CN111680099A - Block chain consensus method and system based on decision tree model training - Google Patents
Block chain consensus method and system based on decision tree model training Download PDFInfo
- Publication number
- CN111680099A CN111680099A CN202010318931.1A CN202010318931A CN111680099A CN 111680099 A CN111680099 A CN 111680099A CN 202010318931 A CN202010318931 A CN 202010318931A CN 111680099 A CN111680099 A CN 111680099A
- Authority
- CN
- China
- Prior art keywords
- decision tree
- tree model
- data
- node
- block
- 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.)
- Granted
Links
Images
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
- G06F16/27—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
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/24323—Tree-organised classifiers
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q20/00—Payment architectures, schemes or protocols
- G06Q20/38—Payment protocols; Details thereof
- G06Q20/382—Payment protocols; Details thereof insuring higher security of transaction
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Abstract
The invention discloses a block chain consensus method and a system based on decision tree model training, wherein the system comprises a consensus algorithm scheduler, a parameter and data acquirer, a decision tree model trainer and a consensus verifier; the system can be butted with the existing block chain system to replace common recognition algorithms such as POW/POS/POA and the like. The invention introduces the excessive calculation power of the block chain into the training of the decision tree model, and leads investors to use the mining machine for training the artificial intelligent model through the excitation mechanism of the block chain, thereby being capable of guiding capital, calculation power and energy to be put into more meaningful work and solving the problems of insufficient calculation power and high cost. The invention uses the POW calculation power of the block chain to carry out decision tree calculation of big data, thereby reducing the cost, saving social resources and using the calculation power to meaningful work.
Description
Technical Field
The invention relates to the technical field of block chains, in particular to a block chain consensus method and system based on decision tree model training.
Background
The development of the block chain technology is generally agreed by enterprises, research institutions, universities and the like at home and abroad, and is considered as the core of the next generation of valuable internet. The main stream block chain platform bit currency, Ethengfang, Laite currency and the like generally adopt a POW consensus algorithm, and determine the nodes of the block by repeatedly performing hash value operation by an ore machine, wherein the node has higher input calculation power and has higher probability to obtain block reward. This mechanism enables trust establishment and value consensus to be achieved through machines and algorithms, investors invest a lot of money to buy mining machines and power, the computing power of a whole bitcoin network has reached 70EH/S by 2019 and 9 months, the computing power and energy are used by investors to perform hash value operation so as to obtain rewards, and the computing power and energy waste in this mode are very serious and problematic.
Decision Tree (Decision Tree) is a Decision analysis method for evaluating the risk of a project and judging the feasibility of the project by constructing a Decision Tree to obtain the probability that the expected value of the net present value is greater than or equal to zero on the basis of the known occurrence probability of various conditions, and is a graphical method for intuitively applying probability analysis. This decision branch is called a decision tree because it is drawn to resemble a branch of a tree. In machine learning, a decision tree is a predictive model that represents a mapping between object attributes and object values.
The mainstream block chain generally adopts consensus algorithms such as POW (point of sale) and the like to determine block nodes, so that the problem of energy and computational complexity waste exists.
Disclosure of Invention
In view of this, in order to solve the problem that the consensus algorithm of the block chain in the prior art wastes energy and computational power, the invention provides a block chain consensus method and system based on decision tree model training.
The invention solves the problems through the following technical means:
in one aspect, the invention provides a block chain consensus method based on decision tree model training, comprising the following steps:
the main body generates big data acquisition information and sends the big data acquisition information to the node, and the node broadcasts the big data acquisition information to the adjacent nodes;
calculating and verifying by adopting a decision tree model training consensus algorithm, verifying the effectiveness of big data acquisition information by using a node, and putting the node into a buffer pool until the number n of data sets A in the buffer pool reaches a threshold value alpha;
node acquires all big data collection stored on chain by parameter and data acquirerThe information Z is merged with the current data set A in the buffer pool to generate D, and the items contained in D are mapped to the matrix MnpThe above step (1); respectively calculating A by adopting a decision tree algorithmj(1. ltoreq. j. ltoreq.p) as classification class, { A1，A2，…Aj-1，Aj+1，…ApTaking the decision tree as a characteristic attribute;
the node completes calculation of a decision tree model, stores parameters of the decision tree model in a block head, generates a first block coinage transaction for recording the node to obtain an accounting reward, generates n data acquisition transactions and other transfer transactions from a data set A, packs the n data acquisition transactions and other transfer transactions into a block body, combines the block head and the block body to generate a block and broadcasts the block in a whole network;
other nodes receive the information of the new block, and the common identification verifier verifies the new block; when a decision tree model is adopted, all big data acquisition information Z stored on a chain is acquired by a node through a parameter and data acquirer and is merged with a current data set B in a buffer pool of the node to generate D', and the decision tree model is used for predicting A in DjCarrying out classification accuracy, and verifying whether the accuracy is greater than the parameter requirement; if the accuracy parameter index is reached, the block is placed in the local block chain.
Further, before the calculation and verification are performed by adopting the decision tree model training consensus algorithm, the method further comprises the following steps:
and the node 'consensus algorithm scheduler' selects a consensus algorithm, if the consensus algorithm is trained by the decision tree model, the decision tree model training consensus algorithm is adopted for calculation and verification, and otherwise, the traditional block chain consensus algorithm is adopted for calculation and verification.
Further, data information is directly stored on the block chain in a data contribution transaction mode, and the form of the data contribution transaction is expressed as { a subject wallet address, a data acquisition reward amount and data information }; or the data information is combed and sorted and then put into an external data storage system, and a resource locator for data storage is returned.
Further, if the underlying block chain is based on the block chain of bitcoin and Lei-Tech, a new data contribution transaction type is expanded, wherein the 'data information' is stored by adopting a reserved field in bitcoin transaction; if the block chain platform with the intelligent contract mechanism is based on the Etherns and the EOS, the data information is packaged to serve as parameters and is called for the method of the intelligent contract, when the data information passes the verification of the intelligent contract, the intelligent contract is used for transferring accounts to the main wallet address, and the amount is the data acquisition reward amount.
Further, the threshold α is voted by all node participants by means of a smart contract, and the accuracy parameter is voted by all node participants by means of a smart contract.
Further, the decision tree is calculated using ID3, C4.5, C5.0, or an extended algorithm.
In another aspect, the present invention provides a block chain consensus system based on decision tree model training, including:
the parameter and data acquirer is used for generating big data acquisition information by the main body and sending the big data acquisition information to the node, and the node broadcasts the big data acquisition information to the adjacent node;
a decision tree model trainer for calculating and verifying by adopting a decision tree model training consensus algorithm, a node verifying the effectiveness of big data acquisition information and putting the big data acquisition information into a buffer pool until the number n of data sets A in the buffer pool reaches a threshold value α, a node acquiring all the big data acquisition information Z stored on a chain by using a parameter and data acquirer and merging the big data acquisition information Z with the current data set A in the buffer pool to generate a D, and mapping items contained in the D to a matrix MnpThe above step (1); respectively calculating A by adopting a decision tree algorithmj(1. ltoreq. j. ltoreq.p) as classification class, { A1，A2，…Aj-1，Aj+1，…ApTaking the decision tree as a characteristic attribute; the node completes calculation of a decision tree model, parameters of the decision tree model are stored in a block head, a first block coinage transaction is generated and used for recording the node to obtain an accounting reward, and meanwhile, a data set A generates n data acquisition transactions and packs the data acquisition transactions and other transfer transactions togetherForming a block body, combining the block head and the block body to generate a block and carrying out whole-network broadcasting;
the consensus verifier is used for verifying the new block by the other nodes after receiving the information of the new block; when a decision tree model is adopted, all big data acquisition information Z stored on a chain is acquired by a node through a parameter and data acquirer and is merged with a current data set B in a buffer pool of the node to generate D', and the decision tree model is used for predicting A in DjCarrying out classification accuracy, and verifying whether the accuracy is greater than the parameter requirement; if the accuracy parameter index is reached, the block is placed in the local block chain.
Further, the block chain consensus system trained based on the decision tree model further includes:
and (4) scheduling a consensus algorithm, wherein the consensus algorithm is used for node selection, if the consensus algorithm is trained for the decision tree model, the decision tree model consensus algorithm is adopted for calculation and verification, and otherwise, the traditional block chain consensus algorithm is adopted for calculation and verification.
Further, data information is directly stored on the block chain in a data contribution transaction mode, and the form of the data contribution transaction is expressed as { a subject wallet address, a data acquisition reward amount and data information }; or the data information is combed and sorted and then is put into an external data storage system, and a resource locator for data storage is returned;
if the underlying layer block chain is based on the block chain of the bitcoin and the Leitexin, a new data contribution transaction type is expanded, and the 'data information' is stored by adopting a reserved field in the bitcoin transaction; if the block chain platform with the intelligent contract mechanism is based on the Etherns and the EOS, the data information is packaged to serve as parameters and is called for the method of the intelligent contract, when the data information passes the verification of the intelligent contract, the intelligent contract is used for transferring accounts to the main wallet address, and the amount is the data acquisition reward amount.
Further, the decision tree is calculated by using ID3, C4.5, C5.0 or an extended algorithm, the threshold α is voted by all node participants by means of an intelligent contract, and the accuracy parameter is voted by all node participants by means of an intelligent contract.
Compared with the prior art, the invention has the beneficial effects that at least:
the invention provides a method for mining the big data decision tree models as block chain consensus achievement aiming at personal big data, enterprise big data, environment big data and the like, and can apply the calculation power to valuable model mining.
The invention introduces the excessive calculation power of the block chain into the training of the decision tree model, and leads investors to use the mining machine for training the artificial intelligent model through the excitation mechanism of the block chain, thereby being capable of guiding capital, calculation power and energy to be put into more meaningful work and solving the problems of insufficient calculation power and high cost.
The invention uses the POW calculation power of the block chain to carry out decision tree calculation of big data, thereby reducing the cost, saving social resources and using the calculation power to meaningful work.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
FIG. 1 is a flow chart of a block chain consensus method based on decision tree model training according to the present invention;
FIG. 2 is a schematic structural diagram of a block chain consensus system based on decision tree model training according to the present invention.
Detailed Description
In order to make the aforementioned objects, features and advantages of the present invention comprehensible, embodiments accompanied with figures are described in detail below. It should be noted that the described embodiments are only a part of the embodiments of the present invention, and not all embodiments, and all other embodiments obtained by those skilled in the art without any inventive work based on the embodiments of the present invention belong to the protection scope of the present invention.
Example 1
As shown in fig. 1, the present invention provides a block chain consensus method based on decision tree model training, which comprises the following steps:
step S110: the main body generates big data acquisition information and sends the big data acquisition information to the nodes, and the nodes broadcast the information to adjacent nodes. Data information is directly stored on the blockchain in a data contribution transaction mode, and the form of the data contribution transaction can be expressed as { a subject wallet address, a data acquisition reward amount and data information }.
If the underlying layer block chain is based on the block chains of bitcoin, Leitexin and the like, a new data contribution transaction type is expanded, and the 'data information' can be stored by adopting a reserved field in bitcoin transaction; if the intelligent contract is based on a blockchain platform with an intelligent contract mechanism, such as an Ethernet, EOS and the like, the data information is packaged to be used as a parameter and used for calling a method of the intelligent contract, when the data information passes the verification of the intelligent contract, the intelligent contract is used for transferring accounts to a main wallet address, and the amount is the data acquisition reward amount.
Alternatively, the data information may be sorted and then put into an external data storage system, and a resource locator for data storage is returned.
Step S120: and (4) selecting a consensus algorithm by the node 'consensus algorithm scheduler', jumping to the step S130 if the consensus algorithm is trained for the decision tree model, and otherwise, calculating and verifying by adopting a traditional block chain consensus algorithm.
Step S130: and the node verifies the validity of the data acquisition information and puts the data acquisition information into the buffer pool until the number n of the data sets A in the buffer pool reaches a threshold value alpha. The threshold α may be voted by all node participants by way of intelligent contracts or the like.
Step S140: the node acquires all big data acquisition messages stored on the chain by using a parameter and data acquirerZ, merging the Z with the current data set A in the buffer pool to generate D, and mapping the items contained in D to a matrix MnpAs shown in table 1. Respectively calculating A by adopting a decision tree algorithmj(1. ltoreq. j. ltoreq.p) as classification class, { A1，A2，…Aj-1，Aj+1，…ApAs a feature attribute decision tree. The decision tree is calculated by using algorithms such as ID3, C4.5, C5.0 or an extended algorithm.
TABLE 1 matrix MnpExamples of the invention
Note: the data source is not limited to personal big data, enterprise big data, environment big data and the like. In this example, the attributes of the matrix column are not limited to use with application apps, and may be extended to any personal big data such as "walk every day," "buy XX stock," and so on.
Step S150: the node completes calculation of the decision tree model, the parameters of the decision tree model are stored in a block head, a first block coinage transaction is generated and used for recording the node to obtain an accounting reward, meanwhile, the data set A generates n data acquisition transactions and other transfer transactions to be packed into a block body, the block head and the block body are combined to generate a block, and the block is broadcasted in the whole network.
Step S160: the other nodes receive the information of the new block, and the consensus verifier verifies the new block. When a decision tree model is adopted, all big data acquisition information Z stored on a chain is acquired by a node through a parameter and data acquirer and is merged with a current data set B in a buffer pool of the node to generate D', and the decision tree model is used for predicting A in DjAnd (5) carrying out classification accuracy, and verifying whether the accuracy is greater than the parameter requirement. If the accuracy parameter index is reached, the block is placed in the local block chain. The accuracy parameter can be determined by intelligenceThe decision of voting by all node participants can be agreed and the like.
Example 2
As shown in fig. 2, the present invention further provides a block chain consensus system based on decision tree model training, which includes a parameter and data acquirer, a consensus algorithm scheduler, a decision tree model trainer, and a consensus verifier.
And the parameter and data acquirer is used for generating big data acquisition information by the main body and sending the big data acquisition information to the nodes, and the nodes broadcast the information to the adjacent nodes. Data information is directly stored on the blockchain in a data contribution transaction mode, and the form of the data contribution transaction can be expressed as { a subject wallet address, a data acquisition reward amount and data information }.
If the underlying layer block chain is based on the block chains of bitcoin, Leitexin and the like, a new data contribution transaction type is expanded, and the 'data information' can be stored by adopting a reserved field in bitcoin transaction; if the intelligent contract is based on a blockchain platform with an intelligent contract mechanism, such as an Ethernet, EOS and the like, the data information is packaged to be used as a parameter and used for calling a method of the intelligent contract, when the data information passes the verification of the intelligent contract, the intelligent contract is used for transferring accounts to a main wallet address, and the amount is the data acquisition reward amount.
Alternatively, the data information may be sorted and then put into an external data storage system, and a resource locator for data storage is returned.
And the consensus algorithm scheduler is used for selecting a consensus algorithm for the nodes, if the consensus algorithm is trained by the decision tree model, calculating and verifying by adopting the decision tree model training consensus algorithm, and otherwise, calculating and verifying by adopting the traditional block chain consensus algorithm.
And the decision tree model trainer is used for verifying the validity of the data acquisition information by the nodes and putting the data acquisition information into the buffer pool until the number n of the data sets A in the buffer pool reaches a threshold value alpha. The threshold α may be voted by all node participants by way of intelligent contracts or the like.
Node acquisition chain with parameter and data acquirerAll the stored big data acquisition information Z is merged with the current data set A in the buffer pool to generate D, and the items contained in D are mapped to the matrix MnpAs shown in table 1. Respectively calculating A by adopting a decision tree algorithmj(1. ltoreq. j. ltoreq.p) as classification class, { A1，A2，…Aj-1，Aj+1，…ApAs a feature attribute decision tree. The decision tree is calculated by using algorithms such as ID3, C4.5, C5.0 or an extended algorithm.
TABLE 1 matrix MnpExamples of the invention
Note: the data source is not limited to personal big data, enterprise big data, environment big data and the like. In this example, the attributes of the matrix column are not limited to use with application apps, and may be extended to any personal big data such as "walk every day," "buy XX stock," and so on.
The node completes calculation of the decision tree model, the parameters of the decision tree model are stored in a block head, a first block coinage transaction is generated and used for recording the node to obtain an accounting reward, meanwhile, the data set A generates n data acquisition transactions and other transfer transactions to be packed into a block body, the block head and the block body are combined to generate a block, and the block is broadcasted in the whole network.
And the consensus verifier is used for verifying the new block by the other nodes after receiving the information of the new block. When a decision tree model is adopted, all big data acquisition information Z stored on a chain is acquired by a node through a parameter and data acquirer and is merged with a current data set B in a buffer pool of the node to generate D', and the decision tree model is used for predicting A in DjAnd (5) carrying out classification accuracy, and verifying whether the accuracy is greater than the parameter requirement. If the accuracy parameter index is reached, the block is placed in the local block chain. The accuracy parameter can be voted and decided by all node participants through intelligent contract and other ways.
The invention provides a method and a system for achieving block chain node consensus by adopting a decision tree, which are divided into a consensus algorithm scheduler, a parameter and data acquirer, a decision tree model trainer and a consensus verifier. The system can be butted with the existing block chain system to replace common recognition algorithms such as POW/POS/POA and the like.
The invention provides a method for mining the big data decision tree models as block chain consensus achievement aiming at personal big data, enterprise big data, environment big data and the like, and can apply the calculation power to valuable model mining.
The invention introduces the excessive calculation power of the block chain into the training of the decision tree model, and leads investors to use the mining machine for training the artificial intelligent model through the excitation mechanism of the block chain, thereby being capable of guiding capital, calculation power and energy to be put into more meaningful work and solving the problems of insufficient calculation power and high cost.
The invention uses the POW calculation power of the block chain to carry out decision tree calculation of big data, thereby reducing the cost, saving social resources and using the calculation power to meaningful work.
The above-mentioned embodiments only express several embodiments of the present invention, and the description thereof is more specific and detailed, but not construed as limiting the scope of the present invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the inventive concept, which falls within the scope of the present invention. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (10)
1. A block chain consensus method based on decision tree model training is characterized by comprising the following steps:
the main body generates big data acquisition information and sends the big data acquisition information to the node, and the node broadcasts the big data acquisition information to the adjacent nodes;
calculating and verifying by adopting a decision tree model training consensus algorithm, verifying the effectiveness of big data acquisition information by using a node, and putting the node into a buffer pool until the number n of data sets A in the buffer pool reaches a threshold value alpha;
the node acquires all big data acquisition information Z stored on the chain by using the parameter and data acquirer, combines the big data acquisition information Z with the current data set A in the buffer pool to generate a D, and maps the items contained in the D to a matrix MnpThe above step (1); respectively calculating A by adopting a decision tree algorithmj(1. ltoreq. j. ltoreq.p) as classification class, { A1，A2，…Aj-1，Aj+1，…ApTaking the decision tree as a characteristic attribute;
the node completes calculation of a decision tree model, stores parameters of the decision tree model in a block head, generates a first block coinage transaction for recording the node to obtain an accounting reward, generates n data acquisition transactions and other transfer transactions from a data set A, packs the n data acquisition transactions and other transfer transactions into a block body, combines the block head and the block body to generate a block and broadcasts the block in a whole network;
the other nodes receive the information of the new block, and the consensus verifier verifies the new block; when a decision tree model is adopted, all big data acquisition information Z stored on a chain is acquired by a node through a parameter and data acquirer and is combined with a current data set B in a buffer pool of the node to generate D', and the decision tree model is used for predicting A in DjCarrying out classification accuracy, and verifying whether the accuracy is greater than the parameter requirement; if the accuracy parameter index is reached, the block is placed in the local block chain.
2. The block chain consensus method based on decision tree model training of claim 1, wherein before performing the calculation and verification using the decision tree model training consensus algorithm, further comprising:
and selecting a consensus algorithm by the node consensus algorithm scheduler, if the consensus algorithm is trained by the decision tree model, calculating and verifying by adopting the decision tree model training consensus algorithm, and otherwise, calculating and verifying by adopting a traditional block chain consensus algorithm.
3. The decision tree model training-based blockchain consensus method according to claim 1, wherein data information is directly stored on the blockchain in a data contribution transaction form expressed as { subject wallet address, data collection reward amount, data information }; or the data information is combed and sorted and then put into an external data storage system, and a resource locator for data storage is returned.
4. The block chain consensus method based on decision tree model training as claimed in claim 1, wherein the underlying block chain, if based on bitcoin and leybu block chains, will expand new data contribution transaction types, where data information is stored using reserved fields in bitcoin transactions; if the intelligent contract is a blockchain platform with an intelligent contract mechanism based on the Etherns and the EOS, the data information is packaged to be used as a parameter and used for calling a method of the intelligent contract, when the data information passes the verification of the intelligent contract, the account is transferred to the address of a main wallet through the intelligent contract, and the amount is the data acquisition reward amount.
5. The decision tree model training-based block chain consensus method according to claim 1, wherein the threshold α is voted by all node participants by means of an intelligent contract, and the accuracy parameter is voted by all node participants by means of an intelligent contract.
6. The block chain consensus method based on decision tree model training of claim 1, wherein the decision tree is calculated using ID3, C4.5, C5.0, or an extended algorithm.
7. A block chain consensus system based on decision tree model training, comprising:
the parameter and data acquirer is used for generating big data acquisition information by the main body and sending the big data acquisition information to the node, and the node broadcasts the big data acquisition information to the adjacent node;
a decision tree model trainer for calculating and verifying by adopting a decision tree model training consensus algorithm and verifying nodesThe validity of the big data acquisition information is put into a buffer pool until the number n of the data sets A in the buffer pool reaches a threshold value α, all the big data acquisition information Z stored on the chain is acquired by the node through the parameter and data acquirer and is merged with the current data set A in the buffer pool to generate D, and the items contained in D are mapped to a matrix MnpThe above step (1); respectively calculating A by adopting a decision tree algorithmj(1. ltoreq. j. ltoreq.p) as classification class, { A1，A2，…Aj-1，Aj+1，…ApTaking the decision tree as a characteristic attribute; the node completes calculation of a decision tree model, stores parameters of the decision tree model in a block head, generates a first block coinage transaction for recording the node to obtain an accounting reward, generates n data acquisition transactions and other transfer transactions from a data set A, packs the n data acquisition transactions and other transfer transactions into a block body, combines the block head and the block body to generate a block and broadcasts the block in a whole network;
the consensus verifier is used for verifying the new block by the other nodes after receiving the information of the new block; when a decision tree model is adopted, all big data acquisition information Z stored on a chain is acquired by a node through a parameter and data acquirer and is combined with a current data set B in a buffer pool of the node to generate D', and the decision tree model is used for predicting A in DjCarrying out classification accuracy, and verifying whether the accuracy is greater than the parameter requirement; if the accuracy parameter index is reached, the block is placed in the local block chain.
8. The decision tree model training-based blockchain consensus system of claim 7, wherein the decision tree model training-based blockchain consensus system further comprises:
and (4) scheduling a consensus algorithm, wherein the consensus algorithm is used for node selection, if the consensus algorithm is trained for the decision tree model, the decision tree model consensus algorithm is adopted for calculation and verification, and otherwise, the traditional block chain consensus algorithm is adopted for calculation and verification.
9. The decision tree model training-based blockchain consensus system of claim 7, wherein data information is directly stored on the blockchain in a form of data contribution transactions expressed as { subject wallet address, data collection reward amount, data information }; or the data information is combed and sorted and then is put into an external data storage system, and a resource locator for data storage is returned;
if the underlying layer block chain is based on the block chain of the bitcoin and the Leitexin, a new data contribution transaction type is expanded, and data information is stored by adopting a reserved field in bitcoin transaction; if the intelligent contract is a blockchain platform with an intelligent contract mechanism based on the Etherns and the EOS, the data information is packaged to be used as a parameter and used for calling a method of the intelligent contract, when the data information passes the verification of the intelligent contract, the account is transferred to the address of a main wallet through the intelligent contract, and the amount is the data acquisition reward amount.
10. The decision tree model training-based block chain consensus system as claimed in claim 7, wherein the decision tree is calculated using ID3, C4.5, C5.0 or an extended algorithm, the threshold α is voted by all node participants by means of an intelligent contract, and the accuracy parameter is voted by all node participants by means of an intelligent contract.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010318931.1A CN111680099B (en) | 2020-04-21 | 2020-04-21 | Block chain consensus method and system based on decision tree model training |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010318931.1A CN111680099B (en) | 2020-04-21 | 2020-04-21 | Block chain consensus method and system based on decision tree model training |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111680099A true CN111680099A (en) | 2020-09-18 |
| CN111680099B CN111680099B (en) | 2023-08-22 |
Family
ID=72451843
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010318931.1A Active CN111680099B (en) | 2020-04-21 | 2020-04-21 | Block chain consensus method and system based on decision tree model training |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111680099B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106656798A (en) * | 2016-12-30 | 2017-05-10 | 先锋支付有限公司 | Method for computing decision path and distributed nodes |
| CN107864198A (en) * | 2017-11-07 | 2018-03-30 | 济南浪潮高新科技投资发展有限公司 | A kind of block chain common recognition method based on deep learning training mission |
| CN108323200A (en) * | 2018-01-25 | 2018-07-24 | 深圳前海达闼云端智能科技有限公司 | Data training method and device based on block chain, storage medium and block chain link points |
| CN109729168A (en) * | 2018-12-31 | 2019-05-07 | 浙江成功软件开发有限公司 | A kind of data share exchange system and method based on block chain |
| US20200027005A1 (en) * | 2018-07-18 | 2020-01-23 | Salesforce.Com, Inc. | Systems and methods for accelerating execution of processes based on artificial intelligence (ai) prediction of blockchain consensus |
-
2020
- 2020-04-21 CN CN202010318931.1A patent/CN111680099B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106656798A (en) * | 2016-12-30 | 2017-05-10 | 先锋支付有限公司 | Method for computing decision path and distributed nodes |
| CN107864198A (en) * | 2017-11-07 | 2018-03-30 | 济南浪潮高新科技投资发展有限公司 | A kind of block chain common recognition method based on deep learning training mission |
| CN108323200A (en) * | 2018-01-25 | 2018-07-24 | 深圳前海达闼云端智能科技有限公司 | Data training method and device based on block chain, storage medium and block chain link points |
| US20200027005A1 (en) * | 2018-07-18 | 2020-01-23 | Salesforce.Com, Inc. | Systems and methods for accelerating execution of processes based on artificial intelligence (ai) prediction of blockchain consensus |
| CN109729168A (en) * | 2018-12-31 | 2019-05-07 | 浙江成功软件开发有限公司 | A kind of data share exchange system and method based on block chain |
Non-Patent Citations (4)
| Title |
|---|
| MOHAMMAD JABED MORSHED CHOWDHURY等: "Blockchain versus Database：a critical analysis" * |
| 戴安博;陈恭亮;: "POW区块链共识算法分析与展望" * |
| 袁勇;倪晓春;曾帅;王飞跃;: "区块链共识算法的发展现状与展望" * |
| 黄宇翔: "区块链中基于C4.5决策树的PBFT共识算法性能优化研究" * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111680099B (en) | 2023-08-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2020253775A1 (en) | Method and system for realizing machine learning modeling process | |
| CN111680793B (en) | Block chain consensus method and system based on deep learning model training | |
| WO2021147486A1 (en) | Data processing method and apparatus | |
| CN110751261A (en) | Training method and system and prediction method and system of neural network model | |
| CN108804512A (en) | Generating means, method and the computer readable storage medium of textual classification model | |
| CN111259772B (en) | Image labeling method, device, equipment and medium | |
| US20100332281A1 (en) | Task allocation mechanisms and markets for acquiring and harnessing sets of human and computational resources for sensing, effecting, and problem solving | |
| CN111681091B (en) | Financial risk prediction method and device based on time domain information and storage medium | |
| CN110458540B (en) | Contribution-based random signature consensus mechanism algorithm | |
| Lou et al. | Ponzi contracts detection based on improved convolutional neural network | |
| CN111680098A (en) | Block chain system for data acquisition, data annotation, AI model training and verification | |
| CN112541817A (en) | Marketing response processing method and system for potential customers of personal consumption loan | |
| CN111680076A (en) | Block chain consensus method and system based on association rule model training | |
| CN110597984B (en) | Method and device for determining abnormal behavior user information, storage medium and terminal | |
| Bastiani et al. | Portfolio optimization from a set of preference ordered projects using an ant colony based multi-objective approach | |
| CN111680099A (en) | Block chain consensus method and system based on decision tree model training | |
| Levchenko et al. | Methodological fundamentals of support of scientific and educational institutions through targeted capital investments | |
| Wu et al. | Efficient LLM inference solution on Intel GPU | |
| KR102244705B1 (en) | Method for controlling worker inflow into project by reversal adjustment of work unit price between crowdsourcing based similar projects for training data generation | |
| CN111178535B (en) | Method and apparatus for implementing automatic machine learning | |
| CN113656702B (en) | User behavior prediction method and device | |
| Lv et al. | Distributed computing to blockchain: Architecture, technology, and applications | |
| Krawczyk | Cryptocurrency Price Evolution Analysis in relation with Complex Social Phenomenons and Network Effects | |
| CN117078443A (en) | Real-time account checking method and device | |
| CN117788139A (en) | Training method and device for information output model, computer equipment and storage medium |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |