the mould based on Hyperledger Fabric
Block block chain solution support platform.
Positive beneficial effect:
The present invention can efficiently solve the inconvenient technology drawback of traditional data assets information screening, from mass digital assets information
Required data are found in data, and the data are encrypted by block chain, transmission, are shared, and the present invention has had the advantage that: mutually
Reliability is high, data can not be distorted, dates back, be interconnected, distributed storage, decentralization etc.；
The present invention realizes the classification of various different data assets informations by using data mining algorithm so that user rapidly from
Attribute needed for immense data obtain user according to the attribute of setting, improves the ability of user's garbled data assets information；
The present invention improves the ability of the data assets information on screening different blocks chain network path by ant group algorithm model,
It is quickly found out data assets information capability；
The present invention is by using algorithm of knowing together in block chain, Encryption Algorithm, asymmetric encryption, hash algorithm, intelligent contract sum number
Word signature etc. guarantees the safety of data, to realize the data interaction between different user and block chain node.
Detailed description of the invention
Fig. 1 is the schematic diagram of block chain digital asset processing method of the present invention；
Fig. 2 is block chain digital asset processing method algorithm schematic diagram of the present invention；
Fig. 3 is K-means clustering algorithm schematic diagram in block chain digital asset processing method algorithm of the present invention；
Fig. 4 is ant group algorithm flow chart in block chain digital asset processing method algorithm of the present invention；
Fig. 5 is block chain digital asset processing device structure diagram of the present invention；
Fig. 6 is block chain block diagram in block chain digital asset processing unit of the present invention；
Fig. 7 is block platform chain structural schematic diagram in block chain digital asset processing unit of the present invention；
Fig. 8 is block chain network node schematic diagram in block chain digital asset processing unit of the present invention.
Specific embodiment
Hereinafter, preferred embodiments of the present invention will be described with reference to the accompanying drawings, it should be understood that embodiment described herein
Only for the purpose of illustrating and explaining the present invention and is not intended to limit the present invention.
Embodiment 1
As Figure 1-Figure 4, a kind of digital asset processing method based on block chain, comprising the following steps:
(S1) digital asset information is received；
In this step, a variety of different digital asset information are received, and information fusion is carried out to the digital asset information.In reality
Body assets and equity assets are really weighed in a manner of centralization, such as real estate management center, bank, stock exchange etc., different
A large amount of data are generated in industry.Block chain technology is used to carry out the ownership of digital asset, is digital asset and block chain skill
Art developing direction, for large-scale outbreak and the control for preventing digital asset, it is necessary to use block chain technology.
(S2) digital asset information processing；
In all digital asset fuse informations, classified using data mining algorithm to the digital asset received, and
Sorted digital asset information is stored, while improving the essence of sorted information using data mining algorithm again
Degree.Data mining algorithm is according to one group of heuristic of data creation data mining model and calculating.Data mining generally refers to
The process of wherein information is hidden in by algorithm search from a large amount of data.It is usually related with computer science, and passes through
All multi-methods such as statistics, online analysis and processing, information retrieval, machine learning, expert system and pattern-recognition realize above-mentioned mesh
Mark.When the present embodiment is calculated using the algorithm, the arrangement of data prediction is contained, pretreatment is able to use family and obtains
More pure data, do not elaborate herein.When being calculated using data mining algorithm, following step is generally included
It is rapid:
(S21) the digital asset information is divided by same attribute using the sorting algorithm in the data mining algorithm
Class screens user from a large amount of information identical digital asset information according to categorical attribute；In this step, energy
It is enough that digital asset information is carried out to preliminary processing.
(S22) the sorted digital asset information of the sorting algorithm is further learnt again using ant group algorithm, is realized
The accurate processing of digital asset information obtains more accurate data.
Through the above steps, the classification of data is realized, so that user is rapidly from immense data according to the attribute of setting
Attribute needed for obtaining user improves the ability of user's garbled data assets information.
In the present embodiment, the sorting algorithm is any one in following algorithm: decision Tree algorithms, Cluster Classification are calculated
Method, BP neural network algorithm, algorithm of support vector machine, VSM method, Bayes Piao sorting algorithm or k- neighbour's element algorithm.
Select algorithms of different to can be realized different screenings, in the present embodiment to clustering algorithm and BP neural network algorithm into
Row explanation, is described more fully below.
The Cluster Classification algorithm is K-means clustering algorithm, wherein the step of K-means clustering algorithm are as follows:
(1) sample data is chosen in mass digital assets information, and is selected in initial cluster according to selected sample data
Heart point, in sample data, the digital assets information data of random extraction K, using the digital asset information as sample number of clusters
According to the center of set, and the threshold value T of the number of iterations is set, wherein K > 50,0 < T < 10；
(2) digital asset message sample cluster point is divided, the point of each digital asset message sample aggregate of data is divided into following number
In the point of word assets information sample cluster:
The point of cluster represented by the center nearest apart from the digital asset message sample, make the digital asset message sample with
The central point that the central point of initial cluster is nearest is divided into one kind；
Wherein, the distance between the nearest center of the digital asset message sample and the represented point of cluster formula are as follows:
；
Wherein x, y respectively indicate different digital asset message samples, and n indicates the dimension of digital asset message sample, d(x, y)
Each digital asset is calculated according to the central point of the cluster sample of each digital asset message sample for Euclidean distance
The distance between message sample and these central sample parameters, and according to minimum range by corresponding digital asset message sample
Re-start division；
(3) digital asset information sample is indicated with the central point at each sample number strong point in different digital assets information sample cluster
The central point of this sample cluster calculates every again according to the central point of different parameters data or different clustering information sample datas
A number the distance between assets information sample data central point and these clustering information data centers, and according to minimum range
Again division is re-started to respective digital assets sample data, calculated minimum data will forms matrix D every time, then are as follows:
Wherein, x is the set of the minimum value found out；
(4) it judges whether to iterate to calculate, if the number of iterations is equal to given threshold T, does not have to iterative calculation, if iteration
Number is not identical as given threshold, then repartitions digital asset message sample cluster point, and return step (2) repeats step
(2) and (3).
As the further technical solution of the present invention, in BP neural network algorithm calculating, in which:
Adjust the formula of output layer power system are as follows:
;
Adjust the formula of hidden layer weight coefficient are as follows:
For the accurate function model of quadratic form of the input pattern pair in each digital asset message sample are as follows:
;
For total accurate function expression of N number of digital asset message sample:
。
In above-mentioned formula, neuron in parameters neural network, it is specific as shown in Figure 2.
(S3) it is further processed using algorithm of the ant group algorithm to classification output, seeks optimal digital asset information；Into
When row ant colony calculates, the step of the ant group algorithm are as follows:
(1) it initializes；By the digital asset information initializing of block chain, the total group y(t of initialization of digital asset information is chosen),
If y(t)=ymax, enable digital asset information as ant element, when initial, all elements of ant matrix of elements are initialized as 0,
Then the initial position of the ant element is randomly choosed；
(2) m ant element is randomly placed in n position, if the cycle-index that the ant element finds path is Nc, press
Nc+ 1 sequence is recycled；
(3) ant element taboo list call number k=1 is set, is recycled by k+1；
(4) state transition probability formula according to the following formula calculates the probability of ant selection position j；
；
Wherein, δ is visibility factor, and the visibility factor indicates that the inverse of the distance between different location, α are that pheromones are dense
Spend relatively important parameter, β is the relatively important index of visibility factor, Node be connected directly with position i and ant element still
The set of unbeaten position；
(5) selection has the position of maximum rating transition probability, ant element is moved to described general with maximum rating transfer
The position of rate, and the position is logged into taboo list；
(6) judge, if having accessed all positions in set, enable k < m, wherein m is the number of position, then is executed by k+1
Circulate operation updates the information content in each path if not accessed all positions in set；
(7) it checks termination condition, checks whether and meet termination condition, the termination condition is that ant selects the probability of position j big
In 80%, if meeting the termination condition, further operating is carried out；
(8) judge whether to form new group, if the termination condition is that ant selects the probability of position j less than 80%,
New group is formed, then Pheromone Matrix is updated again, the method for update is to recalculate minimum data matrix D；
(9) judge whether to meet and terminate genetic condition, when meeting termination genetic condition, the termination genetic condition is the ant
Ant selects the probability of position j to be greater than 80%, then exports calculated result.(S4) by treated, data pass through Encryption Algorithm, common recognition
Algorithm etc. uploads to block chain；
In this step, common recognition algorithm, Encryption Algorithm, asymmetric encryption, hash algorithm, intelligent contract and number label are also used
Name etc. guarantees the safety of data, to realize the data interaction between different user and block chain node.
The original design intention of intelligent contract is to create flexibly controllable intellectual capital, but due to the limitation of technology development and lack
Weary actual application scenarios.The appearance of block chain greatly enriches and has developed intelligent contract technology, block chain intelligence contract quilt
It is defined as a kind of computer program, which can execute automatically after deployment success, keep block catenary system flexible
Programming and operation data.Rivest, shamir, adelman refers to uses the one of different code keys during data are encrypted and decrypted
Kind Encryption Algorithm.Public private key pair used in asymmetric encryption procedure, wherein public key is mainly used for encryption and external disclosure, and
Private key is mainly used for decrypting and is secrecy.Hash algorithm is also known as secure hash algorithm (Secure Hash
Algorithm, abbreviation SHA), major function is that the information input of random length is converted to the information output of regular length,
Obtain eap-message digest.The main feature of hash algorithm include: the data processing of 1) hash algorithm be it is unidirectional, according to output valve
Almost impossible retrospectively calculate goes out input value；2) the data costs time of identical hash algorithm processing different length is identical and result
Length it is also identical；3) its output result of identical input information is identical, as long as but have a byte difference in input,
Output result is also completely different and result between there is no any association.Digital signature is asymmetric encryption techniques and eap-message digest skill
The integrated application of art, its basic principle are the proofs as identity of the sender plus a segment information behind data cell
(S5) user obtains digital asset information by block chain, so that data is shared.
Embodiment 2
With reference to figure 5-8, a kind of digital asset device based on block chain, described device includes:
Client receives a variety of different digital asset information, and to the digital asset information for receiving digital asset information
Carry out information fusion；
Assets information processing system is used for digital asset information processing, according to data fusion information, to the data information received
Classify, and sorted information is stored, while using data mining algorithm to the essence for improving sorted information
Degree, and be further processed by ant group algorithm model using algorithm of the ant group algorithm to classification output, seek optimal number money
Produce information；
Block platform chain handles information for receiving treated digital asset, and to treated data carry out Encryption Algorithm,
Other algorithms such as common recognition algorithm；
Node server makes user obtain digital asset information by block chain, in a particular embodiment, generally includes but office
It is limited to business data block chain node, bank data block chain node or finance data block chain node.Pass through node server
Shared assets information is obtained from block platform chain.
In the above-described embodiments, client described in reference diagram 6 is integrated with user log-in block, information management module, data
Enquiry module or quota control module, wherein the user log-in block is for making user obtain digital asset information；The letter
Breath management module is for being arranged, transferring the digital asset information；The data inquiry module is for inquiring the digital asset
Information, the quota control module are used to manage the capacity of the digital asset information.
In the above-described embodiments, it is referred to as multi-party common maintenance with reference to Fig. 6 block chain, decentralization, can be traced, can not usurp
The distributed data base changed is the computer technologies such as Distributed Storage, point-to-point transmission, common recognition mechanism, Encryption Algorithm
New application mode.Request data in regular period can be packaged into a data block by cryptological technique
(block), a kind of chain structure and using Hash fingerprint by it is connected into sequentially in time to store.Data block is usual
It is made of block head and block body two parts.Wherein, block head is commonly stored the Hash of the version number of system, a upper block
The data such as value, merkle root and timestamp, and detailed request data is then contained in block body.By taking bit coin as an example, it
It also stores in addition to that information in block head and digs the data such as mining random number, what is stored in block body is exactly specific hand over
Easy data.
In the above-described embodiments, assets information processing system described in reference diagram 5 includes data receipt unit, data acquisition list
Member, data storage cell, taxon and ant group algorithm model, wherein the output end of the data receipt unit and the data
The input terminal of acquiring unit connects, the data receipt unit, data capture unit, data storage cell, taxon and ant
Group's algorithm model is connect with data storage cell, and the input terminal of the output end of the taxon and the ant group algorithm model connects
It connects；Wherein:
The data receipt unit is used for for obtaining digital asset information, the data capture unit from the data receiver list
Member extract digital asset sample data, the data storage cell for store the data receipt unit, data capture unit,
Taxon or ant group algorithm mode input or input information, the taxon are used for the digital asset information according to institute
The categorical attribute for stating taxon setting is sorted out, and the ant group algorithm model is used for the number for exporting the taxon
Assets information advanced optimizes.
In the above-described embodiments, block platform chain described in reference diagram 7 is the modularization based on Hyperledger Fabric
Block chain solution support platform.Fabric platform is a kind of alliance's chain framework, supports intelligent contract technology, system operation
It independent of token, and can support about hundred transaction handling capacities per second, substantially meet and counted between mechanism, alliance
Demand of the word assets across institutional network.In addition, Fabric is using modularization framework, wherein common recognition algorithm etc. can be made
It selects to use for user for a pluggable module.It is able to use family and carries out weight to particular module according to self-demand simultaneously
It newly designs and develops, thus selects block chain basic platform of the Fabric as digital asset transaction system herein.Fabric master
Will comprising member service module (Membership Services), block chain service module (Blockchain Services) and
Chain code service module (Chaincode Services).Wherein member service module mainly provides member registration, Identity Management
With the functions such as transaction vetting, passes through certificate of registry issuing organization (ECA) and transaction authentication center (TCA) carries out institute registration certification
And transaction authentication.Block chain service module is mainly responsible for point-to-point communication, common recognition and storage of account book data between node etc..
Chain code service module provides intelligent bond service, provides safe contract running environment etc..Meanwhile the platform passes through through each
Flow of event (Event Stream) between a component realizes asynchronous communication.
It in the above-described embodiments, further include so that various industries such as bank, enterprise and finance with reference to Fig. 8 block chain network
By block chain network in the interactive business data block chain node of the enterprising row information of block platform chain, bank data block chain link
Point, finance data block chain node, can be with setting information transit node in block chain.And block chain node connects in chain-type
It connects, block chain node is mutual by business data block chain node, bank data block chain node or finance data block chain node
It connects, makes using digital asset treated data sharing.
In the above-described embodiments, it can be realized contract upload with reference to Fig. 7 and Fig. 8 super keepe, contract deployment, dispose and go through
The functions such as history inquiry, mechanism and user's registration.The function of organization administrator mainly realizes that user's assets are supplemented with money, transactions history is looked into
The functions such as inquiry, digital asset distribution, exchange rate management, structural capital is supplemented with money, assets information is safeguarded, assets information record of conversion.And
Ordinary user is merely capable of realizing the functions such as user's registration login, digital asset transaction, commodity exchange.Data management has safety
The characteristics of property, accuracy and flexibility.Finally, the function and performance to block chain digital asset transaction system totality are surveyed
Examination.Test result shows that system can be realized contract deployment, institute registration, assets distribution, transaction in assets and commodity exchange etc.
Basic function, and improved common recognition algorithm can make the transaction handling capacity of system in the secure mode improve about 8.2%-
10.5%, system can generally reach about 350 trading processing abilities per second, better meet digital asset across mechanism
Every demand of transaction
Although specific embodiments of the present invention have been described above, it will be appreciated by those of skill in the art that these are specific
Embodiment is merely illustrative of, and those skilled in the art, can be in the case where not departing from the principle and substance of the present invention
Various omissions, substitutions and changes are carried out to the details of the above method and system.For example, merge above method step, thus according to
Substantially identical method executes substantially identical function to realize that substantially identical result then belongs to the scope of the present invention.Therefore,
The scope of the present invention is only limited by the claims that follow.
Claims (10)
1. a kind of digital asset processing method based on block chain, which comprises the following steps:
(S1) digital asset information is received；A variety of different digital asset information are received, and letter is carried out to the digital asset information
Breath fusion；
(S2) digital asset information processing；In all digital asset fuse informations, using data mining algorithm to receiving
Digital asset classify, and sorted digital asset information is stored, while using data mining algorithm again
Improve the precision of sorted information；
(S3) it is further processed using algorithm of the ant group algorithm to classification output, seeks optimal digital asset information；
(S4) by treated, data pass through Encryption Algorithm, common recognition algorithm calculating uploads to block chain；
(S5) user obtains digital asset information by block chain.
2. a kind of digital asset processing method based on block chain according to claim 1, which is characterized in that the number
The step of assets information processing are as follows:
(S21) the digital asset information is divided by same attribute using the sorting algorithm in the data mining algorithm
Class screens user from a large amount of information identical digital asset information according to categorical attribute；
(S22) the sorted digital asset information of the sorting algorithm is further learnt again using ant group algorithm, realizes number
The accurate processing of assets information obtains more accurate data.
3. a kind of digital asset processing method based on block chain according to claim 2, which is characterized in that the classification
Algorithm is any one in following algorithm: decision Tree algorithms, Cluster Classification algorithm, BP neural network algorithm, support vector machines
Algorithm, VSM method, Bayes Piao sorting algorithm or k- neighbour's element algorithm.
4. a kind of digital asset processing method based on block chain according to claim 3, which is characterized in that the cluster
Sorting algorithm is K-means clustering algorithm, wherein the step of K-means clustering algorithm are as follows:
(1) sample data is chosen in mass digital assets information, and is selected in initial cluster according to selected sample data
Heart point, in sample data, the digital assets information data of random extraction K, using the digital asset information as sample number of clusters
According to the center of set, and the threshold value T of the number of iterations is set, wherein K > 50,0 < T < 10；
(2) digital asset message sample cluster point is divided, the point of each digital asset message sample aggregate of data is divided into following number
In the point of word assets information sample cluster:
The point of cluster represented by the center nearest apart from the digital asset message sample, make the digital asset message sample with
The central point that the central point of initial cluster is nearest is divided into one kind；
Wherein, the distance between the nearest center of the digital asset message sample and the represented point of cluster formula are as follows:
；
Wherein x, y respectively indicate different digital asset message samples, and n indicates the dimension of digital asset message sample, d(x, y)
Each digital asset is calculated according to the central point of the cluster sample of each digital asset message sample for Euclidean distance
The distance between message sample and these central sample parameters, and according to minimum range by corresponding digital asset message sample
Re-start division；
(3) digital asset information sample is indicated with the central point at each sample number strong point in different digital assets information sample cluster
The central point of this sample cluster calculates every again according to the central point of different parameters data or different clustering information sample datas
A number the distance between assets information sample data central point and these clustering information data centers, and according to minimum range
Again division is re-started to respective digital assets sample data, calculated minimum data will forms matrix D every time, then are as follows:
Wherein, x is the set of the minimum value found out；
(4) it judges whether to iterate to calculate, if the number of iterations is equal to given threshold T, does not have to iterative calculation, if iteration
Number is not identical as given threshold, then repartitions digital asset message sample cluster point, and return step (2) repeats step
(2) and (3).
5. a kind of digital asset processing method based on block chain according to claim 3, which is characterized in that in the BP
During neural network algorithm calculates, in which:
Adjust the formula of output layer power system are as follows:
;
Adjust the formula of hidden layer weight coefficient are as follows:
For the accurate function model of quadratic form of the input pattern pair in each digital asset message sample are as follows:
;
For total accurate function expression of N number of digital asset message sample:
。
6. a kind of digital asset processing method based on block chain according to claim 2, which is characterized in that the ant colony
The step of algorithm are as follows:
(1) it initializes；By the digital asset information initializing of block chain, the total group y(t of initialization of digital asset information is chosen),
If y(t)=ymax, enable digital asset information as ant element, when initial, all elements of ant matrix of elements are initialized as 0,
Then the initial position of the ant element is randomly choosed；
(2) m ant element is randomly placed in n position, if the cycle-index that the ant element finds path is Nc, press
Nc+ 1 sequence is recycled；
(3) ant element taboo list call number k=1 is set, is recycled by k+1；
(4) state transition probability formula according to the following formula calculates the probability of ant selection position j；
；
Wherein, δ is visibility factor, and the visibility factor indicates that the inverse of the distance between different location, α are that pheromones are dense
Spend relatively important parameter, β is the relatively important index of visibility factor, Node be connected directly with position i and ant element still
The set of unbeaten position；
(5) selection has the position of maximum rating transition probability, ant element is moved to described general with maximum rating transfer
The position of rate, and the position is logged into taboo list；
(6) judge, if having accessed all positions in set, enable k < m, wherein m is the number of position, then is executed by k+1
Circulate operation updates the information content in each path if not accessed all positions in set；
(7) it checks termination condition, checks whether and meet termination condition, the termination condition is that ant selects the probability of position j big
In 80%, if meeting the termination condition, further operating is carried out；
(8) judge whether to form new group, if the termination condition is that ant selects the probability of position j less than 80%,
New group is formed, then Pheromone Matrix is updated again, the method for update is to recalculate minimum data matrix D；
(9) judge whether to meet and terminate genetic condition, when meeting termination genetic condition, the termination genetic condition is the ant
Ant selects the probability of position j to be greater than 80%, then exports calculated result.
7. a kind of digital asset device based on block chain, which is characterized in that described device includes:
Client receives a variety of different digital asset information, and to the digital asset information for receiving digital asset information
Carry out information fusion；
Assets information processing system is used for digital asset information processing, according to data fusion information, to the data information received
Classify, and sorted information is stored, while using data mining algorithm to the essence for improving sorted information
Degree, and be further processed by ant group algorithm model using algorithm of the ant group algorithm to classification output, seek optimal number money
Produce information；
Block platform chain handles information for receiving treated digital asset, and to treated data carry out Encryption Algorithm,
Common recognition algorithm；
Node server makes user obtain digital asset information by block chain.
8. a kind of digital asset device based on block chain according to claim 7, which is characterized in that the client collection
At having user log-in block, information management module, data inquiry module or quota control module, wherein the user log-in block
For making user obtain digital asset information；The information management module is for being arranged, transferring the digital asset information；It is described
Data inquiry module is for inquiring the digital asset information, and the quota control module is for managing the digital asset information
Capacity.
9. a kind of digital asset device based on block chain according to claim 7, which is characterized in that the assets information
Processing system includes data receipt unit, data capture unit, data storage cell, taxon and ant group algorithm model,
Described in the output end of data receipt unit connect with the input terminal of the data capture unit, the data receipt unit, number
It is connect according to acquiring unit, data storage cell, taxon and ant group algorithm model with data storage cell, the taxon
Output end connect with the input terminal of the ant group algorithm model；Wherein:
The data receipt unit is used for for obtaining digital asset information, the data capture unit from the data receiver list
Member extract digital asset sample data, the data storage cell for store the data receipt unit, data capture unit,
Taxon or ant group algorithm mode input or input information, the taxon are used for the digital asset information according to institute
The categorical attribute for stating taxon setting is sorted out, and the ant group algorithm model is used for the number for exporting the taxon
Assets information advanced optimizes.
10. a kind of digital asset device based on block chain according to claim 7, which is characterized in that the block chain
Platform is the modular tile chain solution support platform based on Hyperledger Fabric.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910581679.0A CN110287268A (en) | 2019-06-30 | 2019-06-30 | A kind of digital asset processing method and system based on block chain |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910581679.0A CN110287268A (en) | 2019-06-30 | 2019-06-30 | A kind of digital asset processing method and system based on block chain |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110287268A true CN110287268A (en) | 2019-09-27 |
Family
ID=68020265
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910581679.0A Pending CN110287268A (en) | 2019-06-30 | 2019-06-30 | A kind of digital asset processing method and system based on block chain |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110287268A (en) |
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111179074A (en) * | 2019-11-27 | 2020-05-19 | 上海源庐加佳信息科技有限公司 | Block chain evidence transaction system and method with exchange rate self-adaptive change |
| CN111597167A (en) * | 2020-05-18 | 2020-08-28 | 黄会仙 | Big data management system and method applying block chain technology |
| CN111654364A (en) * | 2020-07-06 | 2020-09-11 | 重庆知翔科技有限公司 | Method for realizing data safety communication by using block chain encryption technology |
| CN111787114A (en) * | 2020-07-06 | 2020-10-16 | 重庆知翔科技有限公司 | Novel block chain network architecture construction method |
| CN111831715A (en) * | 2020-05-25 | 2020-10-27 | 闽侯县人民检察院 | Intelligent access and certificate storage system and method based on artificial intelligence big data |
| CN111929633A (en) * | 2020-05-31 | 2020-11-13 | 宁夏隆基宁光仪表股份有限公司 | Electric energy meter detection system and method based on fusion ant colony algorithm |
| CN111949735A (en) * | 2020-08-26 | 2020-11-17 | 鲁泽军 | System and method for realizing data query by applying account book of block chain |
| CN112039855A (en) * | 2020-08-14 | 2020-12-04 | 海南大学 | Scientific and technological resource data safe storage and sharing method based on alliance chain |
| CN112699112A (en) * | 2020-12-31 | 2021-04-23 | 东莞市盟大商业保理有限公司 | Data mining process sharing method based on block chain technology |
| CN113282957A (en) * | 2021-06-03 | 2021-08-20 | 光大科技有限公司 | Data asset racking processing method and device |
| CN113283726A (en) * | 2021-05-17 | 2021-08-20 | 国网冀北电力有限公司 | Block chain asset detection, entry and evaluation system |
| CN113472513A (en) * | 2021-06-11 | 2021-10-01 | 电子科技大学 | Parallel safe multi-party computing method based on block chain |
| CN113986990A (en) * | 2021-10-26 | 2022-01-28 | 北京市科学技术情报研究所 | Data resource acquisition and labeling method and device based on block chain data mining |
| TWI764456B (en) * | 2020-12-21 | 2022-05-11 | 鴻海精密工業股份有限公司 | Method and device for block operation, computer device and storage medium |
| CN116757849A (en) * | 2023-08-14 | 2023-09-15 | 中资科技(江苏)有限公司 | Asset management system and method based on block chain |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104899229A (en) * | 2014-03-07 | 2015-09-09 | 上海市玻森数据科技有限公司 | Swarm intelligence based behavior clustering system |
| CN106875171A (en) * | 2017-01-23 | 2017-06-20 | 无锡源锐电子商务有限公司 | A kind of micro- many block chain distribution credit investigation systems and reference method |
| CN107045679A (en) * | 2017-04-06 | 2017-08-15 | 甄益权 | A kind of electronic goods inventory management system based on data mining |
| CN107103087A (en) * | 2017-05-02 | 2017-08-29 | 成都中远信电子科技有限公司 | Block chain big data analysis of market conditions system |
| US20180001184A1 (en) * | 2016-05-02 | 2018-01-04 | Bao Tran | Smart device |
| CN108521434A (en) * | 2018-05-29 | 2018-09-11 | 广西电网有限责任公司 | A kind of network security intrusion detecting system based on block chain technology |
| CN108985010A (en) * | 2018-06-15 | 2018-12-11 | 河南师范大学 | Gene sorting method and device |
| CN109614238A (en) * | 2018-12-11 | 2019-04-12 | 深圳市网心科技有限公司 | A kind of recongnition of objects method, apparatus, system and readable storage medium storing program for executing |
| CN109949881A (en) * | 2018-10-16 | 2019-06-28 | 陕西医链区块链集团有限公司 | Big data processing method and equipment based on block chain |
-
2019
- 2019-06-30 CN CN201910581679.0A patent/CN110287268A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104899229A (en) * | 2014-03-07 | 2015-09-09 | 上海市玻森数据科技有限公司 | Swarm intelligence based behavior clustering system |
| US20180001184A1 (en) * | 2016-05-02 | 2018-01-04 | Bao Tran | Smart device |
| CN106875171A (en) * | 2017-01-23 | 2017-06-20 | 无锡源锐电子商务有限公司 | A kind of micro- many block chain distribution credit investigation systems and reference method |
| CN107045679A (en) * | 2017-04-06 | 2017-08-15 | 甄益权 | A kind of electronic goods inventory management system based on data mining |
| CN107103087A (en) * | 2017-05-02 | 2017-08-29 | 成都中远信电子科技有限公司 | Block chain big data analysis of market conditions system |
| CN108521434A (en) * | 2018-05-29 | 2018-09-11 | 广西电网有限责任公司 | A kind of network security intrusion detecting system based on block chain technology |
| CN108985010A (en) * | 2018-06-15 | 2018-12-11 | 河南师范大学 | Gene sorting method and device |
| CN109949881A (en) * | 2018-10-16 | 2019-06-28 | 陕西医链区块链集团有限公司 | Big data processing method and equipment based on block chain |
| CN109614238A (en) * | 2018-12-11 | 2019-04-12 | 深圳市网心科技有限公司 | A kind of recongnition of objects method, apparatus, system and readable storage medium storing program for executing |
Non-Patent Citations (1)
| Title |
|---|
| 崔亮: "基于蚁群算法的遥感图像分类研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111179074A (en) * | 2019-11-27 | 2020-05-19 | 上海源庐加佳信息科技有限公司 | Block chain evidence transaction system and method with exchange rate self-adaptive change |
| CN111597167A (en) * | 2020-05-18 | 2020-08-28 | 黄会仙 | Big data management system and method applying block chain technology |
| CN111831715A (en) * | 2020-05-25 | 2020-10-27 | 闽侯县人民检察院 | Intelligent access and certificate storage system and method based on artificial intelligence big data |
| CN111929633A (en) * | 2020-05-31 | 2020-11-13 | 宁夏隆基宁光仪表股份有限公司 | Electric energy meter detection system and method based on fusion ant colony algorithm |
| CN111654364A (en) * | 2020-07-06 | 2020-09-11 | 重庆知翔科技有限公司 | Method for realizing data safety communication by using block chain encryption technology |
| CN111787114A (en) * | 2020-07-06 | 2020-10-16 | 重庆知翔科技有限公司 | Novel block chain network architecture construction method |
| CN112039855B (en) * | 2020-08-14 | 2022-03-08 | 海南大学 | Scientific and technological resource data safe storage and sharing method based on alliance chain |
| CN112039855A (en) * | 2020-08-14 | 2020-12-04 | 海南大学 | Scientific and technological resource data safe storage and sharing method based on alliance chain |
| CN111949735A (en) * | 2020-08-26 | 2020-11-17 | 鲁泽军 | System and method for realizing data query by applying account book of block chain |
| TWI764456B (en) * | 2020-12-21 | 2022-05-11 | 鴻海精密工業股份有限公司 | Method and device for block operation, computer device and storage medium |
| CN112699112A (en) * | 2020-12-31 | 2021-04-23 | 东莞市盟大商业保理有限公司 | Data mining process sharing method based on block chain technology |
| CN112699112B (en) * | 2020-12-31 | 2024-02-06 | 东莞盟大集团有限公司 | Data mining flow sharing method based on blockchain technology |
| CN113283726A (en) * | 2021-05-17 | 2021-08-20 | 国网冀北电力有限公司 | Block chain asset detection, entry and evaluation system |
| CN113282957A (en) * | 2021-06-03 | 2021-08-20 | 光大科技有限公司 | Data asset racking processing method and device |
| CN113472513A (en) * | 2021-06-11 | 2021-10-01 | 电子科技大学 | Parallel safe multi-party computing method based on block chain |
| CN113472513B (en) * | 2021-06-11 | 2023-08-25 | 电子科技大学 | Parallel secure multiparty computing method based on block chain |
| CN113986990A (en) * | 2021-10-26 | 2022-01-28 | 北京市科学技术情报研究所 | Data resource acquisition and labeling method and device based on block chain data mining |
| CN113986990B (en) * | 2021-10-26 | 2022-05-10 | 北京市科学技术情报研究所 | Data resource acquisition and labeling method and device based on block chain data mining |
| CN116757849A (en) * | 2023-08-14 | 2023-09-15 | 中资科技(江苏)有限公司 | Asset management system and method based on block chain |
| CN116757849B (en) * | 2023-08-14 | 2023-10-20 | 中资科技(江苏)有限公司 | Asset management system and method based on block chain |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110287268A (en) | A kind of digital asset processing method and system based on block chain | |
| CN111598186B (en) | Decision model training method, prediction method and device based on longitudinal federal learning | |
| Liu et al. | Keep your data locally: Federated-learning-based data privacy preservation in edge computing | |
| CN112949837A (en) | Target recognition federal deep learning method based on trusted network | |
| CN112101403B (en) | Classification method and system based on federal few-sample network model and electronic equipment | |
| CN112101404B (en) | Image classification method and system based on generation countermeasure network and electronic equipment | |
| CN110544528B (en) | Advanced learning-based upper and lower ophthalmic remote diagnosis platform and construction method thereof | |
| CN114580663A (en) | Data non-independent same-distribution scene-oriented federal learning method and system | |
| US11917060B2 (en) | Apparatus and methods for mapping user-associated data to an identifier | |
| CN111949735A (en) | System and method for realizing data query by applying account book of block chain | |
| Gong et al. | Adaptive clustered federated learning for heterogeneous data in edge computing | |
| US11573986B1 (en) | Apparatuses and methods for the collection and storage of user identifiers | |
| Chiaro et al. | FL-Enhance: A federated learning framework for balancing non-IID data with augmented and shared compressed samples | |
| US20230252416A1 (en) | Apparatuses and methods for linking action data to an immutable sequential listing identifier of a user | |
| CN116186754A (en) | Federal random forest power data collaborative analysis method based on blockchain | |
| Li et al. | Multi-attribute feature fusion algorithm for blockchain communications in healthcare systems using machine intelligence | |
| Mu et al. | FedDMC: Efficient and Robust Federated Learning via Detecting Malicious Clients | |
| Islam et al. | FedClust: Optimizing Federated Learning on Non-IID Data through Weight-Driven Client Clustering | |
| Chen et al. | Advances in Robust Federated Learning: Heterogeneity Considerations | |
| US11683174B1 (en) | Apparatus and methods for selectively revealing data | |
| US20230252098A1 (en) | Apparatus and methods for expanding contacts for a social networking platform | |
| CN115169590A (en) | Industrial Internet of things equipment participation federal learning method based on edge calculation and transfer learning | |
| Karim et al. | Implementing federated learning based on rainforest model | |
| Guan et al. | DCIGAN: a distributed class-incremental learning method based on generative adversarial networks | |
| CN107742140B (en) | Intelligent identity information identification method based on RFID technology |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190927 |
|
| RJ01 | Rejection of invention patent application after publication |